From 8c547d73af01d2e473a965555fefa8dcab16d6c1 Mon Sep 17 00:00:00 2001
From: vitya <vitya.kuznetsov@gmail.com>
Date: Tue, 5 May 2026 21:21:19 +0300
Subject: [PATCH] feat(project-bootstrap): generic Step 5.6 skill-deps check

Collapse Step 5.6 from a single-skill detector (only the
superpowers@claude-plugins-official plugin) into a generic
`trigger -> fulfiller` table walker that scales to every canonical
CLAUDE.md trigger.

Inline 9-row map in SKILL.md covers: caveman, superpowers (kind: plugin),
using-wiki, using-tasks, using-projects-meta, pulling-before-work,
project-discipline, using-interns, active-platform. The `kind` flag
(skill | plugin) drives which install command is emitted in the chat-only
recommendation block. Detection paths: ~/.claude/skills/<name>/SKILL.md
for skills, plugins.<id> in ~/.claude/plugins/installed_plugins.json
for plugins.

Algorithm: read project's CLAUDE.md -> match each non-comment line vs
map (substring + tolower, mirrors Step 5 idempotent merge) -> for each
canonical match check disk -> print one chat block listing every missing
fulfiller with copy-pasteable install commands, OR a single
"all dependencies satisfied" line. User-custom lines and removed
canonical lines are silently skipped. Hard rule "never auto-install"
preserved verbatim.

version: 1.6.0 -> 1.7.0 (MINOR per project-discipline Rule 3 -- adds
capability, absorbs prior superpowers-only detector cleanly).

Closes [bootstrap-skill-deps-check] (.tasks/STATUS.md done).
Closes [bootstrap-recommend-projects-meta] by absorption -- the deferred
mirror task was the seed of this generalization; the generic walker now
handles using-projects-meta along with everything else, no per-skill
mirror needed.

Design rationale at .wiki/concepts/bootstrap-skill-deps-check.md:
- why generic over per-skill mirrors (5x mirror explosion)
- skill vs plugin kind distinction
- MCP-server-backed skills (only check using-X policy skill;
  setup-X self-fires via Prerequisites pointer)
- source-of-truth invariant: SKILL map + assets/CLAUDE.md.template
  must stay in sync (a future CI lint could enforce)
---
 .tasks/STATUS.md                             |  21 ++--
 .tasks/bootstrap-skill-deps-check.md         |   9 +-
 .wiki/concepts/bootstrap-skill-deps-check.md | 100 +++++++++++++++++
 .wiki/index.md                               |   1 +
 .wiki/log.md                                 |   2 +
 dist/project-bootstrap.skill                 | Bin 9559 -> 10474 bytes
 skills/project-bootstrap/README.md           |  11 +-
 skills/project-bootstrap/SKILL.md            | 109 +++++++++++++------
 8 files changed, 206 insertions(+), 47 deletions(-)
 create mode 100644 .wiki/concepts/bootstrap-skill-deps-check.md

diff --git a/.tasks/STATUS.md b/.tasks/STATUS.md
index 97da69b..59c35c1 100644
--- a/.tasks/STATUS.md
+++ b/.tasks/STATUS.md
@@ -22,20 +22,19 @@ _Updated: 2026-05-05_
 
 ---
 
-## ⚪ [bootstrap-skill-deps-check] — refactor project-bootstrap Step 5.6 into a generic skill-dependencies check (replaces per-skill `Step 5.X` mirror shape)
-**Status:** ready
-**Where I stopped:** (not started) — design agreed in chat 2026-05-05 after `[interns-skills-mvp]` shipped: adding `delegate to interns when allowed` to the canonical CLAUDE.md template made it visible that every new trigger would need its own `Step 5.X` detector mirror, which doesn't scale. Decision: collapse Step 5.6 (superpowers plugin) and the deferred `[bootstrap-recommend-projects-meta]` into a single generic `Step 5.6` that reads the canonical trigger list and maps each line to a fulfiller (skill or plugin) for missing-deps detection. Hard rule "never auto-install" carries over verbatim — chat-only recommendation block with copy-pasteable install commands
-**Next action:** Read `.tasks/bootstrap-skill-deps-check.md` for the full spec — initial trigger→fulfiller seed table is in the Notes section. Write `.wiki/concepts/bootstrap-skill-deps-check.md` design page first (rationale: why generic over per-skill mirrors, kind: skill vs plugin distinction, MCP server caveat). Then edit `skills/project-bootstrap/SKILL.md` Step 5.6 in place, bump `version:` 1.6.0 → 1.7.0. Update `skills/project-bootstrap/README.md` Workflow Step 5.6 description. Rebuild + install. Close `[bootstrap-recommend-projects-meta]` with a note in commit message
-**Branch:** (not started)
+## 🟢 [bootstrap-skill-deps-check] — refactor project-bootstrap Step 5.6 into a generic skill-dependencies check (replaces per-skill `Step 5.X` mirror shape)
+**Status:** done
+**Where I stopped:** `skills/project-bootstrap/SKILL.md` Step 5.6 переписан с single-skill `superpowers`-only detector на generic `trigger → fulfiller` table walker (9-row inline map: 8 skills + 1 plugin; `kind` flag drives install-command emission); README Workflow Step 5.6 description обновлён под новую форму; `version:` 1.6.0 → 1.7.0 (MINOR — adds capability, absorbs prior detector cleanly); `dist/project-bootstrap.skill` rebuilt + installed; `~/.claude/skills/project-bootstrap/SKILL.md` shows `version: 1.7.0`; design page `.wiki/concepts/bootstrap-skill-deps-check.md` written (rationale: why generic over per-skill mirrors, skill/plugin kind distinction, MCP-server caveat, source-of-truth invariant between SKILL map ↔ `assets/CLAUDE.md.template`); `.wiki/index.md` + `.wiki/log.md` updated. Subsumes `[bootstrap-recommend-projects-meta]` by absorption.
+**Next action:** (none — kept until merged)
+**Branch:** master
 
 ---
 
-## ⚪ [bootstrap-recommend-projects-meta] — Step 5.7 in project-bootstrap: recommend `setup-projects-meta` if MCP tools missing
-**Status:** superseded
-**Where I stopped:** (not started) — opened as follow-up to `[bootstrap-projects-meta-trigger]`. The `check across all projects` trigger is now in every CLAUDE.md template, but on a fresh machine without `projects-meta-mcp` registered the trigger is silently no-op until the user verbally asks for cross-project work
-**Next action:** **superseded by `[bootstrap-skill-deps-check]`** (2026-05-05) — that task absorbs this one into a generic `Step 5.6` that walks the whole canonical trigger list, not just projects-meta. Kept here for git-log archaeology; close once `[bootstrap-skill-deps-check]` ships
-**Branch:** (not started)
-**Blocker:** waits on observing a real fresh-machine bootstrap that silently misses the dependency — defer until we see the failure mode in practice
+## 🟢 [bootstrap-recommend-projects-meta] — Step 5.7 in project-bootstrap: recommend `setup-projects-meta` if MCP tools missing
+**Status:** done
+**Where I stopped:** closed by absorption 2026-05-05 — `[bootstrap-skill-deps-check]` shipped a generic Step 5.6 that walks the whole canonical trigger list (`using-projects-meta` is one of 9 rows in the inline `trigger → fulfiller` map). The per-skill mirror this task envisioned was rejected as a copy-paste explosion shape; the generic walker handles the same case + the analogous gap for every other canonical trigger.
+**Next action:** (none — kept until merged)
+**Branch:** master
 
 ---
 
diff --git a/.tasks/bootstrap-skill-deps-check.md b/.tasks/bootstrap-skill-deps-check.md
index 7d89fb3..48dd08e 100644
--- a/.tasks/bootstrap-skill-deps-check.md
+++ b/.tasks/bootstrap-skill-deps-check.md
@@ -26,7 +26,14 @@ Refactor `project-bootstrap` Step 5.6 (single-skill `superpowers` plugin detecto
 - [ ] Optional polish: print a one-line "✅ all skill dependencies satisfied" when nothing is missing, to make the silent-success case visible. Probably worth it; very low cost.
 
 ## Completed steps
-(none — task created)
+- [x] 2026-05-05: read `skills/project-bootstrap/SKILL.md` + README to confirm scope (Step 5.6 located lines 349-389; README Workflow item 5).
+- [x] 2026-05-05: wrote `.wiki/concepts/bootstrap-skill-deps-check.md` design page (rationale, skill/plugin kind, MCP-server caveat, source-of-truth invariant).
+- [x] 2026-05-05: replaced SKILL.md Step 5.6 in place with generic `trigger → fulfiller` map (9 rows) + algorithm + recommendation block. Hard rule "never auto-install" preserved verbatim. ✅ all-satisfied case prints one line.
+- [x] 2026-05-05: bumped SKILL.md `version:` 1.6.0 → 1.7.0 (MINOR per project-discipline Rule 3 — adds capability, absorbs prior single-skill detector cleanly).
+- [x] 2026-05-05: updated README.md Workflow Step 5.6 description to match the new shape.
+- [x] 2026-05-05: rebuilt `dist/project-bootstrap.skill` via `scripts/build.sh`, reinstalled to `~/.claude/skills/project-bootstrap/` via `scripts/install.sh`; verified installed `version: 1.7.0`.
+- [x] 2026-05-05: updated `.wiki/index.md` (added concept entry) and `.wiki/log.md` (ingest + decision lines).
+- [x] 2026-05-05: closed sibling `[bootstrap-recommend-projects-meta]` 🟢 in same commit (closed by absorption — note in commit message).
 
 ## Notes
 - Triggers in current template (2026-05-05) and their fulfillers — initial seed for the map:
diff --git a/.wiki/concepts/bootstrap-skill-deps-check.md b/.wiki/concepts/bootstrap-skill-deps-check.md
new file mode 100644
index 0000000..51ff231
--- /dev/null
+++ b/.wiki/concepts/bootstrap-skill-deps-check.md
@@ -0,0 +1,100 @@
+---
+title: "project-bootstrap@1.7.0 — generic skill-dependencies check (Step 5.6)"
+type: concept
+updated: 2026-05-05
+---
+
+# project-bootstrap@1.7.0 — generic skill-dependencies check (Step 5.6)
+
+_2026-05-05._
+
+## Problem
+
+Step 5.6 in `project-bootstrap@1.6.0` detected exactly one missing fulfiller — the `superpowers@claude-plugins-official` plugin — and printed a recommendation if absent. The shape worked but doesn't scale.
+
+The canonical CLAUDE.md template grew from 5 lines (1.0.0) to 9 lines (1.6.0) — every release added a new trigger:
+
+| Release | Added trigger | Fulfiller |
+|---|---|---|
+| 1.1.0 | `we're on Windows` / Linux / macOS | `active-platform` (skill) |
+| 1.2.0 | `check across all projects` | `using-projects-meta` (skill) |
+| 1.4.0 | `pull remote before work` | `pulling-before-work` (skill) |
+| 1.5.0 | `follow project discipline` | `project-discipline` (skill) |
+| 1.6.0 | `delegate to interns when allowed` | `using-interns` (skill) |
+
+Each new trigger silently no-ops on hosts where the corresponding skill / plugin isn't installed. The Step 5.6 superpowers detector was the right idea, but mirroring it as `Step 5.7`, `Step 5.8`, … per missing-skill — five mirror sections to cover the gaps above, and one more per future trigger — is a copy-paste explosion. Worse: a deferred task `[bootstrap-recommend-projects-meta]` was already opened in 1.2.0's wake to mirror the `superpowers` detector for `using-projects-meta`, and the same gap is structurally inevitable for every line in the template.
+
+## Decision
+
+Collapse Step 5.6 into a single **generic** "Skill dependencies check" that:
+
+1. Reads the project's `CLAUDE.md` (just-written or pre-existing).
+2. Walks every non-empty, non-comment line.
+3. Looks each line up in a `trigger → fulfiller` map embedded in the SKILL.
+4. Checks the corresponding detection path on disk:
+   - `kind: skill` → `~/.claude/skills/<name>/SKILL.md` exists?
+   - `kind: plugin` → key under `plugins.<id>` in `~/.claude/plugins/installed_plugins.json`?
+5. Prints **one** chat-only block listing every missing fulfiller with a copy-pasteable install command.
+
+The `superpowers`-only Step 5.6 from 1.6.0 is subsumed cleanly: `superpowers` becomes one row in the map, with `kind: plugin` so its install command is `/plugin install …` rather than `bash scripts/install.sh …`.
+
+`[bootstrap-recommend-projects-meta]` (the deferred mirror task) is closed by absorption — the generic step handles `using-projects-meta` along with everything else in the same commit.
+
+Bumps `project-bootstrap` 1.6.0 → 1.7.0 (MINOR — adds capability, doesn't break the existing detector since it's absorbed).
+
+## Why generic over per-skill mirrors
+
+Per-skill mirror shape:
+
+```
+Step 5.6 — Recommend superpowers if missing
+Step 5.7 — Recommend setup-projects-meta if MCP missing
+Step 5.8 — Recommend project-discipline if missing
+Step 5.9 — Recommend pulling-before-work if missing
+…
+```
+
+Each section is ~30 lines of nearly-identical "read detection path → if absent print recommendation" prose. Adding a new canonical trigger means writing another mirror section. Five-skill template → five mirror sections; ten-skill template → ten. The detection logic is the same; only the path and install command differ.
+
+Generic shape replaces the prose mirrors with one ~10-row table. Adding a new canonical trigger means adding one row in the map (plus the line in `assets/CLAUDE.md.template`, in the same commit). The detection algorithm is invariant.
+
+## Skill vs plugin distinction
+
+Two install pathways exist on a Claude Code host:
+
+- **Skills** live at `~/.claude/skills/<name>/`, installed via `bash scripts/install.sh <name>` (or via the `find-skills` skill). Detection: file existence.
+- **Plugins** are a higher-level Claude Code concept (slash commands, hooks, sub-agents, MCP servers); installed via `/plugin install <id>@<marketplace>`. Detection: key lookup in `~/.claude/plugins/installed_plugins.json`.
+
+The map's `kind` column flags which pathway each fulfiller uses, so the recommendation block emits the correct install command. Currently only `superpowers` is `kind: plugin`; everything else is `kind: skill`. Future triggers may add more plugins.
+
+## MCP-server-backed skills
+
+`using-context7`, `using-projects-meta`, `using-interns` each depend on an MCP server that's separately installed (`setup-context7`, `setup-projects-meta`, `setup-interns`). Step 5.6 only checks the `using-X` policy skill — not whether the MCP server is registered or running. Rationale: every `using-X` skill carries a "Prerequisites" pointer in its body that fires `setup-X` at first use if the MCP tools are missing. Bootstrap doesn't need to duplicate that detection — the skill itself self-bootstraps when invoked. Step 5.6 only ensures the `using-X` skill is present so the trigger isn't silently dead.
+
+## Hard rule — never auto-install carries over
+
+The `superpowers` detector at 1.6.0 had a hard rule: "never auto-install". Reasons:
+
+- Slash commands (`/plugin install …`) aren't callable from inside a skill.
+- Silently mutating user-level skill / plugin state without consent is overreach.
+
+Both reasons generalize. The 1.7.0 generic check is recommendation-only — it prints to chat and never writes into project files or user-level config. The user can install some / all / none of the recommendations, or remove canonical lines from `CLAUDE.md` to lean the project's trigger set down.
+
+## What about user-custom triggers?
+
+Step 5.6 ignores any line in the project's `CLAUDE.md` that doesn't match a trigger row in the map. If the user added a custom trigger like `use my-team-style-guide`, it's their responsibility — bootstrap's contract is "we own canonical triggers; non-canonical lines are your responsibility". The check is permissive on custom lines (silent skip), strict on canonical lines (recommend if missing).
+
+Removed canonical lines work symmetrically: if the user deleted `delegate to interns when allowed` on purpose, Step 5.6 reads from the actual file and never sees that line, so it never recommends `using-interns`. Correct behavior — the user opted out.
+
+## Source-of-truth invariant
+
+The map embedded in SKILL.md and the trigger list in `assets/CLAUDE.md.template` must stay in sync. Adding a new canonical trigger requires editing both in the same commit. Mismatch = silent gap (template adds a trigger, map doesn't have its row, the recommendation never fires for it). A future hardening could lint the two against each other in CI; for now it's a discipline rule for whoever bumps the version.
+
+## Composition with the rest of bootstrap
+
+Step 5 (idempotent merge) ensures the trigger lines are *present* in the project's `CLAUDE.md`. Step 5.6 (this) ensures the fulfillers are *installed* on the host. Together they close the loop:
+
+- 5 → trigger in the file.
+- 5.6 → fulfiller on disk.
+
+Either alone is partial. Together a fresh bootstrap on a fresh machine surfaces every install gap in one shot.
diff --git a/.wiki/index.md b/.wiki/index.md
index 103cc83..ba13baf 100644
--- a/.wiki/index.md
+++ b/.wiki/index.md
@@ -15,6 +15,7 @@ Catalog of all wiki pages. One line per page, organized by type. Updated on ever
 
 - [active-platform-decision.md](concepts/active-platform-decision.md) — why `active-platform` is a skill (not a memory entry); why default = Windows; how it's wired into `project-bootstrap`
 - [bootstrap-claude-md-merge.md](concepts/bootstrap-claude-md-merge.md) — project-bootstrap@1.3.0 — Step 5 upgrade path becomes idempotent merge (read → diff vs template → confirm → append missing); fixes silent gap where pre-1.2.0 projects never picked up new canonical triggers (`check across all projects`, `we're on Windows`)
+- [bootstrap-skill-deps-check.md](concepts/bootstrap-skill-deps-check.md) — project-bootstrap@1.7.0 — Step 5.6 collapses the per-skill "detect-and-recommend" mirror shape into one generic `trigger → fulfiller` table walker (skill vs plugin kind, never auto-install); subsumes the deferred `[bootstrap-recommend-projects-meta]` and the existing `superpowers`-only detector
 - [bootstrap-manifest.md](concepts/bootstrap-manifest.md) — record of which `project-bootstrap` / `setup-wiki` / `setup-tasks` versions initialized this project's `.wiki/` and `.tasks/` layout (overwritten on re-bootstrap; history in git)
 - [build-notes.md](concepts/build-notes.md) — why `build.ps1` exists alongside `build.sh`; PS 5.1 backslash-in-zip gotcha; how to extract a `.skill`
 - [install-portability.md](concepts/install-portability.md) — `install.sh` / `build.sh` rewritten to drop `mapfile` (bash 4+) and `find -printf` (GNU only) so stock macOS (bash 3.2 + BSD find) works
diff --git a/.wiki/log.md b/.wiki/log.md
index b00be12..00b5fe8 100644
--- a/.wiki/log.md
+++ b/.wiki/log.md
@@ -43,3 +43,5 @@ Parseable: `grep "^## \[" .wiki/log.md | tail -20`.
 
 ## [2026-05-05] ingest | concepts/interns-design
 ## [2026-05-05] decision | interns-skills-mvp — shipped `setup-interns` v0.1.0 (8-phase install: detect `.common/lib/interns-mcp/`, `pip install -e`, `.common/secrets/interns.env` write, `mcpServers.interns` registration with absolute Python interpreter + `cwd`) and `using-interns` v0.1.0 (runtime policy mirroring project-discipline Rule 4: ask-mode default, conversational grant/revoke, always-ask paths for `.env`/secrets/keys/SSH/credentials with transitive rule, cost-cap >$0.10, session-end reset; routing hints for `bulk_text_read` + `transcript_distill`); `project-bootstrap` 1.5.0→1.6.0 with canonical CLAUDE.md trigger `delegate to interns when allowed` between `follow project discipline` and `we're on Windows`, Step 5 commentary paragraph, manifest table extended with both new skills + `project-discipline` row; root `CLAUDE.md` dogfood updated; both READMEs written; descriptions verified (setup-interns 899 chars, using-interns 814 chars, both under 900 budget); all three rebuilt + installed + listed by harness with full descriptions (no H1 fallback)
+## [2026-05-05] ingest | concepts/bootstrap-skill-deps-check
+## [2026-05-05] decision | bootstrap-skill-deps-check — `project-bootstrap` 1.6.0→1.7.0 collapses Step 5.6 from a single-skill detector (only `superpowers` plugin) into a generic `trigger → fulfiller` table walker. Map embedded in SKILL.md (9 rows: caveman, superpowers plugin, using-wiki, using-tasks, using-projects-meta, pulling-before-work, project-discipline, using-interns, active-platform); `kind: skill` vs `kind: plugin` flag drives the install command emitted in the recommendation block. Algorithm: read project's CLAUDE.md → match each line vs map (substring + tolower, mirrors Step 5 idempotent merge) → for each canonical match check disk (`~/.claude/skills/<name>/SKILL.md` or `installed_plugins.json` key); print one chat-only block listing every missing fulfiller + install commands, or one ✅ line if all satisfied. User-custom lines silently skipped; removed canonical lines silently skipped (respects user opt-out). Hard rule "never auto-install" carries over verbatim. Subsumes the deferred `[bootstrap-recommend-projects-meta]` task (closed by absorption — generic step handles `using-projects-meta` along with everything else). MCP-server-backed skills only check the `using-X` policy skill; `setup-X` self-fires on first use via Prerequisites pointer, bootstrap doesn't duplicate.
diff --git a/dist/project-bootstrap.skill b/dist/project-bootstrap.skill
index bc0187b509603219269c6868d976c65a39b6b8ea..20860bf75f801ea90fe4346862ce493b8717a8fb 100644
GIT binary patch
delta 9737
zcmV+kCidCaO6pM?P)h>@6aWAK2mn{ArCe4ins7M@002D|000}4F$oosFbjX(ZrsKd
zzUNaM*cY*cT`m+$Zlt;f3_AgYD6wHV@I_FVv*he@yj%`5Gt^pzQ23^OfVP*t?t}SB
z`kgaFE+si_TEL0O;mn!y`<?IXL+YIUpvy2{S{r<Ds>`zT)&!#(^C#`eI_kT%Qx%@o
zu$gw&ZG5LnO{OK=YU-5tXS9DdVMaxcKW5!pr;Axuy!rO|%OAeYw^hNPc4lK11wHy+
zxlV=p`YTTt7eCNDEK{SdZ66MJTTp)Ed0(g9oL^{Zm8%YBnQAL4UR*r?>7~e|oe4Gh
zjcFPR&aBtk`8>;B;hYLk8R~_drLBejGwMva(G{sa*sThtR84bzmSul)Iy^M6`S6fF
zfBFaMZ5OWD@K!4~k8dm6RNCeA!fBDKue7@kwQ1M1a&}9;#C>I*i>&0ZLEJ~<18+>u
z%ju;K`0Hs`s{jY6212WA3bl5626r~N4+eQ&$%xjf^Ev&<SCYm5cFwR0Y&rY|`CVg5
z6R5Q9$~ZR6w(!BjhxC80)-B=7;F&CYTkGU4cEVhh!CZ+!wxzCi%Hy#y8!cXWV8%ok
zlz%Xz2V<u2i`Sv=#;<%RSwB6Ys){)B!?T1}Hv6Dlm~Mr<sdM{Iwl$g^6*sHtcGmC#
zG8W5?x1*tOEi6~~x7KYS1EW;mmNkNpj8KS~_H_y>ysQGdntFe)T~;=TIwD}&pxX*D
zfYjc#{BCh_%>3x#*A6lJr8k~Kl4ZrcYAUF*@M&uU=QnY{#wtLH?Nfb;D}&d~N|MHe
ztkR8MOKeyLBynlCooW%>7(wLot~O;&+ujFSaw)<=O#>UTh3(m@5>C{a>)V!{X@Z3H
z=R$%uXDy09KFWXd#r}P9AlH{E%~?vRTHA81>=lodnonej6;ol+tp6-+Fnti0ov%n6
zE(4C()_4!C0S8}jst>k{C4iVn$VfW}hoTH|K0{1fTEQD^_fnM`cA~20wJoDMTqE?h
z#yuOYJD+r*%9#~AGwif(vvjei@#c=<1KZ4Mg}@`Vg4ut<vPv)e^;#_(Jro``aY;tY
zv+RamLovFcOWQlZ<_-O5*(EpG&3rx||HD3kPdEincpy%2e!1Kjx!kPC>CTRzu`kgo
zr}2D(Ulsyj*1<3Kt9byVHBjr0SU`@BVC9pfJ#=H|7B_7XHXr)se>*tj$qfxjT(SSB
zd53R954eBZ0VHQ87>^7vZKXe^=f<wn6NBNE(Yy5O)Na9l5f<30y}SSvOWlR|g1X%R
z5#o!NNZ@%;dPv7FYaKHjA76|aEIlb|d-?YH+n+AQRbA728v9o9l>f|q)32Y&XZF_M
zr%4~%M`~QW8>mT(qelh6ihPfII=jOPTf|Fahh~2#&q#+dKgj7-3j}KC@8Czf^Hf{J
zYDRviIw{Ixr@wNVVI%E8O#(OokZ$tr!nFOzf)<k{Ak3@FLgXjdpNYUhbFSkcHGr~V
z0<kZD26}GhTkY1IM-`5sB-#M%WtU1DOc*fOEm}bgF6UB2Qb6n~-~&VV&;WCKqvyc9
zxUqk=bKBic%rPg%vYu}NtSjw9iUqoc5QqxTZ**y0<rCP(=844fKoCDIKQTPHAHD@%
zJL~;?2*@pfF}ENCx(R5YwX7Pu%d(>!EF!W5p)NV7#ChvGeisn!oq$he9G0w$9!u;i
z*4~6g&A=h<)YGK0`6S1obLeo05c|8~)Y^Y;6$CFETW-#Ts?bh(7PYc{Tg}oEdjq{E
z0^QwJA3-9|zGj17r0~F)S4gg3diWbooC$%vMP3*jrTxQC%yy6#5Ql8ki4w(ltF_ap
zrR*_FzYGlHN1s3a{e*9bM2%Z4D?u8q5cE$c#_G85k3NgunD|Z{Ho9->yPV=ZkHvpy
z$0Jfmk7jNqSP}bko*fU0(Mc{^y<_S|#joU@lT4F*ho~{f>`L^x-vwv45OsDNsV051
zGQKn&*G@7m?qi1ITHYz7y64D`i|k<p?qp)Y6Sg4YP^G2%+7d8JpjG82r+2E^+-dRq
zvh{&4hU;(TVPowkh6Wtc2w~IPrLKRtu8ZOD=fD1qR(->aSi1s{(}@vPERV#Y2cQt<
zV<N%<B>%j~OEAAmFJed*Pg}Ls&lZ>8pI=<C4l$qI$fzbKfa7aWs>MjF-lvuPgSTxV
z$I{AyXtb{)NoXiG7Z8&Y5+AUJLT*QWN5c}AVL7GkuICu2f@X9WXdTl(WD9?~{A<3$
z?@RUbKmQWpT1amjOGn&2`ehg&g!CtYu(p*&AdFdYAP1<5Eh>8wi*~y;fg@j(H45--
z&xOYQc<W1$WF4In$u+YSTw$GLTsnJaHkh8oTo41;$Rq^ac2N<LISf%O4BiEvzwUi4
za|`w(>f;n7$iSSOt1A1Q<Zpk(GB)Bn(;_cfHy3%v0Bm;=3@Zt}faL&cNYfSH-s+F6
zx9%d-d($_}@8);sGs)#)@)L%1Z(f`BtTeRE>3OqL*SNd3yVy_~wZ}f&m-PS-;+tzI
zvdzcaO?$;{Vel?WL>Y{cY$vnDFAki1ItF>1JmJ<4JX0i>$oZHmqJe*0j~L^?Dt3Fo
zFpJ@kL?N*$4>Q$hGQN1R&PL~*$4tz!?|6oeV!>@4G7OW-;o-nn9=&Fcb6M-AIXF8!
z#GF+Wk@oOXwp6$m6S(1?p0Yc~(*2({aE|2)lL3(t`a+NR{3w@S{#S{`eoGN2#0i%o
zbW8XEoo3Erb9zoK!hL_GX*|~XqXN~M{mjvBbtQ8Y|BEeXB$o%YL;~?FDMP1Ygr1D_
zLtzVRy$5~wbZ6%K3Q=|7UeZ@FUaxhCNR)8;y&&b~`<Lf${;*)SPQT`w&!7HP#He0s
zEz|gKoi&HC7GSYMyZgVV%zJX~&X+7GcDcPe`}ZUU#F1w@>MVa!_FBM)Bg$nL9h20X
ziks*)S@_KYlb%uH7n-&RzP~<B*HfD51dq^+(l0v||F9q&e`Onx%RM;k<qv&&>gs_9
zOq`vT76-G@@LRiXEk)&^NT-YgfC0B6LoTM2DQ!+a*RX!N8rAtdGYfDejE5NwOpAa1
zhy|r&$nx4VOX6W?>2-KSi)kg=U;2@84M;wNxTkdpoj+SFc!7uGx?ko<p~WU0S{xsL
zt)47bCnqPTN5|isKGvt-oF0`&M<++8l|DUQJ<I+LP)h>@6aWAK2mn>8rCdcx(7Njz
z0006@lP(D%e_UIS9LIHj?_W_~0oKlHdd8$k+gcJU)1(wJCMkwXMGj<z-P=>M)7qZy
zQD1gA#=`JJoTmT@0s{d82S)Ochdd`h@|=I7KM?<feBU`$eVLhEl86!7B4@g*s!yFd
zm+xG9!Y~Z-cxjK#sw}>-NgbXQMP1cpyb3ODS*1mOe{60|el+<(Ftb%srmI>modm`_
z&eJ-Lv-Fp?GDT^c)p;3Xkcs_TCe2N~uqJ8B(&n|97un2~$L2h($7X`R)APJ2?by8d
z<iVq-pG=msF_xXI(~ER!nkvoD&ClX;71xW+`;}SRdQr?Uv5u>YYKqlL!;c2UCKnhy
zHV>aXfB51N*D>p~UYP14%`)6h&(E=y3D*9ivY;rf+^zM(DuqpDOH;+0${eKauKYF*
z#^#{q3cpmgZdTo0tb5=#-=7lCNXA9#KMUD1y^hPeKN9O13vO>f8ur|*WKC=@i<>-I
zfTg4{J|_>s(%9s7&D-{MTGgDPj5TqNC&qb=fANJ$ihQ1)H>H)y>!Q4<R&ip<g_p_^
zJ~KDzyyL((O;tNKWVQy+mDKh?5BO9eH^o&j5Ts6m5Hb|JXP&!5|7j~g!Kno;U{wri
zmMbi&gpg#LU#4Y|FI6r;yIB?#hE>s*o+1ZJ;|gc@`O21Y4OUR5)&)jG)Q-*35zp)B
zf5;q?CvN6QIB|634uyAHR{0^5z|sAlIj!x={J?zo>))D3AQ4aI;z96mVUr8UNX)&K
zHlA&i<JGoY&(adJigI%t1W^>7#nmFnDidaL03kP}y$n}z3DFBfd=D|)+&-Dk?Bz6X
zz{Kx=-`HePm;>BA-q`BETwV39<i$bof0YSmsu<?$ZalwlO^{3743WA16uGc9N3Xd_
z^PUp*<|PotncbS`F19mUHSW(O<Cfbq-9^p>!yqV&V%>>hY^r9tjLVG|fwQc@N$`N=
zG}dtinQ3wu1N}~2KErun+1k$Z6oOAV;@BAT-S2)wlY<Zc^f!))a?No^E_a)je_QQN
zf`_sumythidhbs=GdR6SS2B<fQ;Dla#y_UJ(6Py1QzkrsE#q##ZEU4h_TWiTU@Fvg
zQGaYs7gV{m7@5S{*~bUM64m-t)kw6yT*jO~3674Ge3KVyTFxv6+2N?8qb*gqCCmOv
zS_i@7xoido6Dyd`G|qaGE(35!e>Z^{QD@pCGb^l4maWRldQ4_s7E4oG*ad!zpyjX@
z({Ap>--{+(HLbn&agEHzmzLL>ye=Bp$l10+-<EORLAo`rrw0}Y+gQdK4?*__8N8Sk
z>m1hYzPC!w*3xO7$kQI26-^!7|6Ulve9%Rnsmb*d7Ph43>)=0YQb@9xe^s6GIESrl
z5}rgQCs;Ol&ZFut!P%a>@5+Y{Wt=+I021-YX7-%>g^%DfBJpM+??>tuAra;==!Rfr
zVAgqQEyTrUGvyR09h)T1iyRDtfz=C?LN1pVVX?w(Si3`SHD&M!B&OKlGTV&RJ*U_M
zm^+Y0L((SZQIWq-!|9HOe+y^v27HF3Whrz-n97aSFaU5=v>&rFos;a<%I5GGB8vUZ
zwNecBXPKShoD~c#;{@6P9CCD2)x`?im)%%`2WOM^;3JUtZ3D|+4WDwzx$cT+el+SH
z>324#CZ7Se@D$=%xG0jAxf7n!3p>XS^8{RUYF*pcH7L$DvhD4Sf053rXi7{d;Lyva
zUW|^h5ph#wf0{tB9S`A3TVQ1l&mm05W>MFx>UcWkH|pS`Ih(*~PcPiK>76^b;~$>Q
z@7}%p(XBf_{^&#d(T_j6mE5{@_tr-<`_Y}bI^9TMo6_a%uoFGgx3T`ucYpnNrh?Qi
z<Bq}A$|mVNO$0n~f9F6cq8?Zx&1d%YU<FwsiNW6DoLeVjSAa?|xMv$vZ&r3R1_YVW
zG4Q|zXJH+TsIees4VTjeMTTafup8oxQO5=f_0?bCPx$m{_~_BsynbZ}iiy>*>Sb!z
zy|rX(cuodkZI*E!QWxU0tkY^g3G>T%O%C;aLvI=0<sqlbe`Qm1iF+!y^AxMiiliZm
zszepA2)R|K76^H;CAqxuyjj@-cx-Gcl91SHOw7|j-A5u`u)G*cIk>QPg+*};iCxv(
zi@M8ZN=CqJ<DVpD(BPi4cP+rs3*OyY%U!-{rb>8!qRgbz^oW77t*49gb{er~EwQH0
z@uV<=L}UU>f9DyD$e~Ui(+iidRIoM<PYSnbz+&(^hWUZ*!ZRpk3mZg~)^HhPIR3Mx
zx1}8%R^`ozu0>lfV2JA?zvsS5s1je;Dxh3A??^K@p)G$8URCs{RU%j#)tu3`tNN09
zb1L^_>#gf@KI{3L6m4Q&Kvq@89Ab#`jSedWhpU--f5`!I6;2V%tNP*ElP6D=5?rWl
znIFTd{hy5tvC2z2t^M4Fkb~O91x)RkZlB)7kn%t-k=bQBvsLdH*5Y08eIvdpOOsj-
z!BAktrc`jUCTcY;5<bsTcz-MI3PMy3Jh;TDH|pJlE4FH;E5ZRH#2^{~g)s(iX&J7Z
z7j?3Te=C{YDwfVp3I?R^nx3X72mj8RMB{cm6Ut+C39n(g!a%V^H~ZQJhlF#5TY(9>
zM}f`jrJObFF{q|v^ka`B^$xIPuXxhOkvy$uHuZtdV0u@u#<n}#Do5}v21+{@_Fveu
z_$(yU;Cy=TCy>ls^z7&ehg`;am8G==j^^Q}f5h2B+A)GBPi3g?8CnB5sRAfF<!*4M
zAi;%rpWQMa^tYx&JSr%91K*@*?o)~nL-eiFr(T;1(8P98OoI4?mIVLLy>+JGF{nwC
zMR#%n_r}y-m4vidVll700^@MBJnb{`qC<;4v*8_QwAWZX=3NB5LpQos?F9)F^Eo6z
ze}ESyfY-)g*m;~Y7BJ4yQmuTNLOrgNx-GY>Jp9~yKOE&(Jwf>Tu=hp1(T>C9{7;<n
zInE#E6xNM}vG!Q|p;M;oM?7~dzJA21>cjp4+e}t4v7g0H3JC3k0jzL_R4|Az7>sis
zth2J_Q?XgVQoo4!zhE1N+%Hxq03!E6e_1Fe)XUSI_(?8(LP<TQR;D%d#c3x$iL>Je
zx;y?`+Ih^B20wdi1D%D-EGtV0f@KgGtjxh*f}me~bzu4|06nnFnF(+IAnL^<U)`^Z
zSxo0Z;W+tP!bXhkAhmjF5xmPZ-jkEuW_jO&TpO~9-&2FuN|2oA3yS~~071f$f7mP#
zXFEJFNOp?44(unRNa|^UAm)9E+s2~s&MYifIE|c+W}lc4&b2sihw2ycx|6!2qsJce
zF)E{5h9RIb89PgB)i@ESm<|}a2zNrWpppfO70J?Y#3njHNEp{m1#>JZm2aDZDY-!w
z)V^N9O2P(WP3A2$IakR%6E}P+f5br8hK=9|R}HLK8;>EdO_Pk=scC+NiTLvT(Wm&E
z{t>a+qHxixeGMU#2RUzxgTjh^LqgPCDH@{pm_i`eWlGbcjwzLtAdFx%nM_;nrSYgT
zN;!gIB$t+-vEiqZT`kXP_lZyzVFkiqP%eEOrFa@f4_6R0RdhvU5>u38fBa1hgVk|q
zDZB49G=!xu$~vUj0iXW8nZ{>Tku|lQ@=4RWaD@5^A|TwdihtFd`HUjTKJ4L)aUUX#
z`yPMX^WCGsBBC|tmZ{swV_smSLb5pyi;(i|WWgOx7HEe3hHQZbwr`&<XcGl`lJg9l
zJ$?D$<rk++`tM5~{1KA{e}hzjqkKCTa8vBB$b^Sk0;y40HL>z8fqM7YcZ$?8K60ng
zvJ1eUW6z4XoH^#$W${hwb@UIv|Lwm||M2_Y|MT>_fBZLo_!s>3+y5AuRn~ON-RD1H
zl{M!lvL?L_lu@Le8i9>#$wHNJ-bh?6NS;*rs1t)ymqn4>J<hdff91Nphf16z2Kc;f
z!MiKW>T;>U%XJ}o39GS6lM6)|g4kE3t;q0WHL9#af%h5;_j7xQi(K|I>IF?|NnEnA
zz23_;n$za2g1$9Qlz5qvDDWqM(BX)}FM+2R?<@)?;tr#=eV+kgZl0uh^EyI2++AA6
z$>*n$h#I4+Vjgt&f809J$OU;{xH6LN$7hVm8kiq=m6|4TX<@g(A#P4cY?G)Cc6MUq
zYF~yW8_G451m=Tlb6i(H!j&LCk4dAUTX|u_vdJ~f6{RGIOLUfymP!#s9t6^FwGm@)
z(H_?)!EFIDM(h$9D3)$4AK@;g3MAmg!EV2!v4lD^@lgzhf5qK0QQ}jJDhz-}xE4Z(
zeQAq}RZ{rr>T342<SKR!)q_k~$)xi+qg~0ybeqW}KN!zx@*{9{86hr+>Vi&}Ac=ZU
z_6^U2vy@)b9tF*V6EcbHV9JukSjG0+Ce9cJNMf_dT*XUlP-zj)iXSgZzaSu%l(d>W
zsT&uRJ3c(`e{Ya{*dufMwmsajK1e8JG}kV1xYjkUGK%{ZB)q6bkr?g}Oz@sG+f2;k
zuDqzLt<s!nlNjOhTuf)(od)wpO}Q#6$;Gz0Z3HFU1VJ*vf*=~l11wD)3~{k6R%J@A
z4-Qw+jo|h|NvRj`P)5L<Y<&`ZI6<rcFTl!QT2+4cf0a-#Q|ZOAI%w^r+6>a$!pyud
z2*!!3BN0+)99-mz&Qq=2<nAQ6gVP_ByZC|3Fo)0dxnl)JA}W#~mK|#rD&8&<@j(X~
zSa2n{&S&i|b__w~{WwP#y;|SL2j<H-W%^J6p9g_Mck6ON#9vr_65Qp9_#wxROoBy?
z;&Z!}e-k)#CFa&f(_M3<_^yHq80&%79*GW)VXS3fr`4Um7aZ8FtO<)&KtvV%P^gYA
zhq7Jyg=TivtTYC2)@NWBndkEQEZ#jAi+{ZbQMj<};kRLa=jz@w4_sxxs{~EVC$yAm
z64_DVt%soTyjR0e2o?nRdV%p5tYan6n`N8_e~>PKNic3jD^<yNAHmQO%LQqnz-Yio
zF~ijcerg#cQv8mSvZyLes_VomSP=@8fE-|mmx!Xg2s8)Sg-B_Yq${x^vmS_q4go?`
zs+KNj3ASxhhlrzV>4=m&f>~Uu!TR!p9}_NZ9XpsB0R74;VV9M`&f{|c)^n9_4@0X3
zfBfDI=-Mx%WfnTa_!35!;aEU<Aw*;H#%l|F%~_{xikvj1D2J%<wgH;YG-o`ZGh8Ob
z=m=2h=c+cu03`wd^vESHcA#>&O=6Q6_{LTXU(sT7M}%cxy&4RC_39|XSrnN%c&BU=
z$MI{<cR#;5m>k!Ep$?QSj{{9(367uwe@BcxWbrVZ&m{>G5ieG@l8S-$nn?Mq=<yV*
zR+~HtSZ%XJTO#BKyml~xg=YNiS?l98?Ye*;X-#nDV|<?`3D$8bbyjDbd|yiKoC6{-
z0+i1Xr^{Ecjn!4Ay=43uqFd~45fgC+%?i3}<E4552|MGaE<%B7416JL3$bLtf7T5@
zPNec1yD&qAq{v%`7VzZuGPjLfO!TYiL|ZVXG9QuOJyQ@St<y>kqc<CA6;#Z5GT5FG
zsi~!aznAd_0jlV}GbSPj*Xr{%lHhVR{c!_9NPHYVhi%+aMFv*Yu{pdoYM<Bn*{Rto
zeFW3C3CySOv8#F9WVK5bbUPCgf9{#X+at|sf`<yqsajL!YsLZG_8eH6y;6FtR>g(t
z-O8bMrVwUa#$52jk#P-j=B!z++9YSd#0(9;yGyK7)+y6zl{m4=E^%utSR8Ii0w`kO
zw8pA;M(#5e831Y=P+Xi}6ZF{<gtbDiJD#q$lBzui_5UVRZ*m1US#>vle@m<~_Lw~s
ziox}HR)7#7yIGn@+6;#S$M|^qxtapa8U0f2y~t2-NEAoa|L_A%4~;47bt<}N06ow9
zsjQLo)-7zja`dy%Rf$!mNzV$Rt*9mS>BHyVq#vp!cDG)=B4Mux@m`UDXdG<a?;iTf
z(Sta{*2!e#5)zkS&x0Irf3`q`Y?#Z7X-|K3>-OFM{s*CkB9c%VfX`_WX9_Qj$Sl|*
z$+d}j-jgIu5r4q!3J4$~F3SSoVXxf0U_#{1F;QvAra7;MW37#pl`t9{(Y2=Rg)1)X
zIEb@#ys1KZV2Sbt*hCYXUov>En9ISjPR)hg@SoGu&zMb`F%uTUe{D(UqFVGkaA^y9
z#Mrx&&`P)qNBJf<JUp%7T^w*baj)y$KG3~R*L+Hk=<0fL9k}dCo8@z}LmeS042M!9
zRnt(_G!lpB)odr&+pAW}xX{N-zKBXiS-Ds?aHr0ky&i2BUO^Fj9%O2s6Jnk&m^V}W
zYXE8`fSrj&!=mDie*?{YLtN8DvO;Ao5w3ZD8s@R)UpI)QU-v5KD+znaVo9&iiAqu>
zpiTR@pRn0U#89fP$;9lWpeCAx>I(KCI-RpmB=}N7jqS5(%Mzg<Daj6zH-E*M`N|db
z^sp4=uyau^I!{rJ`W<$Ig2Vfjf4D28I{z2BMB$hWcR53Ce}g)+_1Z#7Jn-v^EGsLI
z?!xanT{4Nz6FzIs&!yN91d`B^e2ur+F4!O~r$2lA<cZIxwPjxj1ao!l_?09q4>R&z
z<dK1YY7h<1B<cdhp0Q-P9U1XRqyl@~JBX+LAXsKR_FX4|YwI~S!@5%7B(K=lwe^$x
zj-V6Yx4h>ue{ALCF=-OC=pD;Do{E?#@FFeSLniONDIw><>MJA9Ggs!%9iq50FA7-J
ztKbSmw*O&Zw6mdz#Xr9%d@f4jms<93WJ<qPY&cdMKem(3y-6-@J)EWetox_!a}vYZ
zL*Tb60A@D*N47R~IL(8Fo<sFqJS3(kE60MboB<x`f1+E^VgI5fox#$2YCafXs~wMc
z<vL${B9s`Exrkc3>GvIxcoU{nJsOj8f*Yu*QLM-o^0630iIrH2e>;oQHiyQ2WfgX|
zey_>f*mb+{(Hz<dJdq&Wes?4>C#z9dY2@+hAU)&!1=OI)FLJ1F>zq6^PKvBq=Cn?{
zdQQ|tf3Q@gYGk$y@DIfRt1`?ivp6<S7&2%U;4oRlwFHjievsuz9y#CFOZK;kSb4F*
zpHZ8u-OZD0VknU0OW|`b9xnhIy8L=k!qu+|t*bheU9!G%p5~ewcT5a=;9HVq+bBUZ
zcG68YCvA$EyNa0PP1j;E$>1&gZ3g&z;$L4_e``;yKP7kCfq$m>cS&Z-7IW>2Qk<rp
z_KZka{OqDx&9zCPmC5n889HS%)9zWga)!^wGkrR5GK|hdLHTOPFhQno^QcU&e3`5}
zpPLFc!Iu(0$V)Lj*2J@!I8o`S0cK>MEt8WaxG2@?w5N$0b4`M$X(ie2)_r!R6)=sY
ze{n0ybxL#lDhQQ>WsI5cjk_}aQiMcSJ;A&p>~rk6GCu=~!asU?+B^x4T(z;B!%y4p
zpzjv;r2qJosQ0;YK4v$<bAzUxSH~#!_8S-UO#QLqQn#X-*FlO=X7;}S#9>rbjVeTd
zhS)XEIL@id6)`@HrjGdP;4Nk!d>w6tf2wZ8v{k%U?#kqws!&c$y?Q#Pz8#f*kNvc%
zEZ6IEzLB@xxVK~PU|s+8{W;nm9j%{!6Ctja{PvXil}XACx!9{~Qm=2OXfWYjDBFIL
zz>n*4msi(h({7?~&xE(5Z~v1>-wipnYr)eE1n!J~OZxUbhvdCEJF^c_z3GJAf6#Y1
z+irD|wHwV&cO$($CHJd6A?{7&ZVi4rf_I;wzVAVHUchNCmc#ORFLda)aucA09-t6Q
zKyG{)YBVvQyk^sml;^aQ@}?TPz82$gg}ged8IraLIM*8T%g-L4b|CbnuSYK94Z^ca
zD~fc<_`QSr#7Dg{?L96-EF|?5e-9Z1IVSDflT6UFK%He9?=H2lc6)-5i{93@#V+53
z(8oCrL&j$y#=RE2TY@JcRa;a)6t6C>Tw32M-(|AhMgiVFkv$3V5}F3S<SnU8!UeLC
zoCy=0QlUwHsq1?9rOX@Fon6)3l{NQBB3EYVshkP01QK$6zkV48no=y6e+qTmKA{V5
zpUT)VT#Cs9AmMr=qKlNTLyD+J0%N3IW>*XDOS@!G_(cvs9;~9Ca{n@K^2H8*cLjXs
zm<a=#oON0c2BMG6p?0|}<BTl9uK)D(^JhHI1BY%8eC=4?QGvQNssNg0NJ?t0woA3I
zVF+05G0D!(t@JKTMl8<ze^vlhv<|k`15}M8Ul%MmLG^5P9QekI2jUi`vEb;)by#?)
z&2!R`#xP>j7g&Dx8}X&pZq&o<X*Ew>{!!`a$|7DpSb}1ATt}%7?<DHz9;cs9`wa;{
zoV0|W7RxrU+o60I7WlSJMy0HxV|HF(yZQhZD%5SXVEWO*?*9Mkf4~0cKmXRiLOKM^
zgihM4VyMrQ+Fao`xyy#it^0D(vvX%QbL!i+x#Yd6XHD&rGcE5VIqTY9hT&5ivN`j*
zp|5G<FV`fcN#$1Z{bsxFpEv&LPVtbcHu4MHcPmKo^5ljE?zbzPn8W*A<K&OK$alZ~
zSGO%6pByr=fladxf9EPO4_ORgNXO&}0?W~HOGCO9)!aI{_SWr_-G@GqDwrSnfwo;b
zgE4|$_X)tEGr>IWyOT<Cl&$qynr7A45xVYYa1io_&(YD-htESzH-&s%)8{~?wag(Q
z*Yf!zw&3nVru;33EzmUT++?r5_4CLlpxUI3*mOKp-UBm_f9HW(OeVq7N?TiejbgmD
z)brBH3#yegORoxfHdL?_pX8ElKbHzTE>=?Dyw@|6zENk^u->SRwRDl*Z1M#j$+zql
z3^f_L>k%SX>j4Qx#?~&W=deJ<cDoMW0n2Hkf2v4M8)<(P>91HgC&6D*5KLAV#YE2P
zGq_T1(cP-Te|xlsLp#klr7K93R@?;cN@7fl$9&UJN{m`F^g7N)d}#|3ETHcR=t)hz
z4`Y|B^|fPtZBosSW(i9=a0Ls)gn=fFdWo1G9D|>iH(y=YN;5qbk1-vzwG9{4Rs#ia
z9a7*6uYz{83$~vrEBGpTz6DYH?W4@jPr78Crs^I_f8J#HTL4V6OyrZRWQR+0kSq`h
z9rwh``vmQIYD#<1CNX`NecNESh-YrC%Dvbo>$dtMRa?#R4SoV*NRs}njBgz1yg>Jh
z1HE4h*iZh}ue|IKKS*c(NRyfR`W)Z7q%(~{Ec0yKUs=01qzM5Y;V8dn9(wZIpTTMW
z^k0OMf4u!+`wF-IG7b&2-(7#w;5Tx7d)MyU*bdb8elUmYb-d{Y)zAv6n$L{|yRR*~
zaiyA^%t}Q?Do=-lpHi_iaSZb79A>!J%+7niY7hj^*bIpot7G?a&eqQ?K>Io>L~o^^
zXv1a`HE_ZREFDw`a1O4|s~k**r^zC>a|h4Ff2jC`KO1WYy@J=Zjr6-H14W4}fAc+&
zweLsHl}ZP_`YoQ?|G2Y;(vr$6h|-^wid&LW^?bmZ;jh<>rR?t`Gf9xjdJlVA)&9&%
zU#Z;UvqE}B<Y1hxR<*Z6QWIehRewnuVG=Huo^M!aBMXC>s!0+=KY$x@wv1-^UTGP(
zBD=3-rRUdm!R+wYQOT1%kXbNoni2Z=VE9`p2mDQ%;C}(L0wM<j4p*wBTvjQXa5)J8
z06i6x7bH6$RjQ?2MM==Q>l*+70!sh@8UO$Q000000000000456aU@3ql_irNA}*8Y
XBq{=eCX*f_8<Q_3A_kBr00000t_Aa#

delta 8854
zcmY+KRZyIP5@zwB!GgQHPO#wa5Zr>h1{-W3KQ6&NFt|&w;O_1c++Bma?Y$4Xx3-_Y
z>Z*P})#p1_TTmeRstAwp2?hoR8Rj6W@Y|)P5cV1}42;2lRwRklba?TcXuz4%8ZXXk
zRWTv0s2zz;i?exgeWSte_&R^J#*e3;9@SW>jUrmiDrw7T_ecl^sL!kYLj9_RhO?-c
z3?K7b*ATaL^M<y@($YYnA1dwB6c$@E$@3FmXr5>V&XY9q)H>xAm#3zxq8Tq)2gd9E
zTA4%C<kZQIRMa_s3m4YAq5&hI7xfbrk~EHlm*dvj1<@a=^_COa4R-k{0%xz3N*v$(
zo<j;FBPou^QcAHKeVm`$#!*^p+Nx6N_XzZDO-Ej(saq1RbO@|PJMXw{%fBgm<fn&b
zsGZb*=2c8k%)tG~EGgXhch2sxGsg&zL@$9b!zn}~#3p@ZmR9~~Qw-?d4}yPsIr2<!
zJa<~UP(e)$ZB*bZ{7lr&Ju{ljH?!KJ54JChavH{Oswx3-u)y*Dd@lLD6OG*#WuzFk
zk<w7_3?ud#OMg9~yf7ZEYiU!2(88OJN<VVl>IT<Xp7`A{+6-^ebrbQ?FCTTUWXiA*
zouo+6<l;r3z1&jvfg7Msr2TGBG;M~ZuEr1E!I&Ytt;fcXjb4_E9Rcwm_LRKTA__yP
zLyUjBON#pKNlrgKqNt_xWl?0eLtd>;f?cjF;`lyz9=<lnaDO$e{q@}%Bb&;sW>r_1
z2-U{4xvR7Ol$42(F0`^_%U3Gcf3lz=UnAg;Gdd53c6x!$CK&J%1FLw@`NEV29X%NC
z?0$NL-Qq(Mc?N$?F-)L+%y$?mo$IQbjoE=Nnrh%v_Ic!X^dwJ=6kUnue^VcksciqQ
zi-_QoyJF<->~ul7?QKw=SL9J0qn+^+ro`5SrlDH6f)OT9X>1CNUgWx7(Yd>B%VZz_
z?#D5j(t5ww(Ft^fn@*^sP9Md%Sr&T@%{kDI8gLQdk3CJ!$jr*R40}tfyAW3o>RYna
zA(08emVsL^nP9TLQsX}(`BP)Khy<t#miZ&CwBz)Lihr`yKcOz^6_EIDzgiprr%~+#
zb95P@Qe*NT#qIu-A}FK?(?LTEage4i!_HKXNvGF`O&f?N#l?j3(*^CxyUKpgAzYiT
zCr7urj`=ZzK5XckT6A<1<d-D^i<)&IM!Nap+OGEIsudsKo+W3VnrA69`zY7RiqOZJ
zY4}eY^g+QsXCA&Lhm>e&L`GilcwhpbuihC7?mg}#Bi-4J8K7h*diP%4TG53k*M^}0
zfnsD4N`T5FiXFH7h0BQH3z=a@Ummm8-3@0nhvfNA|4(R3trvl9YyQ|hk+)f0*CjWE
zF{<`t)T9)~%Gjs&>Qi@5XG<&DRl=HnAl>w1?Kg~f1xL{D&f9FF3hZJ%vK4PTec!_p
zy@>pFQVVI1F5&idvk<oJ!cqy)5L!az&>g7d6zCE&eEP_LTv4dstAqB(VEVaWtnmts
zCXILd<1TGDJc6y&2D>Jo@0hKC0bK7lqXVNK1+O6l{B{%Gr@kL49h(9c3q^5-39hx%
zc?Q)YXyhU$0w6@{#z-_DqC6lKlt`&=%+!pO4XzJebHeytQI!^`6KEuYna6KGOjNkI
z3IXtPpe~E8;SFM0=yys5A>&~Q=#0!CjDFkz>uySqtRL$a$fDJV#w3o8U%u>;cb7nt
zVAq6fbLups*Xf5%L)od_Q98iGQwkZL4F{g8c|n)E8q7g-j&No*&#29OCwcgXROGv}
zthJA{&$)ah&KFoaYtA<H75<xA`H|zL-vKQf7S_nJo2lf;raqgTJA^z)lO4Rg#c-;_
zRQVw}p<Be}6BuS4#$}6S2r`bAn9uRv712r-jMzs-Z0QgY*xA1<x2t{?SZFL*blE$Z
z{pLN!7c3L4$jTy)Q;2nz9Yt2Y)go$&KlRJ>02aClHBVJ*ItUp&wJ}3A&TnqK0={7%
zyQPpu|D1N&ulE_OAlU=3JO^acV?D#u&6ISEvIn)CU1HS;?$hkF`4lbD{<{5>n(Yz!
z=d3g+=%*oEeNZedLl`5NrFW6Q7OpmodR!*4F`Vo>APKNc*(P%%qE$}E73>scaD0q(
z&qvsM*R?V|;dU}qc^!RjO7N?00pNFS(E3KGHwmZ|^pZA9<eQ(=yQu~j>)9B)WxpPx
z>kcy}L5owyce8UFl@!=UVVR*d&39}rLNGq3FVt76S|#+jwMcNPMxk*|27835Z6(-Q
z#jPr)%dw5QVrVGD)*=`c3=7WRa-;8Mg`RWVva+QX#$2}K<HwJ8c^S7YffyPjG<a5%
zR=%JLKb_cDfAe%~-*xA~5w29<y>=4r%;*OrurtGnl>{F7?3?KibGm)rUmrgs+5XvG
z5qyllP4PPnstgTn&A!>X>8W`9Oz`-&HT@Z6eZxOf;6Crr&-SnKmUqgL#$zleERQ^K
z(A*78dfB1H5X`5PPSaB84oH{|nF%(h`nZzr%ytjYenZj~bsi+6x;&69@xpkyz2N$&
znTsD-po`v0i;O~NpTSR`c-ilB;tq2zBxRQ1JBe$B6*)0U*)ugrK^pbf_Z-7|9n1!`
zdcWC((U8juv)C=PpmXNf*XYONkns#H91IejsQG4mptkSlQY<VY3JmY1zH6CvtR#dz
z+Rocz*`aX4U>39T=7Wwm|B=Yg)~u87mmmytoSvzq{218;0&<Gy?X$I!DYNQc<g9*m
zTEU<HTI?uZsZrfL-lJJ-=4cDn!T5q}4CeH$EJPc_Vd;53p_t%cuiWSq>3lj#fapEZ
z*oXj6I^=CWY=zlc!22mJ??*q%NVcEd@4`XC3D?d~X5zU>r*li~vRpRhLI-!mRFIS5
zFyRqf0{@8P@&56fbha1U0JTZV%ZP-1L{Xz`t4VKMD<O(ppT15=l90#q$EFz!{VFnn
z)7{wd1JdIfg^8{h#nIP(i-&f@`;<V}uLT4n{#{)Lxxm-~fFZp~`u?l?Y1mc$fTIM0
zLxvE_FcdM^bQ2Pc^8=w~#uc-BvLktbMnUPI{dF#Tb3SKRBmB9@qq4Dhl#b)#P#3ct
zovLoNPjWOrpQC?N3+(Ib>*{rLJB;Ribvtb8;^pP*r9P6Ff4s80@jo0|_zw={{;&k<
zkO^U6f<$0oi2ut&fQF*Hk`lY4MZ3XT42i5q$9ZuH8T?5a7xde3LM=Jk6>|a^3(L|^
znHX#@GO%i`Tto4avL_g`Kcsp{I-wi}1r8oI5JAQ@?F2!t@|ylfz$wk{^F-+}#Yb6t
z^B|iAoTcAiz{f8?4m81}gKBA&XK71we;0V|w<F8!zG)Ogfy0q`_Noz(oBh-JjrH_u
z%kK%kXrUGgqU)wHs1Vzgv4M5javjt%(=1LNo-Hx8NKY@Z9_%<ez*=VJbONd!gGQun
zpZn@**Ju7Zpb+-Dxye8B5rJJg;_V!>E&_Wuf9_N|QC|M-@m;XCVZ1Ee+$^z0kq^Fp
z`63^-c8LxNP#x=Kz!U+bzF0x|Sa#U2^SUM<T_Y-##Gl=)yVd@^sIDYyeKfGP-<in-
z$$B@IS4ZbZ2pkvma7^%?6}{uR$G+@`Y0L;LHI4OJn;I1H*{-3>24>a7-F^IRI(a5z
zV+N64PFX^wri(pF;0~74&{$>z8me3uoI_FP3+S`~rBS3EmPD;RYU76b<l&XF4tMD1
z+N2(|WaI@_<&HzT3-AdsM`#akT=So0rkn6`)K-Bk34aqXaesC0A=~vB%PXcJ{LcwC
zuYeMD=h}7u0&a;ENAKhXt!C|3m~$(`X+qw=Q$A%l)XHS;_e%rww(x3GMGbf|y>k;|
zM@+W>*vBr030L%5iq^&FIJw7IP%VUNcIf&wMd17Cz{{BLJHbY}tO+(tqSq(kZ%d~*
zya}#V^~wi=$xSPbC*DTp+FIumd5rQ2k#iM!J!wsHG=$BiXIgFY_P>lscOX$)`**KP
zt48A^_!2Kis?p=x$pSsG)`BN7V<!ti43=Qvlb`K&^Ow-aGK$G_2=1<$sHB4vzcl&j
z__Xzp8M95PAa5ci7pHsrr?9oLiRds8Q`7C6(t8|;ij#1pZ28XW7x6;nf^9n*y|bF;
z6apUY@?z0P-q{pnq^HadUsykX2lIonkVEqre$asLyDHEh7lir#!e<nIHKr&_eh&pw
zvRg8xFhl5vhbTn-E{dT<na2AhL__^^+p7^Mqc@m7Tp`xX!5_jcSI_t=z{HlZS(<o7
zJ%&2tVf(()sVfR`!@n~DFIsA~s>#36eJ3a2k;mD?8_gv?%fj5f9<w;I*e}9sZXpH|
zcd=LWKgl^PK*+yxOrECrDRf)VyEuRrlrg!dsjOe#mf$}QT8!oCV|kVHMK$4QFDYH4
z*lbp>tF{kpX$f}g2<J4>Jw-Yxlgocf_4|e%J0v$!T-vFHqoI%D2tB;>w&HY$Zze&h
z*LDWfEo*3M!-M+t<IjJVgCffu^B|%T=E0anLueSyradF`H@;*q42~ZaQ>uY74f53R
zWJeig{%Mo76gn*)+U_Os7E$ew=Og^eW!S9S@oc9F&(blQ#1R&?zd9Mx@lCP!xgJ7I
z@v!FqG~n->MK&v-W~eBoq-dc8P<0){>r)LUYkhOP0OhT@gr{>qAh7N)Zni8ce-=Ji
zgbx<{BO^Iqw6CVsG2V5gCD{W=w*+OF+Dd<<z|M6w$AE*u!P^;Zn;@`&)Yi~(hyL1j
zcFV+*e33Rin5qp70H=2g`b(;)8frLJ`z=M&d0lWF!HB>?HtND(oZ3dX4xSjcABW{T
zEf$vovwUF}CD;nCy|gSdor~vY+*-Rnj-spIIIS(}VDPhh{5gA#j#mYA>Uroj<qp9s
zzf~rxvE?;B0a@ME?db6ef+m(RshmZiTD$aULFo8Hv`CX3N0Hoet)i%t$HBzeO?zbj
zTC3+qC-~stywiT;{qec+k3r+VbsxZKqqBCZ0E+CO(cw#aS7aT^#ryL3R`ou?uY308
z4Dpngca*@JeltSwg93nk4-?Urv7$qRDnYGCwQe_Dp;1jDMu)H(nQ7}m0^x>5NCR<w
z-3qJ~`#?jC)%TlAfR2&(bFB0#r*+g9kaG#gJ36pkthyr`+p&GU5SsH#7elkkwUult
zp~5s1ZeY1`mb-|ffI#~EuPM&{!chti@qQ>Q(VGI@!3lUJt`GQN*BD7Ux34viBQ4;9
zh?QHHz6wVb+dv!ZDb7n`02`|uMT3?G#x={r|M!D>KV&GfrY=a)o{tih$HHUw6!$iE
zJStFZaX?gWBCos3Ee_x0kPcYO-=pZXEz*B*&Kt9sK@SgTs8|l^XqP3;p_{%T(*B92
zD@9f9u0|P7dIIdC)H+AYh1l#|7RW(iSwntn1XJ{}{}yL4SYphrA2|8cdzoD!$$GX`
z{pGv3JKMTXgxIR)-iJ4667x|Z82hZpS~j$q$^6k^sBBv{6PIeH<RIg;xQyeF@8AmR
z(5`4GVlDh^7{kjmX<BY)PR>=ZrxK<W*vq5Tz6s;~vj9NeYBp`Y+a1=}L%<|9NVN{P
z>-3DH()R8y0P8Mux;jH2150O*I_`=>Gi0yAdn&J+!SFl|bgi4uDy|yw*3pdJQzo=U
z{Iq(B?pZ0}83zJ?I+NWIX<YNs*?EphUY!(vW<r^yX~mKVrQkO?`!|I-dJ`@GT9nTX
zpH9@cdjQ%sl(&<b&;YU*!SA4ol^XhtLFR}}Qw7sq-EFAkxr9WZQM@)*ph!-4%DBFJ
zv=@418e#8ZtyC>M^^&696KnimBvTE78(2_5AX~%Qptf3fG1J#&^*+FsV<z&~*P!dP
z_UtZh#mm}R4aQ~_MV;N~Pci#jm7z|iXN2P8vjEZRhtO%U&swmS2dfzFsQA7S_rq-0
z6VCP{efd9&_(qg}?u!&XR!eQnio7oKi{Y;5a1kBj%HX_oqEDxV4(8EMYPatr{8K(`
zw?px+N2=LugWJi`w|fr!b2z<C=@8tPMv9If`^bX2?n1m)b{`m0`iP!F*%gW3WsQsM
zkOrjuMvPLeb1$DNnu<E9aN;;CLl;F`!Yq4nH9<Be!|br(ZAsx2c&9n{HM$z4iw0X`
z|AwFcahQ3uk3HEI{+-;V^3B<+t0N9ii4^}b5mn~d1cAku5)YjkE_Blu=_LR6qplf#
z^;{Ls8^>}O)qUBxA51)ClNBEW<H`NLmloI%$t}#9X1PXs+ip+Hrd_&(pCx;*IHR^y
z49b?Q3z(#~oS(o6^hZYxiWYcs<Gd;7h#mWiu=&BIne*~2n=Z&_cNC(`qnbu)Lwett
z@CVx*B3GfOkABXqig`nOFD(*9$(Q1gaQ`_6j8FUI>!fA^M=2+ekdAlk5c@%9Tm^7h
zP<ye!lNYV{+SkSgUXdbQ4-2_PT4qeM`Iv^X^)2kW(&bfX?M~a%=ZW7$MB7qn6dA#t
z-u%EjpPXSoi5s?;AYO$Kf9_9L4YeLp%pC2#8cvb&306#D;gzyM4ISTc;Ia;hlzgAq
zl*NVw)J<hSt!}T36CRs{7Y@%!Uka$HB$qUWS|b+Da=!e;y4+jJkG<r(rm?Hl+AG(2
zMwOvQdvrjP4%p_5!{QN?mK-Ao5$-lj5b1yB+MB_V!cr=l)k|%!Bi9lymEw##<-V%r
zebH?xzfEw-Mz+Kg<P7z9#XDx~pGEfZ3d|ek!c&uTP*b_!<3calnb!B%fB-g8a>jp^
zm1^NdULhbwj&E9Z(U~rVdK%s`y$D=bPI}`T^#r;3at*N`_|3V4krPb^ve8}d<t@~v
z(+e$6cu{^45SAu5#SBvK`gZC$%R&*CO##V9F|-wmb@oGI#Ij*&*x{^BuZ!(#H{MrF
z9?UmPC}O_0|AB8O!9~%sF%XZEtOs8@ty^DnWsZ9LV~Ikm)ZBNwemVlJE8Co-tS$?(
zwFtfill$H@ZumW)*KYi{U+Wy}cpn6I!hn9`jkm#wrB9Bk|H$7X45!)8(Uh&o`15rI
zh2cmRXwbj|(k$S5N^e)ZG8Oa@KLTl=`>7Mkky}V?vVbkRbGu(J(8|(t3@M$Cbfo(c
zQBpHpt0+wrxX4!z{`8QBq?IKhey5L$34xSE`rd<xJ}DE+`_|S#L=Jh<ukU)gH}t<N
z_$n!Wdcf^I%*lH|+hm#-EdLqZv}0kvVI{7c&fvY&q3{*+K6c*rZpoXvXrQc2U+VRH
zmWu0kWZUE`SHeFAz&(nIIGDmBIh4x95xbF+%1K4{G`)n}<IZY#vI9NV!Dhi3Cm3^P
zzv=A-SvAi+EkU-o?rL=aY+#qhq9Tu#dc<nVmMV#*hx~ivn0WwpI$*AN+7XspW*Y~Q
zG2V%qBA$KklU!G1*qW&<E)#e^Azv3=vBff<whsR<Ax!KAz#57fmd}Rc=6W%kUB09<
zQ{GfG2g4nbFie1^-8vI}#HS$#a2j&%GQ=H!5jTwcjF-qRj`NzeO>z=cn`As&8o1R>
zlBVf_Y`J8YXZ5TM#b<>tsL{iF>r*uQ>ZmrMKwfn$hJ~dVQ@6}*uWy_L5fCDAigV>R
zaSLk@Uaw&XXi5L1pU9DZPaZf4+<zm+H)>9lg7ZYD3RcoTE!uYh+Dhhly@wm*f4X{8
z<<=h6cXy~6d}n58U#x75&I^W8%F*j$N$ps|%-nPnVxHJ(93(x-HUD%%Xw(@|sFeui
zhTFF|nLS)%vO~0h&3f6J2w4-{GAiPZ4Eo}AR<RrfEU!?H{o!UDh$zG5QuiWN-whqs
z$X~tr_qhfBEH<X~A)tqIF#EU#7g5HHd4@8D%$|UGO_X+9LRMcl4oCf<c#XXh5su)B
zUsflmwgWSEjKFr{E*GW)25#_Z{ys3gQ_PQetx%>X4m3&Mou_?Sxb_n%<`vtGAU~~A
zK;2abkp7^gm8&e4N5i9ZL%0Y5XP+Z}xJ#-xohAxzk|0D~sJUHiFr@t4c<qtT;~y)M
z-!vqmb74LFuTbg*3JUKDc}4HUynfcaPx0PVy?ai~DSZr&SC^#zt{HqtWz$BQVakXQ
zN$uO-_n??%Zg~L(>&sNL`^zIc^)l}5LP|`4U*UTJ-*UTby5vxLox+6bW4HxgRBBsX
zRiMXTrlm<F0*K?_;ZX3^{-(y?!93$IdFpk<Gjdb-%ROLG25U6lNGsM+Kz*b#R)=Ks
zX0XS$4KR2~MT5C6mw8LWO0lP^zD7J(qI+bq!|JBmZNP@M;9aeg9)5|NHpi#$y+IWR
zQulPFAXHN3*YsX!uH(|@4nH&M3K<nNy;k7H36??Rmqb+{Gxtv=V{Vl!TwM_`Fj~!X
z{p6Z4jq(l&a2vXfs0{jTtMUG)qpA719L8DnQ_@;Cf%g-<w>X{Rond?9-APR!qrf>1
z-Z-`-ip~gR{HAAAeLG$?arAN$ZHK>sL|piGd+I^!zhXr>#~zmWmv!SfjuG(`mrK(q
z)SpkzDVM(%A6203#<L@|e%%S<m9JB_7qGtVW?EIW^>r0Pl<~hpId*?Ut+{khcH|%e
z0*>)p4GN_))LH}1m)$G$#6~9S9Lscbh|!D}mlddqs==eN8Ul~XerdTf>dA(HL}W>G
zP|q1NLE?)Q?_U-|P+IKBIlKloy`x)k09SDIs&tI7D*lQaHBa=Xp?mK295K9&`);Yz
zO&Or08^^cGir>isS+As*AUqmUIn*<fnYLrVu;$~Jm6_I_A8Rvj2#0nCIkk&#klrys
ze4Pjm!5q6h!#%T=2t^$^(gy)|_Vm~@cW}Dto`sqf+T$Vr)|PVDm8iy=6yz_~aCbO{
z(jq<DkJ2-+NkHf?Z#rg~EyGJHZV7!EhC9U(CN2eZOgZ5J*GQV@84r{07BD69Qf`;t
z%2U>ZST_CLo^ZyZLuDTskKe~je&{fJX=vW>+>e!QlGTRwa20egGIIiO7JQQ+Td25z
zTvV)ewk_jS)^rumdL)MQpp=XItLMh_-BfVH`tCLaY06E&!7_7bttDBRFAE@d7l;@^
zKa!TNOLqS);`hKBd}AKn_g0+BF}$cK(UxjKnI;A4ypQa-dC8fmR^}DH#E4)CKM+UZ
zH^`OXJ>4seD(-9sKLh`O_aJ9U++iDxu7jv>w-5pu2Yj>m{pC3!5?!1kIS~_2M070d
z1u)`;^ORFoEtTs*RLST4!sg9TTw#*ZOk`plHGR-}NICl%twN+@iyIfHTJsUkA)%D5
zN>@nm&NXK~t+`I{&F#k<N~^q^M~`{|TXS;>c6*fXibTq<V89*6fXOqS5zrwfw`Y0c
zLTQ3}ao+x8xiOjHp#af5xwY3t_}&+sTs<z;#Khr;%9cj7*#34(m+L`u@~Bu8Jk(}x
z;-6F8!b*<$b6M}OTR)N2Ue>@-wTYaI$qkxB=9<(wg)+VIz|^aEP0-~9lvwP@32tyM
z2qjj2U6Tv32eL8;Ez4dP$n1`Ef)cNzliEMk)am?^DlEm}D)QrZSo~(+H&y0z*!Rs|
zT)7_QFU4Zek#9GIdYVAp?)0QcFeSWK&ekKmJ%mAIOb{q39#K!~g+^XYS)+P#x0&*N
zarRmX>3<b3n*<`he^Oy|-T=+ne<f&G(&v|l`SD6M3Ji?Q_&u)e+Vf7AZbf=DC-sIh
zCWOY^*h`Gv^&@!;yzlKWs7i=d2;PN=SL+Otbj}19awj@R3ULjovXyl=Ya045x{>Ss
z(~;4P$mq(#_;mT1F>o--dTU;Ox9T<{?Xp>Ym#ylHyZs5ly^!R6Z~Gqn=mj&w-vZ?+
zyPOn?QUDJ{El%3VQ=#Zok}-Fe>UcqB9#l1+?IU%$EL4T1XDnOQZE;V5M8CkBbaBCP
zijrNP{!keIN|MIi#>`7zP9S;*od}Zea1_oeyw}526-=TXs2%M3t^qrC8mj2Q1r}oS
z4-uEZP#2;vDrRH|tn!5sQOko&ZE;Sg51Tl`1AOOE)qm@w9+o$JQKG+^eZ8Y5ZdV56
zq!W}E)iG?8VsKx?9HRrNtKw8?2^A{(@*gPhU0OzSkEZmbGYr@5M=L$nIv;Fe&OW8d
zVg0-Cpygsv%@;eO-TbQt88|>|5;rhPao%7TK(xuwl5S-u%6xE_pOdQIb;aO@z&;4K
z1GV<`bYu2Oe)rT{kNr5iv9(&ua*zB(Df(HLxY@8D*xoD2SgQCCl)+>x7FEg#L&;H<
z;U5GVmITKHVX(S>rppHi!VaUneB@$ncjfqN<3CUcX}~0@6C~T$Li<xD)*?!uXmzaJ
z!&unyVPqURNwrrHBlndf0prro{|>AM2Yj47R(!X3s^3}awBRx0S&F5sQTnGKD~vpK
zBQz^jK4{!Y#p$9YUXA*^RYT8juXwlfz>QE9hl?LTW8|^W=u?g3zaf|2d0{gM!ut@<
zkfps1_=7GEkzr8`q?LzH=!%PDdy7<5g}v581TQs^HaeuA*EQ*dw9u>%GBOY_0I&VG
zhnHH__Gi8c{K$@SrVpweH8F=cL_nm9k%>vJtU2o7`i-3jRSo&CZvExyq~{xl=akk;
z;(fElNUj@q^N#n?_owXl7lYYW)LIh}#@BV5_~}D#cD6$+>t8wQHaCnfEtvi)nE9Bx
z&!1q_CY%`F;J)fq&6w+zT{<K10DRUk>LZHZF0`6qMdMkNxtK#&ofyb7hTPJxB4uNR
zex=J?v8PWWM%CmDr1*27QZSEfx^%N%9Lm1KJX5>0$8fdLtgU@hl6>8>`c8Qv#(ZCW
zEGRi~NQTgz7*BvJBhWnGndVa{TU?wC13DtQF@g?j?90D+i-#R!^I?&n0twPNQa{dO
zr1Zt@<w^4p&(q`<pj-XML6=wCTNP*e)NP!M820UD`na@qUWeO?p0BhVw-be$0bk^1
zl;-(rYR1F2nzIP~E+vgz{Pq5x0#kd7QEh*6@u~@a7gldI<e82wRAyyhvhPOc^%ND7
z2dfvvi>46sbJv=RTg5-c0QN&?!8*ELeLvlucR}m%__D4zeaAL!rk9p?YJc?e(lcf}
z8v$tpqddj~!XzeILE~k)N}<CO^fg$PTcqAZ8mRQ!h`VQiU(O7!n=O8{@xaz-sK(>2
zf&Aq%sU?ftokN#uIIGX$)cjqEB=%OiqGwON!a-KbHJ@TgC1r3IP&0e;#pi?lSVG4F
z(HBoYm}BEdqP9x6U$5;8tW{j1J-7g6Th_^|mJy_AKJNQo3d6k)-y0rc$JH$|;}yfc
zsYxdUv%b?-q$z^2>#+$ECSj~B9HG?Mx>Yc(ShnT6_jH1lkSg>2cY+ZI^v73t8Vg3`
zF8Y?Yb$<#S(7&N0prb8wVCLNGhCM%1(I#nOXUwZA#1P$x<!7F%H*o|J6a)x5oeMMc
zMP#8xu+B_v)U31)*&kqj6Z>NJB;4|Nab)vlp1xH{1^2NS=LT+jfB5dO`d?AU*#)7-
zp-|i#E{C0CZ-~Eo^9{18*Ff2axCI+Vj^<U^6!^e4=N}ECfF^PtQK!h4_zvhQv+v3g
z8IXJLys5PYiIFV6>N_B|km6d`F~n7A{Lils%Umu&J}?S|aq87CFF4Hl&k$-UHxk)^
zwRS}f$KkPH+X!Ju%37NX?VvZFq~n3m)?#(u@E`T&UylBi^=10}Wc)uH@>4V8+aa~i
zMr|?OE$qktzbcYg#vn-f|8&X!wI%=Ql>Be-Q4(wDJ|z+{a>Kz<|0l91LKvCh&i@-p
T5}WC966YAPkX~v2d+>h%s8Lp0

diff --git a/skills/project-bootstrap/README.md b/skills/project-bootstrap/README.md
index f2ce38a..fe54434 100644
--- a/skills/project-bootstrap/README.md
+++ b/skills/project-bootstrap/README.md
@@ -59,10 +59,13 @@ projects bootstrapped at different times debuggable.
 4. **Step 5.5.** Write `bootstrap-manifest.md` recording the versions of
    `project-bootstrap`, `setup-wiki`, `setup-tasks`, `project-discipline`,
    `setup-interns`, and `using-interns` used.
-5. **Step 5.6.** Detect the official `superpowers@claude-plugins-official`
-   plugin via `~/.claude/plugins/installed_plugins.json`. If absent, print
-   a one-time chat recommendation with the install command and upstream
-   link. Never auto-installs, never modifies project files.
+5. **Step 5.6.** Skill dependencies check. Walk the canonical trigger list
+   in `CLAUDE.md`, look each up in an embedded `trigger → fulfiller` map,
+   detect what's missing on this host (`~/.claude/skills/<name>/SKILL.md`
+   for skills, `~/.claude/plugins/installed_plugins.json` for plugins),
+   and print one chat-only block listing every missing fulfiller with a
+   copy-pasteable install command. Prints a single ✅ line when nothing
+   is missing. Never auto-installs, never modifies project files.
 6. **Commit.** `chore: bootstrap project structure` for fresh repos, or
    `chore: upgrade project structure` adding only the new files for existing
    ones. Pushes only on explicit user request.
diff --git a/skills/project-bootstrap/SKILL.md b/skills/project-bootstrap/SKILL.md
index f925d68..2de14cc 100644
--- a/skills/project-bootstrap/SKILL.md
+++ b/skills/project-bootstrap/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: project-bootstrap
-version: 1.6.0
+version: 1.7.0
 description: >
   Initializes or upgrades a project in the current folder: git, .gitignore, README.md,
   .wiki/ using Karpathy's method, .tasks/ for task tracking, CLAUDE.md with skill triggers.
@@ -346,47 +346,94 @@ If a delegated setup-skill is unavailable on this machine (e.g. user installed o
 
 ---
 
-## Step 5.6 — Recommend `superpowers` plugin (chat-only, never auto-install)
+## Step 5.6 — Skill dependencies check (chat-only, never auto-install)
 
-The `CLAUDE.md` template just written contains `use superpowers` as a trigger.
-That trigger is a no-op unless the official `superpowers` plugin is installed
-on the host. On a fresh machine the plugin is often absent, and the user
-won't know the trigger is silently dead. Detect and recommend.
+The `CLAUDE.md` template just written contains canonical trigger lines.
+Each one is a no-op unless the corresponding skill or plugin is installed
+on the host. On a fresh machine these are often absent, and the user
+won't know the trigger is silently dead. Detect what's missing on this
+machine and print one informational block in chat — never write into any
+project file, never auto-install.
 
-Read `~/.claude/plugins/installed_plugins.json`. The path is identical on
-Windows / Linux / macOS — `~` resolves correctly under git-bash too.
+### Trigger → fulfiller map
 
-Look for the key `superpowers@claude-plugins-official` under `plugins`.
-Two outcomes:
+Source of truth for this map is the canonical `assets/CLAUDE.md.template`.
+When a new trigger is added there, also add a row here in the same commit.
+Mismatch between template and map → silent gaps in the recommendation.
 
-- **Installed** — say nothing. Skip to Step 6.
-- **Missing** (key absent, or the JSON file itself doesn't exist) — print
-  this block in chat exactly once. Do **not** write it into any project file:
+| Trigger line in `CLAUDE.md` | Fulfiller | Kind | Detection path | Install command |
+|---|---|---|---|---|
+| `talk like a caveman` | `caveman` | skill | `~/.claude/skills/caveman/SKILL.md` | `bash scripts/install.sh caveman` |
+| `use superpowers` | `superpowers@claude-plugins-official` | plugin | key `plugins["superpowers@claude-plugins-official"]` in `~/.claude/plugins/installed_plugins.json` | `/plugin install superpowers@claude-plugins-official` |
+| `use project wiki` | `using-wiki` | skill | `~/.claude/skills/using-wiki/SKILL.md` | `bash scripts/install.sh using-wiki` |
+| `use task management system` | `using-tasks` | skill | `~/.claude/skills/using-tasks/SKILL.md` | `bash scripts/install.sh using-tasks` |
+| `check across all projects` | `using-projects-meta` | skill | `~/.claude/skills/using-projects-meta/SKILL.md` | `bash scripts/install.sh using-projects-meta` |
+| `pull remote before work` | `pulling-before-work` | skill | `~/.claude/skills/pulling-before-work/SKILL.md` | `bash scripts/install.sh pulling-before-work` |
+| `follow project discipline` | `project-discipline` | skill | `~/.claude/skills/project-discipline/SKILL.md` | `bash scripts/install.sh project-discipline` |
+| `delegate to interns when allowed` | `using-interns` | skill | `~/.claude/skills/using-interns/SKILL.md` | `bash scripts/install.sh using-interns` |
+| `we're on Windows` / `we're on Linux` / `we're on macOS` | `active-platform` | skill | `~/.claude/skills/active-platform/SKILL.md` | `bash scripts/install.sh active-platform` |
 
-  ```
-  ℹ️  Recommended: install the official `superpowers` plugin
+### Algorithm
 
-  CLAUDE.md now contains `use superpowers`, but that trigger is a no-op
-  until the plugin is installed. With it, every session auto-loads
-  brainstorming, planning, code-review, debugging, and TDD skills.
+1. Read the project's `CLAUDE.md` (just-written or pre-existing). Extract
+   every non-empty, non-comment line — these are the active triggers for
+   THIS project. The user may have removed canonical lines on purpose;
+   respect that — only check what's actually in the file.
+2. Match each line against the trigger column above using `trim` + `tolower`
+   substring (same matching as Step 5 idempotent merge). Lines that don't
+   match any row are user-custom — skip silently. The platform line matches
+   the `active-platform` row regardless of which platform is pinned.
+3. For each matched canonical line, check the detection path:
+   - `kind: skill` → does `~/.claude/skills/<name>/SKILL.md` exist?
+   - `kind: plugin` → does `~/.claude/plugins/installed_plugins.json` contain
+     the plugin key under `plugins`? (Treat malformed JSON as "missing" and
+     continue — don't crash the bootstrap over a detection edge case.)
+4. Collect every fulfiller that's missing. Two outcomes:
 
-  Install (run inside Claude Code):
-    /plugin install superpowers@claude-plugins-official
+   - **All present** — print one line:
 
-  Source: https://github.com/anthropics/claude-plugins-official
+     ```
+     ✅ all skill dependencies satisfied — every CLAUDE.md trigger has its fulfiller on this host.
+     ```
 
-  After install + Claude Code restart, the trigger picks it up.
-  ```
+     Skip to Step 6.
 
-**Hard rule — never auto-install.** Slash commands aren't callable from a
-skill, and silently mutating user-level plugin state without consent is
-overreach. The recommendation is informational. The user can install it
-later, ignore it entirely, or remove the `use superpowers` line from
-`CLAUDE.md` if they prefer a leaner setup.
+   - **Some missing** — print one block in chat exactly once. Do **not**
+     write it into any project file:
 
-If the JSON file is malformed (rare), treat as "missing" and print the
-recommendation. Do not crash the bootstrap over a plugin-detection edge
-case — the file isn't ours to fix here.
+     ```
+     ℹ️  Recommended: install the following to fulfill CLAUDE.md triggers
+
+     The triggers below are present in CLAUDE.md but their fulfillers are
+     missing on this machine — they're silently no-ops until installed:
+
+       trigger                                  fulfiller (kind)
+       <trigger-line>                           <fulfiller> (<kind>)
+       <trigger-line>                           <fulfiller> (<kind>)
+       …
+
+     Install (run inside Claude Code or terminal):
+       <install command 1>
+       <install command 2>
+       …
+
+     After install + (for plugins) a Claude Code restart, the triggers pick
+     them up.
+     ```
+
+### Notes
+
+- **MCP-server-backed skills** (`using-context7`, `using-projects-meta`,
+  `using-interns`) — only the `using-X` policy skill is checked here. If
+  the MCP isn't registered, the `using-X` Prerequisites pointer fires
+  `setup-X` at first use; bootstrap doesn't duplicate that detection.
+- The `~/.claude/skills/` and `~/.claude/plugins/` paths resolve identically
+  on Windows / Linux / macOS — `~` works under git-bash too.
+- **Hard rule — never auto-install.** Slash commands aren't callable from a
+  skill, and silently mutating user-level skill / plugin state without
+  consent is overreach. The recommendation is informational. The user can
+  install some / all / none of the recommendations, or remove canonical
+  lines from `CLAUDE.md` to lean the project's trigger set down.
 
 ## Step 6 — Commit