From d9728ef2e7ae58ec593befc0a88318bef55ece9f Mon Sep 17 00:00:00 2001
From: vitya <vitya.kuznetsov@gmail.com>
Date: Tue, 5 May 2026 22:35:55 +0300
Subject: [PATCH] meta(tasks): pause [active-platform-eval] after design +
 pre-flight

Combined the two backlog tasks [active-platform-tuning] +
[active-platform-eval] into a single workstream. Eval IS the tuning
mechanism; "wait for 5 real signals" was a placeholder replaced by
a 20-query synthetic eval set balanced across Win/Lin/Mac.

Spec written at .wiki/concepts/active-platform-eval-design.md
(~150 lines): 20 queries (>=3 should-trigger per OS + near-miss
negatives), run_loop.py 5-iter autoloop in parallel with manual
body sweep (WSL clarity, BSD/macOS expansion, ambiguity policy).
Workspace at .tasks/active-platform-eval/ (eval-set.json committed,
iterations gitignored). Version bump 1.0.0 -> 1.1.0 planned (MINOR).

Pre-flight verified: claude CLI on PATH at C:\nvm4w\nodejs\claude.ps1
(Claude Code 2.1.128); run_loop.py present in skill-creator install.
Both autoloop deps satisfied -- no fallback to manual single-pass.

Per-task file at .tasks/active-platform-eval.md (Goal, Key files,
Decisions log, Open questions, Notes). STATUS.md collapsed the two
original blocks into one paused block; resume point is Q2
(write 20 queries solo vs run skill-creator HTML-review template).

Also fixed in same pause: [install-ps1] STATUS scope expanded to
paired install.sh + install.ps1, cross-platform parity, prune flag
(lesson from [compress-dedup]).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 .tasks/STATUS.md                              |  27 ++--
 .tasks/active-platform-eval.md                |  49 +++++++
 .wiki/concepts/active-platform-eval-design.md | 124 ++++++++++++++++++
 .wiki/index.md                                |   1 +
 .wiki/log.md                                  |   1 +
 5 files changed, 184 insertions(+), 18 deletions(-)
 create mode 100644 .tasks/active-platform-eval.md
 create mode 100644 .wiki/concepts/active-platform-eval-design.md

diff --git a/.tasks/STATUS.md b/.tasks/STATUS.md
index 07f1b7a..1e3f030 100644
--- a/.tasks/STATUS.md
+++ b/.tasks/STATUS.md
@@ -1,5 +1,5 @@
 # Task Board
-_Updated: 2026-05-05 (compress-dedup done)_
+_Updated: 2026-05-05 (active-platform-eval paused — design done, awaiting eval-set authorship decision)_
 
 <!--
   Canonical layout. One block per task. Per-task deep context lives in
@@ -46,10 +46,10 @@ _Updated: 2026-05-05 (compress-dedup done)_
 
 ---
 
-## ⚪ [install-ps1] — PowerShell-native install.ps1
+## ⚪ [install-ps1] — paired install.sh + install.ps1 (cross-platform parity, with --prune)
 **Status:** ready
-**Where I stopped:** (not started) — `install.sh` already works in git-bash on Windows, so this is convenience for PS-only users
-**Next action:** mirror `scripts/install.sh` logic in PowerShell (copy `skills/<name>/` → `~/.claude/skills/<name>/`, support `$env:CLAUDE_SKILLS_DIR` override)
+**Where I stopped:** (not started) — `install.sh` exists, `install.ps1` missing; both must coexist (PS users on Windows shouldn't be forced into git-bash, Linux/Mac users shouldn't be forced into pwsh). Cross-platform = bash + PS *paired*, behaviorally identical.
+**Next action:** (a) write `scripts/install.ps1` mirroring `install.sh` logic (copy `skills/<name>/` → `~/.claude/skills/<name>/`, support `$env:CLAUDE_SKILLS_DIR` override); (b) add `--prune` flag to **both** scripts that drops `~/.claude/skills/<name>/` for any name not in `skills/<name>/` (lesson from `[compress-dedup]` — manual prune was needed because install.sh can't); (c) confirm `build.ps1`/`build.sh` are already paired (they are) and document the parity invariant in `.wiki/concepts/install-cross-platform.md`. README's install quick-start should show both variants side-by-side per `active-platform` cross-platform-docs convention.
 **Branch:** (not started)
 
 ---
@@ -62,20 +62,11 @@ _Updated: 2026-05-05 (compress-dedup done)_
 
 ---
 
-## ⚪ [active-platform-tuning] — tune active-platform triggers based on real usage
-**Status:** ready
-**Where I stopped:** (not started) — current triggers are best-guess; haven't observed real misfires/missed-fires yet
-**Next action:** keep a tally of times the skill should have triggered but didn't (or vice versa); revise the description / trigger list after ~5 real signals. Also add WSL handling explicitly if it comes up
-**Branch:** (not started)
-
----
-
-## ⚪ [active-platform-eval] — run formal skill-creator eval loop on active-platform
-**Status:** ready
-**Where I stopped:** (not started) — depends on having ~5 real interactions logged for tuning context
-**Next action:** invoke `skill-creator` to set up an eval set for `active-platform`; benchmark current vs revised description
-**Branch:** (not started)
-**Blocker:** waits on `active-platform-tuning` to gather signals first
+## 🟡 [active-platform-eval] — eval-driven tuning of active-platform (description + body), absorbs `[active-platform-tuning]`
+**Status:** paused
+**Where I stopped:** design doc complete (`.wiki/concepts/active-platform-eval-design.md`, ~150 lines); per-task file complete (`.tasks/active-platform-eval.md`); STATUS.md collapsed the two original ⚪ tasks into this one block. Pre-flight verified: `claude` CLI on PATH at `C:\nvm4w\nodejs\claude.ps1` (Claude Code 2.1.128); `run_loop.py` present at `~/.claude/plugins/cache/claude-plugins-official/skill-creator/unknown/skills/skill-creator/scripts/run_loop.py`. Stopped right before eval-set authoring at user request — paused for asynchronous follow-up. No code touched, no tooling launched, no `.tasks/active-platform-eval/` workspace dir created yet.
+**Next action:** resume by answering Q2 from the chat ("eval set — write 20 queries solo from current SKILL.md + concept-page open questions, or run skill-creator's HTML review template first for user-driven edits before kickoff?"), then (a) build `.tasks/active-platform-eval/eval-set.json`, (b) snapshot skill to `.tasks/active-platform-eval/skill-snapshot/`, (c) launch run_loop.py in background, (d) parallel manual body sweep, (e) apply changes + bump to 1.1.0 + rebuild + reinstall + final report + commit.
+**Branch:** master
 
 ---
 
diff --git a/.tasks/active-platform-eval.md b/.tasks/active-platform-eval.md
new file mode 100644
index 0000000..22d5b28
--- /dev/null
+++ b/.tasks/active-platform-eval.md
@@ -0,0 +1,49 @@
+# active-platform-eval
+
+## Goal
+Tune `active-platform` (description + body) using skill-creator's `run_loop.py` for description optimization in parallel with a manual body sweep. Replaces the placeholder "5 real signals" approach with a 20-query synthetic eval set balanced across Windows / Linux / macOS. Absorbs the two ⚪ tasks `[active-platform-tuning]` + `[active-platform-eval]` into one workstream — they were inseparable in practice (eval *is* the tuning mechanism). Bumps `version: 1.0.0 → 1.1.0` (MINOR — improved triggering + expanded body coverage; behavior compatible).
+
+## Key files
+- `skills/active-platform/SKILL.md` — frontmatter description (run_loop output) + body (manual sweep) + version bump
+- `dist/active-platform.skill` — rebuild after edits
+- `~/.claude/skills/active-platform/` — reinstall
+- `.tasks/active-platform-eval/eval-set.json` — 20-query trigger eval set, committed before kickoff
+- `.tasks/active-platform-eval/iteration-N/` — workspace for run_loop iterations (gitignored; transient)
+- `.tasks/active-platform-eval/.gitignore` — scopes the iteration subdirs out of git
+- `.wiki/concepts/active-platform-eval-design.md` — design doc (this task's spec; already written)
+- `.wiki/concepts/active-platform-eval.md` — final report (eval set summary, before/after scores, body diff summary)
+- `.wiki/concepts/active-platform-decision.md` — open-questions list (WSL, macOS coverage) is exactly what this eval resolves; cross-link
+- `.wiki/index.md` — add new concept entry
+- `.wiki/log.md` — append decision line
+- `.tasks/STATUS.md` — collapse `[active-platform-tuning]` + `[active-platform-eval]` ⚪ blocks into one 🔴 active block, then 🟢 done
+
+## Decisions log
+- 2026-05-05: combined the two backlog tasks into one. The split was an artefact of the original "wait for production misfires" model; synthetic eval covers the same ground in one pass with controlled cross-platform balance.
+- 2026-05-05: chose autoloop (`run_loop.py` × 5 iterations) **in parallel with** manual body sweep, per user explicit request ("давай одновременно"). The two halves don't conflict — autoloop only mutates frontmatter description; body sweep only mutates body.
+- 2026-05-05: model for run_loop = `claude-opus-4-7` (current session model — triggering test must match what the user actually experiences in production).
+- 2026-05-05: workspace at `.tasks/active-platform-eval/` (project-internal, not `~/AppData/Local/Temp/...`) so the eval set lives in git and the workflow is reproducible from any clone. Iteration subdirs gitignored — transient HTML reports + per-iteration outputs would balloon the repo.
+- 2026-05-05: eval set composition forced cross-platform balance: ≥3 should-trigger queries per OS (Win/Lin/Mac), rest implicit-shell-context. ≥10 should-not-trigger queries are deliberately near-misses (library API questions, README meta-questions, architecture talk) — only 1 genuinely-unrelated negative as a sanity baseline. Per-question-override cases marked `should_trigger: true` (the skill *should* fire, but body handles no-session-flip behavior, which the eval can't measure directly).
+- 2026-05-05: spec lives at `.wiki/concepts/active-platform-eval-design.md` per project-discipline Rule 1 (overrides skill-creator's default `docs/superpowers/specs/`). Final report goes to a sibling `active-platform-eval.md` (separate "what we're going to do" vs "what we did").
+- 2026-05-05: version bump 1.0.0 → 1.1.0 (MINOR) — added capability (better triggering, broader body coverage), no removed coverage, behavior compatible. Recorded in commit message per Rule 3.
+- 2026-05-05: install-ps1 task scope expanded in the same session (paired install.sh + install.ps1, cross-platform parity, --prune flag) — out of scope here, but logged in STATUS.md so we don't lose the requirement when this task closes.
+
+## Open questions
+- [ ] Does the `claude` CLI exist on PATH? `run_loop.py` shells out to `claude -p` for triggering tests. If not on PATH → fall back to manual single-pass description rewrite (still useful, but loses the train/test optimization).
+- [ ] How does `run_loop.py` behave on Windows? skill-creator's docs assume bash-like shell for the invocation; may need to invoke through git-bash or adjust working-directory handling.
+- [ ] Per-question override eval cases — confirmed `should_trigger: true` (skill fires) but the no-session-flip behavior is body-driven, not measurable by trigger eval. Document in `.wiki/concepts/active-platform-eval.md` final report so future readers know the eval didn't directly measure that.
+
+## Completed steps
+- [x] 2026-05-05: read current `active-platform/SKILL.md` (lines 1-86) and `active-platform-decision.md` (lines 1-46) to baseline scope and known weak spots (WSL, macOS coverage, trigger phrase comprehensiveness).
+- [x] 2026-05-05: invoked `superpowers:brainstorming` skill, walked through the design choices (combine vs split, autoloop vs manual, parallel vs sequential), reached approval on combined-and-parallel plan.
+- [x] 2026-05-05: wrote design doc `.wiki/concepts/active-platform-eval-design.md` (per project-discipline Rule 1).
+- [x] 2026-05-05: pre-flight verified — `claude` CLI on PATH (`C:\nvm4w\nodejs\claude.ps1`, Claude Code 2.1.128); `run_loop.py` present at `~/.claude/plugins/cache/claude-plugins-official/skill-creator/unknown/skills/skill-creator/scripts/run_loop.py`. Both autoloop dependencies satisfied; no fallback to manual single-pass needed.
+- [x] 2026-05-05: STATUS.md collapsed the two original ⚪ tasks (`[active-platform-tuning]` + `[active-platform-eval]`) into one block, set 🔴 active during design phase, then 🟡 paused at user request before eval-set authorship.
+- [x] 2026-05-05: paused at user request — task complete through design + tooling pre-flight; resume point is Q2 (write eval set solo vs HTML-review).
+- (further steps appended during implementation when resumed)
+
+## Notes
+- Skill-creator path on this machine: `~/.claude/plugins/cache/claude-plugins-official/skill-creator/unknown/skills/skill-creator/`. `run_loop.py` lives under that at `scripts/run_loop.py`.
+- Snapshot the current skill before kickoff: `cp -r skills/active-platform .tasks/active-platform-eval/skill-snapshot/` so the run_loop's "old description" baseline matches what we're tuning *from*, regardless of any edits I make to the body during the parallel sweep.
+- run_loop accepts `--max-iterations N`. Plan = 5 (skill-creator default + sufficient signal for a single description field).
+- run_loop output: `best_description` selected by held-out test score, not train score (skill-creator's anti-overfit choice). Trust the test-score winner unless qualitative review of the score table reveals an obvious flaw.
+- After this task: `[install-ps1]` (already updated in STATUS.md to require paired install.sh + install.ps1 + `--prune`), then revisit any further skill backlog items.
diff --git a/.wiki/concepts/active-platform-eval-design.md b/.wiki/concepts/active-platform-eval-design.md
new file mode 100644
index 0000000..7b607cb
--- /dev/null
+++ b/.wiki/concepts/active-platform-eval-design.md
@@ -0,0 +1,124 @@
+---
+title: "Design: active-platform eval + tuning"
+type: concept
+tags: [active-platform, eval, skill-creator, tuning]
+updated: 2026-05-05
+---
+
+# Design: `active-platform` eval + tuning
+
+> Tune the `active-platform` skill (description + body) using skill-creator's `run_loop.py` for description optimization, executed in parallel with a manual body sweep. Replaces the placeholder "wait for 5 real signals" approach with synthetic, balanced signals across Windows / Linux / macOS. Absorbs the two ⚪ tasks `[active-platform-tuning]` and `[active-platform-eval]` into a single workstream — they're inseparable in practice (eval *is* the tuning mechanism).
+
+## Why combine the two tasks
+
+`[active-platform-tuning]` was originally framed as "tune description based on real-usage signals". `[active-platform-eval]` was "run the formal skill-creator eval loop, blocked by tuning gathering signals". The blocker assumed signals come from production — but a synthetic eval set covers the same surface area in one pass, with controlled cross-platform balance, and produces both the data *and* the tuned description in the same run. Splitting them was an artefact of the original "wait for misfires" mental model. We're not waiting any longer.
+
+## Scope
+
+**In scope:**
+1. Build a 20-query trigger eval set covering Windows, Linux, macOS, and ambiguous shell-context cases, plus near-miss negatives.
+2. Run `skill-creator/scripts/run_loop.py` (max 5 iterations, train/test split) against the current `active-platform/SKILL.md` description, capturing `best_description`.
+3. In parallel with the loop, manually sweep the SKILL.md body for known weak spots (WSL handling, BSD/macOS divergences coverage, ambiguity policy clarity).
+4. Apply `best_description` to the frontmatter; apply manual body edits.
+5. Bump `version: 1.0.0 → 1.1.0` (MINOR — improved triggering + expanded body coverage; behavior compatible).
+6. Rebuild `dist/active-platform.skill`, reinstall to `~/.claude/skills/active-platform/`.
+7. Document outcome (eval set, before/after scores, body diff summary) in `.wiki/concepts/active-platform-eval.md` (separate from this design doc — this is *what we're going to do*; that's *what we did*).
+
+**Out of scope:**
+- Description optimization for any other skill (this is just `active-platform`).
+- Renaming the skill or restructuring the trigger phrase table.
+- Changing the cross-platform-docs convention (that lives in the skill body and is fine).
+- Building `install.ps1` or any cross-platform install work — that's `[install-ps1]`, downstream of this task.
+
+## Eval set composition (20 queries)
+
+**10 should-trigger queries**, distributed:
+
+| Bucket | Count | Examples (sketch — final list lives in `.tasks/active-platform-eval/eval-set.json`) |
+|---|---|---|
+| Windows-explicit | ≥3 | "мы на винде, дай команду установки X", "I'm on Windows, give me the README quick-start", "сейчас под виндой, как поставить Y через scoop" |
+| Linux-explicit | ≥3 | "we're on a Linux box, write a one-liner для systemd unit", "I'm on Ubuntu prod, как настроить cron", "переключись на линукс, нужен install для apt" |
+| macOS-explicit | ≥3 | "я на маке, как поставить через brew", "I'm on a Mac, how do I configure zsh prompt", "switch to macOS, дай команду для plist" |
+| Implicit shell context | rest | "give me README quick-start for a CLI tool", "напиши one-liner установки", "how do I run this in a fresh terminal" — should still trigger because output is shell-bound, even without OS-trigger word |
+
+**10 should-not-trigger queries** — near-misses, not obvious negatives:
+
+| Bucket | Count | Sketch |
+|---|---|---|
+| Library API questions | 3 | "как использовать `subprocess.run` в Python", "what does `os.path.join` do" — touches shell-adjacent territory but is code-question, not produce-commands-for-user |
+| Architecture / design talk | 2 | "should I use Redis or Postgres for X", "explain microservices vs monolith" — no command output |
+| README content questions (non-commands) | 2 | "what should the description section of a README contain", "how do I write a good API doc" — README *meta*, not quick-start |
+| Per-question override tests | 2 | "how would this look on the prod box, which is Ubuntu" — should trigger (per-question), but **must not flip the session-wide default away from current**. The skill body addresses this; eval should test the description doesn't over-trigger and switch sessions on stray "on Ubuntu" mentions. *Mark as should-not-trigger session-switch; ambiguous for skill activation — TBD during eval set finalization.* |
+| Genuinely unrelated baseline | 1 | "explain the halting problem" — sanity check that the negative bucket isn't all subtle-near-misses |
+
+Final eval set committed at `.tasks/active-platform-eval/eval-set.json` before the run starts (so the eval is reproducible from git).
+
+## Workflow (parallel)
+
+```
+┌─ MAIN AGENT ─────────────────────────────────┐
+│                                              │
+│  1. Snapshot active-platform skill           │
+│  2. Build + commit eval set                  │
+│  3. Launch run_loop.py in background ────────┼─→ ┌─ BACKGROUND ──┐
+│                                              │   │ run_loop.py   │
+│  4. (parallel) manual body sweep:            │   │ ~5-10 min     │
+│     — re-read SKILL.md fresh                 │   │ 5 iter × 20q  │
+│     — note WSL gap, BSD-coreutils gap,       │   │ × 3 reps,     │
+│       ambiguity policy clarity               │   │ train/test    │
+│     — draft revised body sections            │   │ split         │
+│                                              │   └───────────────┘
+│  5. ← run_loop completes → read              │            │
+│     best_description from output JSON        │ ←──────────┘
+│                                              │
+│  6. Apply best_description to frontmatter   │
+│  7. Apply body sweep edits                   │
+│  8. Bump version 1.0.0 → 1.1.0               │
+│  9. Rebuild dist/, reinstall                 │
+│ 10. Write .wiki/concepts/active-platform-    │
+│     eval.md (results + before/after)         │
+│ 11. Update wiki index + log                  │
+│ 12. Update STATUS.md (both ⚪ → 🟢)          │
+│ 13. Commit, ask before push                  │
+│                                              │
+└──────────────────────────────────────────────┘
+```
+
+The two halves are independent: `run_loop.py` only touches the description field via its own iteration loop; manual body edits don't conflict because they target the body. Both converge in step 6-7 where I apply the diffs in sequence.
+
+## Tooling concerns
+
+**`run_loop.py` location:** `<skill-creator-cache>/skills/skill-creator/scripts/run_loop.py`. Need to invoke `python -m scripts.run_loop` from that directory.
+
+**Model ID for the loop:** `claude-opus-4-7` (current session model — the loop's triggering test should match the model the user actually experiences).
+
+**`claude` CLI dependency:** `run_loop.py` shells out to `claude -p` to test triggering. Need to confirm the `claude` CLI is on PATH before kickoff. If missing, fallback to manual single-pass description rewrite.
+
+**Workspace path:** `.tasks/active-platform-eval/` — gitignore the per-iteration subdirectories (transient outputs, benchmarks, HTML reports), commit only `eval-set.json` and the final summary in `.wiki/concepts/active-platform-eval.md`. Add a `.gitignore` line scoped to that workspace.
+
+## Versioning + manifest
+
+`version: 1.0.0 → 1.1.0` — MINOR per project-discipline Rule 3:
+- Description rewrite = improved triggering, behavior compatible.
+- Body additions (WSL clarity, BSD/macOS expansion, ambiguity policy refinement) = added capability, no removed coverage.
+
+`bootstrap-manifest.md` (in projects bootstrapped from this repo) lists `active-platform: 1.0.0` — bumping doesn't propagate retroactively, but new bootstraps after this commit will pick up `1.1.0` automatically via the manifest-write step.
+
+## Spec self-review
+
+- ☑ No "TBD" — except one explicit ambiguity flag in the eval set (per-question override category) that's resolved during eval set finalization, not deferred.
+- ☑ Internal consistency: Workflow step 6 applies `best_description`, step 7 applies body edits, step 8 bumps version — all in sequence, no contradiction.
+- ☑ Scope: focused on `active-platform`. `[install-ps1]` mentioned only as downstream sequencing; explicitly out of scope.
+- ☑ Ambiguity: `should-not-trigger` for "per-question override" cases is the one tricky spot. Resolution: those queries should trigger the skill (the body explicitly handles per-question), but should NOT flip the session-wide default. Eval can only measure trigger-or-not, not session-state mutation — so mark them `should_trigger: true` and rely on the body content to handle the no-flip behavior. Documented in eval set comments.
+
+## Connection downstream
+
+After this task:
+- `[install-ps1]` becomes the obvious next item (cross-platform install scripts pair with the now-better-triggered active-platform skill).
+- `active-platform-tuning-v2` may emerge later if real-world misfires surface gaps the synthetic eval missed; tracked as a fresh task at that time, not now.
+
+## See also
+
+- [active-platform-decision](active-platform-decision.md) — original decision to make `active-platform` a skill (not memory); open questions list (WSL, macOS coverage) is what this eval surfaces and resolves
+- [skill-versioning](skill-versioning.md) — semver discipline that drives the 1.0.0 → 1.1.0 bump
+- [bootstrap-skill-deps-check](bootstrap-skill-deps-check.md) — `active-platform` is one of the 9 canonical fulfillers in the bootstrap dependency map; description tuning here doesn't change its `kind: skill` classification
diff --git a/.wiki/index.md b/.wiki/index.md
index 83187b8..bad6c55 100644
--- a/.wiki/index.md
+++ b/.wiki/index.md
@@ -29,6 +29,7 @@ Catalog of all wiki pages. One line per page, organized by type. Updated on ever
 - [wiki-realignment.md](concepts/wiki-realignment.md) — fixing `project-bootstrap` to create the Karpathy-canonical wiki layout
 - [interns-design](concepts/interns-design.md) — interns-design
 - [compress-dedup.md](concepts/compress-dedup.md) — `skills/compress/` deleted as a byte-identical dupe of `skills/caveman-compress/`; canonical kept for README + SECURITY + caveman-toolkit branding; better Process-step wording ported across; `version: 1.0.0` added to caveman-compress frontmatter
+- [active-platform-eval-design.md](concepts/active-platform-eval-design.md) — spec for eval-driven tuning of `active-platform`: combine the two ⚪ tasks into one workstream, 20-query cross-platform eval set (≥3 per OS + near-miss negatives), `run_loop.py` autoloop **in parallel** with manual body sweep (WSL / BSD / ambiguity), version 1.0.0 → 1.1.0 (MINOR). Status: paused after design + pre-flight check, before eval-set authorship
 
 ## Packages
 
diff --git a/.wiki/log.md b/.wiki/log.md
index ac848b9..c9f1407 100644
--- a/.wiki/log.md
+++ b/.wiki/log.md
@@ -46,3 +46,4 @@ Parseable: `grep "^## \[" .wiki/log.md | tail -20`.
 ## [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.
 ## [2026-05-05] decision | compress-dedup — `skills/compress/` was a stripped-down byte-for-byte dupe of `skills/caveman-compress/` (scripts/ identical SHA256 across all 7 files; SKILL.md diff = `name:` + Process step 2; descriptions textually identical = arbitrary harness tie-break + double-counted listing budget). Kept `caveman-compress` canonical: it carries README.md (benchmarks table + caveman-toolkit branding) and SECURITY.md (Snyk false-positive writeup), and matches the caveman-* prefix invariant. Ported the better Process-step wording from `compress` into `caveman-compress` (`cd <directory_containing_this_SKILL.md>` instead of brittle `cd caveman-compress` which assumes cwd). Added `version: 1.0.0` to caveman-compress frontmatter (first versioned release; aligns with skill-versioning concept). Deleted: `skills/compress/`, `dist/compress.skill`, `~/.claude/skills/compress/` (manual prune — install.sh has no prune step; future `[install-ps1]` task should add `--prune` flag). Rebuilt + reinstalled `caveman-compress`. Slash-command impact: `/compress` removed; `/caveman-compress` + `/caveman:compress` (toolkit-canonical) remain. Concept page `concepts/compress-dedup.md` written (rationale + rejected alternatives: alias-stub has no harness mechanism; "keep both" wastes listing budget; "delete caveman-compress" loses README + SECURITY).
+## [2026-05-05] design | active-platform-eval (paused) — combined `[active-platform-tuning]` + `[active-platform-eval]` into one workstream (eval *is* the tuning mechanism; "wait for 5 real signals" was a placeholder). Spec written at `.wiki/concepts/active-platform-eval-design.md`: 20-query trigger eval set balanced ≥3 should-trigger per OS (Win/Lin/Mac) + near-miss negatives, run in `skill-creator/scripts/run_loop.py` (5 iter, train/test split, model `claude-opus-4-7`) **in parallel** with manual body sweep (WSL clarity, BSD/macOS expansion, ambiguity policy). Workspace at `.tasks/active-platform-eval/` (eval-set.json committed, iterations gitignored). Version bump 1.0.0 → 1.1.0 planned (MINOR). Pre-flight verified: `claude` CLI at `C:\nvm4w\nodejs\claude.ps1` (Claude Code 2.1.128) + `run_loop.py` present in skill-creator install — both autoloop deps satisfied, no fallback needed. Per-task file at `.tasks/active-platform-eval.md`. Paused at user request before eval-set authorship; resume point is Q2 (write 20 queries solo vs run skill-creator HTML-review template for user edits first). Also fixed in same pause: `[install-ps1]` STATUS scope expanded to "paired install.sh + install.ps1, cross-platform parity, --prune flag" (lesson from `[compress-dedup]`).