Three modes now: greenfield-full (new + remote), add-remote, upgrade.
Step 0: detect git/remote/empty state for mode selection.
Step 1.5: Gitea API repo create + push.
Step 8: projects-meta sync for visibility.
Version 1.7.0 → 1.8.0 (MINOR).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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)
setup-interns (v0.1.0) — 8-phase install of the local `interns` MCP server:
detect `.common/lib/interns-mcp/` source, `pip install -e`, write
`.common/secrets/interns.env` with endpoint API keys (gitignored), register
`mcpServers.interns` in `~/.claude.json` with absolute Python interpreter
path + `cwd` so the runtime resolves config relative to project root.
Mirrors setup-projects-meta / setup-context7 confirmation-gate shape.
Description 899 chars (under the 900 budget per
feedback_skill_description_length_limit).
using-interns (v0.1.0) — runtime policy for `mcp__interns__*`. Per-session
permission grant mirrors project-discipline Rule 4: ask-mode default,
conversational grant ("разреши интернов" / "allow interns"), conversational
revoke, always-ask paths for `**/.env`, `**/secrets/**`, `**/*.key`,
`**/.ssh/**`, `**/.aws/credentials` etc with transitive rule (Claude can't
bypass by reading the file with the local Read tool and forwarding content),
cost-cap >$0.10 always asks, session-end automatic reset. Routing hints for
`bulk_text_read` (3+ files or one file >400 lines) and `transcript_distill`
(before .wiki/log.md updates / session summaries). Description 814 chars.
project-bootstrap (1.5.0 -> 1.6.0, MINOR — capability added):
* assets/CLAUDE.md.template: insert `delegate to interns when allowed`
between `follow project discipline` and `we're on Windows`.
* SKILL.md Step 5: same insertion in inline template + new commentary
paragraph explaining the trigger, no-op semantics, install pointer.
* SKILL.md Step 5.5: bootstrap-manifest table extended with
`setup-interns`, `using-interns`, `project-discipline` rows.
* README.md: Workflow Step 5.5 description + See also section both pick up
the new skills.
Root CLAUDE.md dogfood: `delegate to interns when allowed` line added.
.wiki/log.md decision entry. .tasks/STATUS.md task moved to 🟢 done.
.tasks/interns-skills-mvp.md per-task file with goal / key-files /
decisions log / open questions.
Build + install verified: `dist/{setup-interns,using-interns,
project-bootstrap}.skill` rebuilt; `bash scripts/install.sh ...` succeeded;
harness skill listing shows full descriptions for all three (no H1
fallback) — confirms the description budget held.
Versioning per project-discipline Rule 3:
* setup-interns: 0.1.0 (first edit of unversioned artifact, MAJOR=0).
* using-interns: 0.1.0 (first edit of unversioned artifact, MAJOR=0).
* project-bootstrap: 1.5.0 -> 1.6.0 (MINOR — adds capability without
breaking existing CLAUDE.md merge or manifest consumers).
Server runtime itself (`.common/lib/interns-mcp/`) is out of scope for this
task — the skills land lifecycle, policy, and bootstrap integration so any
machine where the MCP server is later installed already has Claude's
policy in place.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Step 5 was binary on upgrade (append whole template / leave alone), so
projects bootstrapped before v1.2.0 silently missed new canonical triggers
(`check across all projects`, `we're on Windows`) on re-run. Now upgrade
reads existing CLAUDE.md, substring-diffs vs template, preserves a
deliberately-pinned platform line, and appends only missing lines after
explicit confirm. Re-runs are no-ops.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
CLAUDE.md template gains a fifth trigger line, `check across all projects`
(verbatim phrase from `using-projects-meta` description). Every new or
upgraded project now auto-loads cross-project task aggregation and shared
projects-wiki access without an explicit verbal trigger.
No Step 5.7 mirror of Step 5.6 (superpowers plugin recommendation):
`using-projects-meta` Prerequisites already self-corrects to
`setup-projects-meta` when MCP tools are missing.
Synced: assets/CLAUDE.md.template, inline copy in SKILL.md (Step 5),
README.md + README.ru.md trigger lists, this repo's local CLAUDE.md,
dist/project-bootstrap.skill, .wiki/concepts/projects-meta-skills.md
(Bootstrap trigger section), .wiki/log.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
CLAUDE.md template adds `use superpowers` as a trigger, but that line
is silently dead until the official plugin is installed. New Step 5.6
reads ~/.claude/plugins/installed_plugins.json and, when the
`superpowers@claude-plugins-official` key is absent, prints a chat-only
recommendation with the install command and the upstream link
(github.com/anthropics/claude-plugins-official).
Strict no-auto-install: slash commands aren't callable from a skill,
and silent plugin install would be overreach.
Bumps project-bootstrap 1.0.0 → 1.1.0. Rebuilt dist archive.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirror the wiki split. Rename `task-status-wiki` → `using-tasks` (preserves
file history via `git mv`). Strip the "Initialization" section out — that
content moves to the new `setup-tasks` skill, which owns greenfield
creation and migration.
`setup-tasks` has 6 phases (sanity → discovery → plan + confirm → backup →
greenfield/migrate → verify → report) and two modes:
- greenfield: write `.tasks/STATUS.md` with the canonical board template
(emoji legend in a comment block; no per-task files at bootstrap — they
get created on demand by using-tasks when actual tasks are added)
- migrate: detect old flat STATUS.md (no emoji, plain `## Done`/`## In
Progress` sections), back it up, then walk the user *interactively*
through each task to extract slug / status / branch / where-stopped /
next-action. Never auto-parses the old format — too varied, real work
at stake.
`using-tasks` Prerequisites section delegates to `setup-tasks` when the
board is missing or non-canonical (no emoji, no per-task files).
`project-bootstrap` Step 4 now delegates to `setup-tasks`.
The user's manual follow-up after this commit:
rm -rf ~/.claude/skills/{wiki-maintainer,task-status-wiki}/
to clean up the stale installs of the old names. (install.sh creates the
new ones but doesn't remove the old.)
This completes the three-commit refactor (a/b/c) tracked in
.tasks/STATUS.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Rename `wiki-maintainer` to `using-wiki` (rename via git mv preserves
file history). Strip greenfield/bootstrap content out of it; add a
Prerequisites section that delegates to the new `setup-wiki` skill when
`.wiki/` is missing or non-canonical.
New `setup-wiki` skill: 6-phase procedure (sanity → discovery → plan +
confirm → backup → create/migrate → verify → report). Two modes —
greenfield (no `.wiki/`) and migrate (existing non-canon, e.g. SUMMARY.md
+ source/). Confirmation gate before any write. Templates for each canon
file (`CLAUDE.md` schema, `index.md`, `log.md`, `overview.md`,
`raw/README.md`) baked in.
`project-bootstrap` Step 3 now delegates to `setup-wiki` instead of
holding inline templates that drift from canon.
After this commit, `~/.claude/skills/wiki-maintainer/` still exists as a
stale install — the user will rm it manually after commit (c) lands the
tasks split.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Six infra skills carry `version: 1.0.0` in frontmatter:
project-bootstrap, setup-context7, task-status-wiki, using-context7,
using-markitdown, wiki-maintainer. Bumped manually on SKILL.md edits;
semver — MAJOR breaks contract, MINOR adds, PATCH wording.
project-bootstrap gets a new Step 5.5 that writes
.wiki/concepts/bootstrap-manifest.md per project — skill + version + role
table read live from each delegated skill's frontmatter, not hardcoded.
The file is overwritten on re-bootstrap; for history, git log.
Why: when canonical layout for .wiki/ or .tasks/ changes, projects
bootstrapped under the old version drift silently. The per-project
manifest makes that drift debuggable instead of guesswork. Communication
and discovery skills (caveman family, find-skills, active-platform)
aren't versioned — their content is "good copy-paste" and snapshot
mismatch isn't a layout problem.
Wiki: .wiki/concepts/skill-versioning.md documents the convention;
index.md and log.md updated. .tasks/STATUS.md tracks (a/b/c) progress.
Setup/using split for wiki and tasks (commits b and c) follows.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Bootstrap was creating .wiki/SUMMARY.md + WORKFLOW.md + source/ — none of
which match Karpathy's LLM Wiki pattern or what wiki-maintainer reads first.
The skill had to bend around an invented layout (no schema file, wrong
catalog name, missing log/overview/entities/concepts/packages).
Rewrote Step 3 to create the canonical layout verbatim:
.wiki/CLAUDE.md schema (project-specific conventions)
.wiki/index.md catalog
.wiki/log.md append-only op log
.wiki/overview.md project overview
.wiki/raw/README.md immutability note
.wiki/{entities,concepts,packages,sources}/.gitkeep
Pinned the gist URL inside the schema:
https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
Bumped dist/project-bootstrap.skill, recorded the why in
.wiki/source/wiki-realignment.md, and queued migration of *this* repo's own
.wiki/ (still on the old layout) as a backlog task — to be done deliberately.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pin every newly-bootstrapped project to Windows / PowerShell out of the box
by adding a fifth trigger line to the CLAUDE.md template. The line activates
the active-platform skill, which then governs all command/example output.
- skills/project-bootstrap/assets/CLAUDE.md.template: append `we're on Windows`
- skills/project-bootstrap/SKILL.md: sync the embedded preview in Step 5 and
document the Linux/macOS substitution
- CLAUDE.md (this repo): backfill the line — was created from old template
- dist/project-bootstrap.skill: rebuilt
- .wiki/source/active-platform-decision.md: append "Wired into project-bootstrap"
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
