- convert.sh's SKILL.md finder now excludes .claude, .codex, .codex-plugin,
.gemini, .hermes, .vibe, and docs — these are generated/symlinked mirrors
for other tools, not source-of-truth skills. On platforms where git
materializes symlinks as plain text (e.g. Git Bash on Windows), the
mirrored files were being parsed as SKILL.md candidates and failing
frontmatter extraction, flooding the run with "Skipping invalid
frontmatter" warnings (#897).
- Renamed the self-improving-agent (si) plugin's `status` and `review`
skills to `memory-status` and `memory-review` so their bare `name:`
values no longer collide with Claude Code's built-in `/status` and
`/review` commands (#885). Updated all in-plugin references
(CLAUDE.md, README, agents, hooks, references, settings.json,
plugin.json) to the new `/si:memory-status` / `/si:memory-review`
invocations.
Fixes#897 (duplicate of #896), #885.
Per PR #891 review: check_readme_badges silently skipped a badge whose regex
found no match, so a renamed or removed shield would quietly drop out of the
gate — the same silent-drift class this gate exists to catch. Now a missing
badge appends a mismatch (mirrors run_check's "no recognizable counter claims
found" precedent), so it fails loudly. Verified: renaming a badge trips exit 1;
the current README still passes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L4JerbGv6vqitUMhqHPA9g
Per PR #891 review: `mismatches: list = []` was an inconsistent drive-by
annotation vs the un-annotated locals elsewhere in the file. Revert to keep
the diff minimal and the style consistent. No behavior change.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L4JerbGv6vqitUMhqHPA9g
Follow-up to the merged agent-harness PR (#890), applying the automated review nits:
- loop_controller.py: drop unused `import shlex`; simplify cmd_record's exit-code
expression to the clearer form already used in cmd_verify (behavior-equivalent)
- SKILL.md + references/verification_discipline.md: document that plan/state files are
a trust boundary (verify shell-executes their cmd strings) — run the harness only on
files produced by goal_compiler, never untrusted input
- README.md: bump Agents 96->97 and Commands 102->103 badges (drift the previous PR
missed because derive_counters didn't validate these badges)
- scripts/derive_counters.py: add check_readme_badges — validates the Skills/Agents/
Commands shields against derived counts, closing the CI blind spot that let the badge
drift ship. Verified it fails (exit 1) on drift and passes when correct.
All gates green: plugin.json (83 OK), smoke --help/--sample (600 pass), JSON output
(0 fail), path linter (0 findings), derive_counters --check (pass).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L4JerbGv6vqitUMhqHPA9g
Two housekeeping items surfaced during the contributor-PR hardening session.
1. CHANGELOG backfill — add [Unreleased] entries for five skills that merged
without their own changelog blocks (roast #865, named-persona-adversarial-review
#867, agent-decision-receipts #868/#869, zero-hallucination-coder #870,
deep-research #872). Earlier merges updated headline counters but not this log.
2. Per-domain counter validation — scripts/derive_counters.py --check now also
validates the README "Skills Overview" per-domain table: each domain row's
count must equal the SKILL.md count in its linked folder, and every on-disk
domain must have a row. Previously --check only validated headline aggregates,
so per-domain rows drifted silently. Verified: passes on the fixed state, fails
on a wrong count, fails on a missing row, and parses exactly the 18 real domain
rows (bold-first-cell install/skills-vs-agents tables are not false-flagged).
Trued up the README table to make the new check pass: fixed six stale row
counts (engineering-team 51->52, engineering 78->80, marketing 47->48,
productivity 6->7, ra-qm-team 18->19, c-level 66->68), added the missing
markdown-html row (5), and named the newly-merged skills in their domain
descriptions. Per-domain rows now sum to the 354 headline.
Headline aggregates unchanged (354 skills / 722 refs / 82 plugins / 18 domains).
* bug: several bug fixes and improvements (see comments)
- [bug] fixed the shebang for portability (wouldn't run on my system)
- [feat] improved the inline python scripts; the `--all` and `--category` flags now read/dedupe names from the `skills-index.json` file so that stale entries (e.g. `.codex/skills/playwright-pro`) do not get treated as installable skills
- [bug] fixed the counter from installed++/failed++ to ++installed/++failed, which caused the script to exit upon installing the first skill
- [style] formatting fix
* fix(codex-install): improve error handling and validation for skill and category installation
---------
Co-authored-by: Alireza Rezvani <5697919+alirezarezvani@users.noreply.github.com>
Gate G1 (check_paths.py --all) was failing on dev's arquiteto-de-empresa
skill, surfaced into this branch by the dev merge. The 3 references are
genuine false positives: two are inside a markdown code-example showing
OKF bundle link syntax in the user's generated output, and one is a
command doc pointing at its sibling skill's references/ dir. Added to
check_paths_allowlist.txt per the workflow's documented remedy.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KEJH6wwyaEs1d6AAca2HLR
- Rewrite docs/stylesheets/extra.css with a warm clay/coral design system:
aurora hero with eyebrow badge and stats strip, gradient card hairlines,
pill tool badges, numbered steps component, reduced-motion support
- Rewrite homepage copy: plain-language 'What is an Agent Skill?' section,
3-step how-it-works, all 17 domain cards, guides section, accurate stats
(337 skills / 17 domains / 66 plugins)
- Add missing markdown-html domain to generate-docs.py (17th domain) and
regenerate catalog: +12 new pages (md-document/md-review/md-slides skills,
cs-markdown-html-orchestrator + cs-scraping-architect agents, 7 commands)
- Fix skill-internal link rewriting in the generator (./SIBLING.md and
ALL-CAPS companion files now resolve to GitHub URLs) — mkdocs --strict
now passes with zero warnings
- Refresh stale counters site-wide (177/192/204/311/338 → 337) in skills
index, plugins index, getting-started, integrations, custom-gpts, guides
- Rebuild plugins page from live marketplace.json: 13 domain bundles + 53
standalone plugins, accurate bundle table and full 66-plugin listing
- Add Guides section to nav (5 existing SEO guide pages, URLs unchanged),
point homepage tool badges at tool-specific guides and real anchors
- Tighten site_description and JSON-LD keywords for 'agent skills' /
'agent plugins' queries; update announce bar to the markdown-html launch
- No existing slugs or URLs changed — all edits are additive or in-place
https://claude.ai/code/session_015bYZ97nV4oRb3LbxCRFVcP
- calculate_cac.py: hoist 'import argparse' to module top per repo convention
- smoke_scripts.py: comment the exit-1-over-exit-3 precedence
- check_paths_allowlist.txt: reword the etc/passwd note ('outside repo root if
resolved literally', not 'deep checkouts')
- cs-scraping-architect.md: clarify both warning and error share exit 1 — parse
the JSON status field for the distinction
https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
- smoke_scripts.py: --help epilog now documents the exit-code table
(0 ok / 1 smoke failure / 3 stale exceptions)
- calculate_cac.py: real argparse --help with an epilog stating the
edit-example_data limitation and the planned --file/stdin enhancement
- cs-scraping-architect.md: add 'model: sonnet' to match sibling agents
Item 4 (senior-security references) was a non-issue — all three referenced
files exist and the now-blocking path gate is green.
https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
The blocking G1 path gate flagged '../../../etc/passwd' — a path-traversal
ATTACK EXAMPLE in a pen-testing skill's attack-vector table, not a real file
reference. It passed locally only because a deep checkout makes ../../../ climb
to the host's real /etc/passwd; on the CI runner it doesn't resolve. Allowlisted
with a reason, per the gate's documented edge-case process.
https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
Implements issue #654 Option A (embedded-sample convention) plus the
verification harness the issue asked for:
- scripts/smoke_json_output.py — new advisory gate (G9) that discovers
every tool whose --help advertises JSON output, runs <tool> --sample
<json-flag>, and asserts the stdout parses as JSON. Tools advertising
JSON without --sample are reported as 'uncovered' (a backlog, not a
failure) so the gate can be adopted incrementally; --strict flips that
to a hard failure once coverage is high. Wired into ci-quality-gate.yml
alongside G8.
- Added --sample embedded fixtures to the 5 tools named in #654:
error_budget_calculator, slo_review, blast_radius_calculator,
audit_log_analyzer, api_linter. Their required args are now optional
when --sample is passed; missing-arg behavior is unchanged otherwise.
- Fixed 4 tools the new gate surfaced (prompt_rater, coach_tip_classifier,
cheat_code_filter, redaction_linter): their --sample path printed human
text and ignored --json; it now honors the JSON flag.
- Synced the 3 dual-published standalone copies (slo-architect x2,
chaos-engineering) so the drift guard stays green.
Gate now reports 16 tools covered, 16 verified, 0 failures.
https://claude.ai/code/session_01CUWsrUNZP9jpxvAwq67UiT
- enforce-pr-target.yml: drop the no-op split/trim/join on the comment body
(array join already produces the final text)
- ci-quality-gate.yml: safety findings now emit a workflow warning instead
of being silently absorbed by '|| true'
- check_paths.py: fnmatch import hoisted to module level
- smoke_scripts.py: stale exception entries now fail the gate (exit 3) so
scripts/smoke_exceptions.txt stays tidy
https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
- derive_counters.py: python_tools condition simplified to the equivalent
parts[0] != 'scripts' (reviewer M1); dead root_scripts variable removed;
--check still passes with identical values
- fda-consultant-specialist quick-start: 820.30 example annotated as a legacy
checklist key mapping to ISO 13485 §7.3 (reviewer m3 — note: switching the
example to '--section 7.3' as suggested would break; the checker's CLI keys
are intentionally the legacy 820.x checklist indices, documented in --help)
- CLAUDE.md: audit/ directory documented as an intentional public audit
record, distinct from the gitignored AUDIT_REPORT.md (reviewer m2)
Reviewer m1 (agents/CLAUDE.md 'engineering-team/' link) is a false positive:
agents/engineering-team/ exists as an agents subfolder containing exactly the
two linked files; check_paths.py confirms 0 unresolvable references.
https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
- #805: insert missing skills/ segment in all per-skill install commands
across 5 domain READMEs (engineering-team, project-management,
marketing-skill, c-level-advisor, ra-qm-team); every path now resolves
to a real directory
- #806: pr-review-expert SKILL.md curl examples now pass Jira/Linear
credentials via stdin curl config (-K -) instead of argv, with a netrc
note, so tokens never reach the process list or shell history
- #807: implement the documented interfaces for the three senior-devops
scripts (terraform_scaffolder: aws/gcp/azure module skeletons with
optional terraform fmt/validate; pipeline_generator: GitHub Actions /
CircleCI configs with build,test,security,deploy stages and runtime
detection; deployment_manager: blue-green/rolling manifests + kubectl
runbooks with deploy/rollback/analyze subcommands); align SKILL.md
- #807: ci-cd-pipeline-builder stack_detector now detects Terraform and
Docker stacks and emits their lint/test/build commands; downstream
pipeline_generator gains a generic job for non-node/python/go stacks
- #748: sync-vibe-skills.py defaults to a flat layout one level below
~/.vibe/skills (the only depth Vibe discovers), with collision-safe
naming and a --nested flag for the legacy namespaced layout
- #785: new scripts/sync-codebuff-skills.py syncs all skills into
Codebuff's ~/.agents/skills using the same flat-layout machinery
https://claude.ai/code/session_01CUWsrUNZP9jpxvAwq67UiT
Adds cs-webinar-marketer agent + /cs:webinar command wiring the webinar-marketing skill (SKILL.md, stdlib funnel scorer, references, templates, evals) under marketing-skill/skills/. Includes a Windows cross-platform fix to scripts/generate-docs.py (normalizes os.sep to forward slashes — verified no-op on Linux) and regenerated docs. Verified: scorer runs (89/100 sample), frontmatter valid, clean merge into dev with no conflicts.
Ran the /update-docs post-creation pipeline across the whole repo.
Docs site (MkDocs):
- generate-docs.py now covers 16 domains (added research-ops at order 15
and compliance-os at order 16 + its embedded-agent mapping). Regenerated
500 pages (328 skills + 89 agents + 83 commands); build passes.
- mkdocs.yml: site_description refreshed to 338/16/51+/87+ + v2.9.0; added
the Research Operations and Compliance OS skills nav sections, the
cs-research-ops-orchestrator + 8 compliance-os agents, and the 6
research-ops command entries.
- docs/index.md: title, description, hero, the five "What's Inside" cards
(338 skills, 51+ agents, 533 tools, 62 plugins, 87+ commands), corrected
six domain-card counts, and added a Research Operations domain card.
- docs/getting-started.md: description, Vibe count, FAQ, bundles table
(six corrected counts) + a research-ops bundle row.
Cross-platform sync (all four scripts gained a compliance-os entry):
- Codex: compliance-os 9 skills symlinked + index; unrelated run/status/
review symlink churn reverted to keep the diff focused.
- Gemini: 9 compliance-os SKILL.md mirrors + index.
- Vibe (repo target): 9 compliance-os symlinks + index.
- Hermes/Vibe domain lists updated for future syncs.
compliance-os was a tracked 9-skill domain previously absent from the docs
site and the codex/gemini/vibe indices; it is now fully wired in.
The MkDocs `site/` build output is gitignored and excluded.
https://claude.ai/code/session_01PUNmQVE4WYvcrzpq2anC3D
Bundle of low-medium-severity follow-ups that were deferred when PR #720
landed the 3 blocking bugs. None of these silently break correctness —
they're discoverability, consistency, and convention gaps.
Bugs / code-quality:
1. fullstack_decision_engine.py: asymmetric cadence matching
`inputs.cadence in target or target in inputs.cadence` produced
asymmetric results — "per-pr" matched "per-pr-with-gates" but not
vice versa. Profile cadences are intentional alternatives joined
by "-or-" (e.g. "weekly-or-on-demand" → {weekly, on-demand}); now
parsed explicitly with "-with-..." modifier suffixes stripped.
Verified:
cadence=per-pr → matches per-pr, per-pr-with-gates, daily-or-per-pr
cadence=daily → matches daily-or-per-pr (only)
cadence=on-demand → matches weekly-or-on-demand
2. fullstack_decision_engine.py: rename weight_total/weight_matched
to w_total/w_matched. Backend and frontend engines already use the
short form; this aligns the three files as a family.
3. sync-gemini-skills.py: 3-way name collision in dedup logic
The naive `if name in seen_names: name = parent-name` handled one
collision but not two. Three "status" skills under "skills" parent
dirs produced two entries both named "skills-status". Now suffixes
with -2, -3, ... so each entry has a unique index name. Eliminates
the duplicate-name ambiguity surfaced when checking PR #713.
Discoverability:
4. senior-fullstack/SKILL.md: surface fullstack_decision_engine.py in
the labeled "Tools" section at the top. Previously only mentioned
inline in the body (5 references buried in the Stack Decision Matrix
section); not findable when scanning the SKILL.md.
Conventions / v2.8.0 compliance:
5. commands/cs-{fullstack,backend,frontend}-review.md: add explicit
"## Forcing-question library" section header per the v2.8.0
convention. Each lists the 7 questions inline with a pointer to
the canonical reference file.
6. agents/engineering/cs-{fullstack,backend,frontend}-engineer.md:
alphabetize the specialist list in the description field (annotated
that workflow body order remains dependency-driven). Makes the
three agent descriptions consistent as a family.
7. agents/engineering/cs-{backend,frontend}-engineer.md: promote the
"Cross-agent invocation" content out of Workflow 3 into a dedicated
"## When invoked as fork target" section with an explicit question-
skip table per parent agent (cs-fullstack-engineer, cs-cto-advisor,
cs-vpe-advisor, cs-ciso-advisor for backend; cs-fullstack-engineer,
cs-content-creator, cs-product-manager for frontend). Closes the
cross-agent contract gap the bot flagged.
Not changed:
- CLAUDE.md plugin-schema section (already corrected in #715; bot's
"stale text" claim was incorrect — it was reading the cumulative diff)
- Workflow body specialist order (intentional dependency order; would
break the SLO-first → API → DB → migration → observability sequence)
Verification:
- All 3 decision engines: --sample → exit 0
- Cadence matching: 3 test cases pass cleanly
- check_plugin_json.py --all → 0 FAIL, 0 WARN, 69 OK
- sync-gemini-skills.py → 392 unique names (was 391 unique / 1 dupe)
Resolves#712 and #714.
Claude Code's plugin spec (code.claude.com/docs/en/plugins-reference) requires
"All paths must be relative to the plugin root and start with ./". CC 2.1.144+
rejects the bare "skills" form with `Validation errors: skills: Invalid input`,
breaking plugin installs from this repo.
Changes:
- 47 plugin.json manifests migrated from "skills": "skills" → ["./skills"]
(canonical post-CC 2.1.144 form, also accepts string "./skills")
- scripts/check_plugin_json.py rewritten to enforce the live spec:
* Hard-fails on non-"./"-prefixed strings (except the legacy "skills" literal)
* Hard-fails on empty strings/arrays and non-string array entries
* Emits WARN (non-fatal) on the legacy "skills" literal as a safety net
for copied templates — the WARN tolerance can be removed later
* Tested against all four canonical forms + 3 garbage forms
- CLAUDE.md §5 rewritten to document the live spec, including the historical
context of the v2.1.107 → v2.1.144 regression window that's now closed
- 15 stale broken symlinks under .gemini/skills/ removed (orphans from older
reorgs that the sync script didn't prune because its cleanup is disabled)
Verification:
- scripts/check_plugin_json.py --all → 0 FAIL, 0 WARN, exit 0 (69 files OK)
- pytest tests/ → 2103 passed
- find . -type l ! -exec test -e {} \; → 0 broken symlinks
- Live spec forms tested: ["./"], ["./skills"], "./skills", ["./a","./b"] all pass
- Garbage forms rejected: bare "./", empty array, non-string entries, plain strings
Adds end-to-end release automation so every CHANGELOG bump produces a
matching git tag + GitHub Release with notes — no manual `gh release
create` invocations required.
- .github/workflows/release.yml — push to main triggers parse-CHANGELOG
→ check tag exists → create tag → create GH Release with notes. Idempotent
(existing tags skipped). Manual workflow_dispatch supports targeting a
specific historical version. Path-filter limits firing to actual release
pushes (CHANGELOG.md, the parser, or the workflow itself changing).
- scripts/extract_release_notes.py — stdlib-only CHANGELOG.md parser.
Outputs JSON, plain text, or github-release-formatted markdown.
Runnable standalone for preview: `python3 scripts/extract_release_notes.py
--format github-release`. Default extracts the latest entry; --version
pins to a specific release.
- CHANGELOG.md — new [2.8.0] entry covering the v2.8.0 Sprint 1 work
(business-operations + commercial domains, #688) plus the #686 plugin.json
fix (#689) and #690 regression-prevention validator + CI gate. This is the
entry the release workflow will pick up on first run after this lands on
main.
When this commit (plus the dev → main sync #692) reaches main, the workflow
fires, parses CHANGELOG, sees v2.8.0 at the top, creates the `v2.8.0` tag
and GitHub Release — automatically. All future releases follow the same
flow: add a CHANGELOG entry, merge to main, done.
Issue #686 was the second round of the same Claude Code path-validator
tightening: v2.1.107 rejected bare "./" (fixed in #539 by moving to
"./skills"), then v2.1.133 also rejected "./skills". The validator that
codified the #539 fix was still recommending "./skills" verbatim — so a
future round 3 would have hit the same trap.
This commit makes the validator catch the regression and runs it in CI:
- scripts/check_plugin_json.py
- Reject any "skills" string starting with "./" (catches both
"./skills" and "./skills/sub" patterns)
- Update docstring + error message to point at the layout-correct
forms instead of the now-broken "./skills"
- Recognize "source" and "attribution" as approved extension fields
(already documented in CLAUDE.md but not in the validator), so the
21 pre-existing false-positives go away and CI can run blocking
- Drop the "./" rejection inside arrays — CLAUDE.md says ["./"] is
the correct single-skill-at-root form
- .github/workflows/ci-quality-gate.yml
- Add blocking "Validate plugin.json manifests" step that runs the
validator on every PR
- CLAUDE.md
- Add an Enforcement note pointing at the validator and the lockstep
rule: when CC tightens its path validator again, update validator
rules and CLAUDE.md together
Verified: 69/69 manifests pass; 6-case smoke test confirms validator
rejects all three known-broken forms ("./skills", "./", "./skills/sub")
and accepts all three documented-valid forms ("skills", ["./"],
explicit array).
Co-authored-by: Claude <noreply@anthropic.com>
The user flagged that we advertise Hermes Agent as a tier-1 supported
platform in the "Works with:" list, but the actual integration was
significantly thinner than Codex/Gemini/OpenClaw:
- No committed .hermes/ tree (other platforms ship pre-generated trees)
- sync-hermes-skills.py DOMAIN_DIRS missing the 3 v2.7.0 top-level
domains (productivity, marketing, research) — running it today would
silently skip all 13 v2.7.0 skills
- Discover function only handled the flat `<domain>/<skill>/` pattern,
missing the nested-plugin pattern `<domain>/<plugin>/skills/<skill>/`
used by all v2.7.0 skills + many older plugins
- Doc count stale at "198+ skills" / "246 skills"
- 35 Hermes mentions vs Codex 1010 / Gemini 622 / OpenClaw 572 —
under-documented relative to the marketing claim
This commit upgrades Hermes to first-class technical support while
labeling it BYO-sync in marketing (honest about the workflow:
pre-generated tree shipped, but user runs sync into ~/.hermes/ once).
**scripts/sync-hermes-skills.py changes:**
1. DOMAIN_DIRS extended with `productivity`, `marketing`, `research`
(the 3 v2.7.0 top-level domains)
2. `discover_skills()` rewritten to handle all 3 SKILL.md location
patterns (same logic as sync-codex-skills.py):
- Pattern 1: `<domain>/<skill>/SKILL.md` (flat legacy)
- Pattern 2: `<domain>/skills/<skill>/SKILL.md` (flat with skills/)
- Pattern 3: `<domain>/<plugin>/skills/<skill>/SKILL.md` (nested plugin)
Dedupes by SKILL.md path.
3. `sync_skill()` now creates RELATIVE symlinks (via os.path.relpath)
instead of absolute. Critical for committed .hermes/ tree to work
across machines. Falls back to absolute if cross-device.
**.hermes/skills/claude-skills/ tree committed:**
- 289 relative symlinks across 12 domains
- skills-index.json (303 skills documented with descriptions)
- All v2.7.0 skills present: productivity (4), marketing (1),
research (8)
**Documentation refresh:**
- docs/integrations.md:
- Header count: 246 → 311 skills
- Hermes section: NEW "Tier: BYO-sync" tip box explaining the
pre-generated tree + the one-line install step
- Install table: "198+ skills" → "303 skills (12 domains)"
- README.md:
- Hermes Agent entry in "Works with:" line now flagged with [^hermes]
footnote explicitly labeling it BYO-sync tier with link to the
sync script
Verification:
- Script smoke-test: `python3 sync-hermes-skills.py --target .hermes/skills --verbose`
→ 303 skills discovered, 289 new symlinks, 14 skipped (pre-existing)
- All v2.7.0 symlinks resolve correctly:
`.hermes/skills/claude-skills/research/research → ../../../../research/research/skills/research`
- 12 domains present in tree (was 9 before)
Per CLAUDE.md ClawHub rules: this PR does NOT update marketplace.json
(Hermes is not on ClawHub). The .hermes/ tree is repo-side
infrastructure only.
https://claude.ai/code/session_01FEUmeuYhmnxVFq7EZM8ZSw
Resolves the two follow-ups left after the v2 megaprompt sweep.
**marketplace.json (.claude-plugin/):** +12 plugin entries for the new v2
skills across 3 categories. Categories added: productivity (3), research (8).
| Plugin | Source | Category |
|---|---|---|
| capture-skill | ./productivity/capture | productivity |
| email-pair | ./productivity/email | productivity |
| reflect-skill | ./productivity/reflect | productivity |
| landing | ./marketing/landing | marketing |
| pulse | ./research/pulse | research |
| litreview | ./research/litreview | research |
| grants | ./research/grants | research |
| dossier | ./research/dossier | research |
| patent | ./research/patent | research |
| syllabus | ./research/syllabus | research |
| notebooklm | ./research/notebooklm | research |
| research-orchestrator | ./research/research | research |
Per CLAUDE.md ClawHub rules: cs- prefix not used in repo registry
(reserved for ClawHub when slug conflicts arise). 12 entries cover 13
skills (email-pair holds inbox-setup + inbox-triage).
Total plugins in marketplace: 43 → 55.
**.codex sync:** Manually created 11 missing symlinks under .codex/skills/
(capture + pulse already existed from prior auto-sync). Added 13 entries
to .codex/skills-index.json with category metadata. Total skills: 290 → 303.
**scripts/sync-codex-skills.py:** Added productivity/, marketing/, and
research/ to SKILL_DOMAINS so future automated sync runs pick up the new
top-level domains (previously only domain folders were registered).
Manual symlink creation deliberately avoids the script's full
--dry-run-flagged 16 [UPDATED] symlinks on pre-existing duplicate-path
skills (chief-ai-officer-advisor, chaos-engineering, etc., which have
both nested-plugin and flat paths in the repo). That churn belongs in
a separate cleanup PR — not in this release-prep PR.
Validation:
- marketplace.json: 55 plugins, all 7 required fields, no duplicates
- skills-index.json: 303 entries across 11 categories
- all 13 megaprompt symlinks resolve correctly
- 8-phase plugin audit on research/research: PASS WITH WARNINGS
(Phase 2 structure 84.1/GOOD, Phase 5 security PASS, scripts 3/3)
https://claude.ai/code/session_01FEUmeuYhmnxVFq7EZM8ZSw
Ran the /update-docs pipeline post-v2.6.1 release. Most of the work was
verification (docs already in sync from prior PRs #644, #649). Two real
issues surfaced and fixed:
1. Codex sync bug (the headline fix)
- scripts/sync-codex-skills.py used iterdir() which is single-level only
- Missed the engineering/<plugin>/skills/<name>/SKILL.md pattern used by
4 Pocock plugins + many other standalone plugins restructured since
PR #593
- Added Pattern 3 discovery: when <domain>/<plugin>/ contains a skills/
subdir with <name>/SKILL.md, recurse one level
- Impact: Codex index 195 → 289 skills (+94 previously-hidden skills)
- Gemini sync was already correct (uses recursive rglob)
- OpenClaw was already correct (uses recursive find)
2. Stale skill counts in 2 user-facing docs
- README.md: 268 → 272 (3 occurrences: tagline + badge + skills overview)
- docs/getting-started.md: 246 → 272 (2 occurrences: meta description + FAQ)
- All other files (CLAUDE.md, docs/index.md, mkdocs.yml site_description,
marketplace.json) were already at 272 (refreshed in PRs #644 + #649)
Other regenerations (no source changes — auto-updated from latest content):
- docs/skills/engineering/*.md regenerated (picks up v2.6.1 description fixes)
- docs/agents/*.md regenerated (no agent changes)
- docs/commands/*.md regenerated (no command changes)
- .codex/skills-index.json + 94 new symlinks (mostly Pocock + plugin-pattern
skills that should have been there since PR #593)
Verification:
- All 5 user-facing docs (CLAUDE.md, README.md, docs/index.md,
docs/getting-started.md, mkdocs.yml) show "272 skills" consistently
- marketplace.json: v2.6.1, 43 plugins, 0 broken source paths
- mkdocs build: 371 pages (280 skills + 58 agents + 33 commands), clean
in 17.31s, no errors or new warnings
- audit_skills.py: runs cleanly against 298 real skills
No production code changes outside the Codex sync fix. This is a docs +
tooling sweep, not a feature release.
https://claude.ai/code/session_01VFreMf7XLBqMgjsrG4wSYe
Adds a small stdlib-only orchestration script that runs the
skill_review_checklist_runner.py (shipped in v2.6.0) across every SKILL.md
in the repo and aggregates results.
Output:
- Total skills audited (PASS / WARN / FAIL / ERROR counts + percentages)
- Failure breakdown by rule (which of Matt's 6 checklist items fail most)
- Top-10 worst offenders (skill folder + specific failing rules)
Excludes auto-generated tool-specific symlinks (.gemini, .codex, .cursor,
.cline, /site/, /.git/) and template fixtures (templates/, assets/sample-skill).
Use case: periodic audit of skill-library hygiene. Re-run after each batch
of new skills to catch drift early. Produced the punch list that informed
the v2.6.1 cleanup planning (40% of repo skills miss "Use when" triggers;
88% exceed Matt's 100-line ceiling — both flagged for triage).
Stdlib-only. No external dependencies. Runs in ~30s on a 298-skill repo.
https://claude.ai/code/session_01VFreMf7XLBqMgjsrG4wSYe
generate-docs.py had a longstanding bug: the rendering loop only iterated
top-level skills and only rendered their direct children. Sub-skills whose
parent is a plugin folder (not a top-level skill at <domain>/skills/<name>/)
were silently dropped.
Affected plugins (standalone-only, no bundled mirror at <domain>/skills/):
- executive-mentor (1 index + 5 sub-skills)
- agenthub (1 index + 7 sub-skills)
- autoresearch-agent (1 index + 5 sub-skills)
- playwright-pro (1 index + 9 sub-skills)
- self-improving-agent (1 index + 5 sub-skills)
- c-level-agents (1 index + 17 sub-skills — the new /cs:* commands)
- llm-wiki (1 index + sub-skills)
- behuman, code-tour, demo-video, helm-chart-builder, karpathy-coder,
llm-cost-optimizer, prompt-governance, statistical-analyst, terraform-patterns,
data-quality-auditor, docker-development (single-skill plugins)
Total: 79 sub-skills + 12 plugin-index skills = 91 pages were being dropped.
(Some plugins like behuman are single-skill so only their index is dropped.)
The bug: rendering loop at line 414 only handled `for skill in top_level`,
then for each top-level found `children = [s for s in sub_skills if
s["parent"] == skill["name"]]`. Plugins where the SKILL.md lives only at
<plugin>/skills/<plugin>/SKILL.md don't appear in top_level (their detection
puts them in sub_skills with parent=themselves), so their children were
orphaned.
The fix: after the existing top-level loop, render orphan sub-skills grouped
by their plugin parent. Index sub-skill (named same as parent) renders as
<parent>.md; other children render as <parent>-<child>.md. This matches the
URL convention already in use (e.g., executive-mentor-challenge.md), so
existing SEO equity is preserved.
Result: skill pages generated 193 → 272 (+79 recovered). Total docs pages
280 → 359. mkdocs build succeeds.
Verified:
- All 12 previously-dropped plugins render their index page
- All 79 previously-dropped sub-skills render their detail pages
- URL convention preserved (executive-mentor-challenge.md, agenthub-board.md,
playwright-pro-coverage.md, etc.)
- karpathy diff_surgeon: 0 findings
After dev → main release: GitHub Pages redeploys with the recovered 79 pages.
The docs site finally has 1:1 correspondence between SKILL.md files in the
repo and pages on the site.
https://claude.ai/code/session_012WtZMm5NJHqkYoRqA9fHMN
PR #628 added 13 new cs-* agent nav entries to mkdocs.yml (cs-cfo-advisor,
cs-cmo-advisor, cs-cro-advisor, cs-cpo-advisor, cs-coo-advisor, cs-chro-advisor,
cs-ciso-advisor, cs-chief-of-staff, cs-general-counsel-advisor, cs-cdo-advisor,
cs-caio-advisor, cs-cco-advisor, cs-vpe-advisor) — but the agent pages they
pointed to didn't exist because generate-docs.py only walked /agents/, not
plugin-internal <domain>/<plugin>/agents/ folders.
Without this fix, those 13 nav links would 404 in production.
Extended generate-docs.py:
Pass 1 (existing): walk /agents/<domain>/*.md (28 canonical agents)
Pass 2 (new): walk <domain>/<plugin>/agents/*.md for each known DOMAINS root
Pass 2 dedupes against pass 1 by slug. Uses a SKILL_TO_AGENT_DOMAIN mapping
(c-level-advisor -> c-level, marketing-skill -> marketing, etc.) since skill
DOMAINS keys differ from AGENT_DOMAINS keys.
Result: 29 → 54 agent pages (+25 plugin-internal agents recovered):
c-level-advisor/c-level-agents/agents/ → 13 new cs-* agents (this session)
c-level-advisor/executive-mentor/agents/ → devils-advocate
engineering/llm-wiki/agents/ → wiki-linter, wiki-ingestor, wiki-librarian
engineering/agenthub/agents/ → hub-coordinator
engineering/autoresearch-agent/agents/ → experiment-runner
engineering-team/self-improving-agent/agents/ → memory-analyst, skill-extractor,
migration-planner, test-architect,
test-debugger
Verified:
- mkdocs build succeeds (357 → 380+ HTML pages)
- All 13 cs-* nav entries from PR #628 now resolve to valid HTML pages
- karpathy diff_surgeon: 0 findings
- Existing /agents/ canonical pass unaffected (dedupe by slug)
After dev → main release: GitHub Pages deploy will surface the recovered
25 agent pages. The 13 cs-* nav entries from the v2.5.7 release will no
longer 404.
https://claude.ai/code/session_012WtZMm5NJHqkYoRqA9fHMN
The skill directory layout changed from depth-3 (category/skill/SKILL.md)
to depth-4+ (team/skills/skill-name/SKILL.md). The find command in
convert.sh still used -mindepth 3 -maxdepth 3, causing "No skills found"
errors. Updated to -mindepth 4 -maxdepth 6 and excluded integrations/ to
avoid picking up already-converted output.
Co-authored-by: Cursor <cursoragent@cursor.com>
After PR #593 restructured umbrella plugins, every sub-skill landed at
<domain>/skills/<name>/SKILL.md. The doc generator's is_sub_skill heuristic
treated len(parts) > 2 as nested, so all 188 skills got flagged as 'children
of "skills"' (a non-existent parent) and were never written to docs/.
Recognise <domain>/skills/<name>/ as the canonical top-level layout.
Backwards-compatible with playwright-pro/skills/<sub>/ standalone-plugin
sub-skills (those legitimately have a real parent at parts[1]).
Result: 0 -> 192 skill pages emitted.
Phase 0 of the multi-skill build: ship the two stdlib-only tools that
the rest of the work depends on.
- scripts/sync_skill_bundles.py: mirror a standalone plugin's
SKILL.md + scripts/ + references/ + assets/ into its domain-bundled
location. --check exits 1 on drift; --sync rewrites the mirror.
- scripts/check_plugin_json.py: validate plugin.json against the
strict ClawHub schema (exactly the 8 allowed fields, semver version,
author{name,url}, skills as string or array — bare "./" rejected per
Claude Code v2.1.107+).
Verified: --all run reports OK on all 30 existing plugin.json files;
sync --check correctly detects missing mirrors. Karpathy-coder gate:
both files score 85/100 under strict (single nesting-depth WARN, no
FAIL) — better than the canonical karpathy-coder tools themselves.
https://claude.ai/code/session_01Dq12xJakFRxwaoU8Pqejdm
PR #593 moved every skill from <plugin>/<name>/ to <plugin>/skills/<name>/
to satisfy Claude Code's runtime loader. That broke two CI jobs that
hardcoded the old paths:
1. **9 test files** had `sys.path.insert(0, ".../<domain>/<skill>/scripts")`
pointing at the pre-restructure location. Inserted `"skills"` between
the domain and skill segments so imports resolve again.
2. **scripts/sync-codex-skills.py** scanned `<domain>/<skill>/SKILL.md`
and emitted "No skills found in repository". Updated `find_skills` to
prefer `<domain>/skills/<name>/` and fall back to `<domain>/<name>/`
so it works with both layouts (in case any domain hasn't been
restructured yet).
Verified locally:
- `python3 scripts/sync-codex-skills.py --dry-run` finds 178 skills
- `pytest tests/` collects all modules; 3216 tests pass
- 4 pre-existing failures remain (3 argparse duplicates in an
`integrations/` script, 1 strict "must have .py" check on a JS-only
skill) — out of scope for this fix.
- Convert Augment integration from flat .augment/rules/*.md to directory-based .augment/skills/<name>/SKILL.md structure
- Align Augment format with Windsurf and OpenCode skill bundle pattern
- Copy supporting folders (scripts/, references/, templates/) to each Augment skill directory
- Update frontmatter from 'type: auto' to standard 'name' + 'description' fields
- Update README documentation for new directory-based installation path
This change is possible because Augment Code now supports skills in beta, allowing us to move from the flat rules format to full skill bundles. This gives Augment users access to the complete skill ecosystem including Python automation tools and reference documentation, not just the markdown content.
Hermes Agent (github.com/NousResearch/hermes-agent) uses the agentskills.io
standard — the same SKILL.md format with YAML frontmatter that our repo uses.
Both tools expect: name, description, version, license in frontmatter, with
references/, templates/, assets/ subdirectories. No format conversion needed.
Adds scripts/sync-hermes-skills.py which symlinks (or copies) our 198 skills
into ~/.hermes/skills/claude-skills/<domain>/<skill-name>/ where Hermes
discovers them automatically via its skill_view/skills_list tools.
Usage:
python scripts/sync-hermes-skills.py --verbose # full sync
python scripts/sync-hermes-skills.py --domain engineering # one domain
python scripts/sync-hermes-skills.py --copy # copy instead of symlink
python scripts/sync-hermes-skills.py --dry-run # preview
After sync, Hermes users can invoke any of our skills via:
/skills (browse)
/<skill-name> (invoke directly)
Compatibility matrix after this change:
Claude Code — native plugin install
Codex CLI — sync-codex-skills.py
Gemini CLI — sync-gemini-skills.py
OpenClaw — openclaw-install.sh
Hermes Agent — sync-hermes-skills.py (NEW)
Cursor/Aider/etc — scripts/convert.sh
Ref #520
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
