- root CLAUDE.md: Navigation Map row, Repository Structure tree line, and an
'Unreleased (post-v2.11.2, PR #961 merged)' narrative for the agent-launcher
domain (grep previously returned zero mentions)
- CHANGELOG: the verification sentence no longer points at
agent-launcher/DELIVERY-REPORT.md — per the maintainer finish-plan
(audit/pr-stream-2026-08) that report moved to gitignored documentation/;
SPEC.md remains the public build target
- sync scripts: v2.12 comment/description strings -> 'unreleased, post-v2.11.2'
to match the normalized plugin version; codex index regenerated
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012FwXG6TqCXKZQvF4iD69cv
Adds agent-launcher to the four sync scripts' domain lists and re-runs them:
.codex + .gemini indexes now carry the 6 skills; .vibe + .hermes repo trees
regenerated (also catches up skills merged since the last sync). The pre-existing
.codex/skills/run symlink collision (autoresearch-agent vs agenthub, both named
'run') is left at its previous target.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012FwXG6TqCXKZQvF4iD69cv
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
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
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>
