Skip to content
cccskills
FreePublished on GitHub

gaia-docs-sync

Regenerate and commit Class S site-served artifacts after registry changes, then sync documentation across the main repo and the adjacent wiki. Use this skill when: you've changed registry/nodes/, registry/named/, or named-skills.json and need to regenerate docs/graph/* so the live website reflects the update; CI Guard E (docs-cohesion.yml) is failing because Class S artifacts are out of date; someone says "sync the docs", "regenerate docs", "run gaia dev docs", "update the site graph", "commit the Class S artifacts", "website is stale", or "update the wiki"; or you're finishing a registry PR and need to ensure docs/graph/gaia.json, docs/graph/gaia.gexf, docs/graph/gaia.svg, and docs/graph/named/index.json are committed alongside the source change. Also covers updating README.md, docs/index.html, and mirroring changes to the adjacent wiki repo at ../gaia-wiki.

The English summary is being prepared. Showing the original description.

Works withGitHub
See how to install

Files included (1)

  • SKILL.md6.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

gaia-docs-sync

Keep the live website (gaiaskilltree.com) and the project wiki in lockstep with the registry. GitHub Pages publishes main:/docs as-is — if Class S artifacts aren't committed, the site is dark or stale.

Background: Why two artifact classes

Class P files (registry/gaia.json, registry/named-skills.json, etc.) are gitignored pipeline internals — regenerated by gaia dev docs but never committed. Class S files (docs/graph/gaia.json, docs/graph/named/index.json, docs/graph/gaia.gexf, docs/graph/gaia.svg) ARE committed and are the exact bytes the browser fetches. Any registry change that doesn't include a Class S regen will either break the site or leave it showing old data. CI Guard E in docs-cohesion.yml enforces this pairing.


Workflow A — Registry change requires Class S regen

Run this whenever you've modified registry/nodes/, registry/named/, or any file that gaia dev docs reads to produce the site graph.

Step 1: Confirm you're on the right branch

git branch --show-current

Use a docs/*, review/meta/*, or cli/* branch depending on what drove the change. Never regenerate on main directly.

Step 2: Run regeneration

gaia dev docs

This produces both Class P (gitignored, don't touch) and Class S (tracked, must commit). Watch for warnings — gaia dev docs warnings are load-bearing; a silent failure leaves the prior Class S state on disk.

Step 3: Verify Class S files changed

git diff --stat docs/graph/

If docs/graph/ shows no diff but you changed the registry, something went wrong — investigate before proceeding.

Step 4: Stage only Class S artifacts

git add docs/graph/gaia.json docs/graph/named/index.json docs/graph/gaia.gexf docs/graph/gaia.svg

Stage only these files, not the gitignored Class P files. Accidentally staging registry/gaia.json (Class P) introduces a file that .gitignore should own and will cause confusion on the next gaia dev docs run.

Step 5: Commit alongside the source change

git add registry/nodes/ registry/named/   # or whatever source files changed
git commit -m "docs: regenerate Class S artifacts after <summary>"

Keeping the source change and its Class S output in the same commit makes the PR diff self-contained and satisfies Guard E.

Step 6: Push and open PR

git push -u origin <branch-name>
gh pr create --title "docs: <summary>" --body "$(cat <<'EOF'
## Summary
- <what changed in the registry>
- Regenerated Class S artifacts via `gaia dev docs`

## Test plan
- [ ] CI Guard E (docs-cohesion.yml) passes
- [ ] `docs/graph/gaia.json` diff looks reasonable (node count change expected)
EOF
)"

Workflow B — Human-authored docs and wiki sync

Run this when editing README.md, docs/index.html, or any page that should also appear on the wiki.

Step 1: Update main repo documentation

Edit the target files in the main repo (e.g., README.md, docs/index.html).

The pre-commit hook may regenerate docs automatically — let it succeed rather than bypassing it.

git add <files>
git commit -m "docs: <summary of changes>"
git push -u origin <branch-name>
gh pr create --title "docs: <summary>" --body "<detailed description>"

Step 2: Pull or clone the wiki

The wiki lives in a separate git repository. Keep it adjacent to the main repo so paths stay consistent.

# First time:
git clone https://github.com/gaia-research/gaia-skill-tree.wiki.git ../gaia-wiki

# Already cloned:
cd ../gaia-wiki && git pull origin master

Step 3: Mirror the changes to wiki pages

Identify which wiki pages correspond to the main-repo changes:

Main repo fileWiki equivalent
README.md (CLI reference)CLI-Reference.md
docs/index.html (getting started)Getting-Started.md
CONTEXT.md (nomenclature)Home.md

Apply the same technical content. The wiki and main repo must describe identical capabilities — divergence causes user confusion and fails the accuracy constraint.

Step 4: Commit and push wiki directly to master

The wiki has no PR flow — push straight to master.

cd ../gaia-wiki
git add <updated-files>.md
git commit -m "docs: <summary of changes>"
git push origin master

Constraints

Do not stamp versions on Class S files. docs/graph/gaia.json, docs/tree.md, and docs/index.html must not carry a version field or banner. The lockstep verifier checks only pyproject.toml, packages/*/package.json — a version stamp on a rendered artifact will break unrelated PRs when they inherit a stale stamp (Issue #807 retro).

Do not manually patch ?v= cache-bust strings. Add new HTML pages to build_html_cache_busting() in scripts/build_docs.py instead — the function auto-applies versioned query strings to all .css and .js references on every gaia dev docs run.

Keep the wiki adjacent at ../gaia-wiki. The clone path is assumed by this workflow and by any scripts that cross-reference both repos.

Auto-sync never touches docs/badges/. The CI auto-sync workflow explicitly skips badge regeneration to prevent stale-snapshot wipes. Badge updates require a human-run infra/badge-* PR.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Measure CI churn cost for a pull request: how many commits and how many CI-compute seconds were burned on avoidable "fix the CI" push rounds. Use when you want to understand the efficiency cost of a PR's iteration cycle, get actionable pre-push check suggestions, or include a churn summary in a pipeline report. Triggers: "ci churn", "how much CI did we burn", "avoidable commits", "ci efficiency", "wasted CI time", "churn report", "/ci-churn". Called automatically by /fp-drift at pipeline close.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 22, 2026

Produce the rendered evidence a human-gated frontend PR owes its reviewer: capture each changed surface (plus the before state for anything modified, plus mobile width), then generate one self-contained local HTML page the founder can open and review without checking anything out. Use when a PR is gated by the "Frontend changes are HUMAN-GATED" section of CLAUDE.md, or when the user says "/design-gate", "screenshot evidence for this PR", "prep this for founder review", "build the design evidence page", "what does this look like before and after". The page comes from a template script, not hand-written markup. Output is session-local and never committed. Do NOT use for non-gated changes: typo/grammar/factual fixes in an unchanged block, dead link targets, alt/ARIA fixes with no visual change, cache-bust bumps, or refactors with no rendered diff.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 22, 2026

One-fix-at-a-time, approval-gated design fix recovery. Given a checklist of fixes (handover doc, CHECKLIST.md, or inline list), applies each individually, presents a diff, and waits for an explicit APPROVE / REJECT / NO CHANGES decision before committing. Trigger phrases: /design-iteration, "go through the checklist one by one", "fix these one at a time", "bucket recovery", "design fix pass".

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 22, 2026

Playbook for correcting a named skill's star level to match its computed Trust Magnitude grade, with an independent post-calibration verification pass and a CLI-logged timeline event (never hand-written). Use when: recalibrating a skill's level, fixing a stale or drifted star rating, running a batch of `gaia dev calibrate` corrections, or confirming a past calibration actually landed. Triggers: "calibrate <skill>", "recalibrate the trust magnitude backlog", "promote/demote <skill> to N stars", "why is <skill> still N stars", "verify a calibration actually landed", "Hall of Heroes ranking is wrong".

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 22, 2026

Close out a completed EPIC / sprint end-to-end: author a fact-verified meta-post announcing what shipped, archive the EPIC's handovers, snapshot orchestrator memory, gate the integration→main merge on CI-green + explicit human go, drive the version bump (merge-commit conventions that auto-sync classifies), and verify the release reached the registry/PyPI. Use when the user says "close out EPIC <n>", "wrap up the sprint", "ship the meta shift", "/epic-close", or asks to finalize an integration branch that is ready to merge to main. Generalizes the EPIC 1002 (Yggdrasil II) close-out. This skill orchestrates — it authors founder docs directly (superadmin) and delegates code/regen to workers; it NEVER merges to main without the human gate.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 22, 2026

Run this skill for Phase 3 of the evidence verification pipeline — the adversarial audit step. Use when you need to check the evidence data lake for bad data before ingestion: dead links, wrong URL formats (tree/ vs blob/), subjective wording ("elite", "high-quality"), stale migration notes, benchmark catalog misuse/vendor-claim leakage, or skills whose star evidence conflicts with classified evidence level. Triggers on phrases like: "audit the data lake", "adversarial check", "ev-adversarial-audit", "check for noise in evidence", "flag bad evidence", "run the audit phase", "quality check the by-type files", or any reference to Phase 3 of the pipeline.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 22, 2026

See all skills by gaia-research

Report a problem with this skill