本文へ移動
cccskills
無料GitHub で公開

gaia-curation-review

Review a Gaia curation PR or branch as a read-only merge gate. Use for canonical registry promotion, schema, evidence, prerequisite, nomenclature, installability, and generated-artifact checks. Route intake batches to /gaia-draft-curate and unrelated PRs to /review.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.9 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

gaia-curation-review

Assess what a curation PR actually changes and return a structured recommendation. This skill is a read-only gate: it does not rebase, push, merge, force-push, or modify the PR.

Scope routing

Classify before reviewing:

  • Intake-only PR or registry-for-review/ batch → route to /gaia-draft-curate.
  • Canonical registry promotion/curation PR → continue below.
  • Unrelated code or documentation PR → route to /review.

Workflow

1. Resolve PR and branch

For a PR number:

gh pr view <number> --json number,title,state,isDraft,headRefName,baseRefName,url,body,labels

For a branch, identify its base and remote. Fetch without changing the current branch:

git fetch origin <branch> <base>

Use a disposable worktree for checks so generated or ignored output cannot pollute the maintainer's working tree:

git worktree add --detach /tmp/gaia-review-<id> origin/<branch>

2. Establish the substantive diff

Run:

gaia dev diff origin/<branch>
git diff --check origin/<base>...origin/<branch>

gaia dev diff is the semantic summary, but it is not the only authority. Inspect source changes under:

  • registry/nodes/;
  • registry/named/;
  • registry/suites/, when present;
  • registry-for-review/, for routing only;
  • docs/graph/, to confirm Class S regeneration when required.

Do not treat generated Class P files as the source of truth.

3. Compare claims with reality

Cross-check the PR title/body against the semantic diff. Flag every mismatch, including claimed skills absent from the diff, incorrect taxonomy/type language, unexpected removals, and claims that generated artifacts were updated when they were not.

4. Review canonical changes

For generic nodes:

  • prerequisites exist and form a valid DAG;
  • type and nomenclature match the current schema and CONTEXT.md;
  • evidence is present with valid provenance;
  • duplicate or overlapping generic mappings are explained;
  • no existing generic or edge is removed without explicit justification.

For named skills:

  • genericSkillRef resolves;
  • contributor path and source identity agree;
  • status/title or catalogRef requirements are satisfied;
  • level/star changes are evidence-backed and timeline implications are understood;
  • installable non-suite skills use a specific links.github blob/ URL, or explicitly declare non-installability;
  • suite components and suite links point to their actual subpaths;
  • terminology follows CONTEXT.md and does not introduce deprecated vocabulary.

For evidence:

  • record evidence type, grade, source URL, and required numeric/provenance fields;
  • distinguish evidence requiring live verification from evidence already validated;
  • flag dead, bare-repository, tree/, duplicated, subjective, or unsupported evidence;
  • do not use legacy Class A/B/C rules as the sole merge gate when the current evidence model provides more specific fields.

5. Check repository and generated-artifact scope

Confirm branch scope is allowed by the branch prefix and project rules. When canonical registry sources change, verify the PR includes required Class S artifacts under docs/graph/ or clearly explains why regeneration is deferred.

Check:

gaia dev validate
gaia dev docs --check
gaia dev test all

If named star levels or timelines changed, also run:

python3 scripts/validate_timelines.py

Record commands that could not run and why. Do not assume a successful command that was not executed.

6. Report severity and recommendation

Separate:

  • Blocking failures — cannot merge safely;
  • Warnings — follow-up recommended but not necessarily blocking;
  • Evidence pending verification — requires live/source review;
  • Checks run — exact commands and outcomes.

Use exactly one recommendation:

  • MERGE SAFE — substantive checks pass; normal rebase/merge is a maintainer action;
  • NEEDS REVIEW — list concrete blockers or unresolved questions;
  • CLOSE — empty, already merged, or no substantive change;
  • ROUTE — wrong workflow, with the destination skill.

Report format

## PR <number>: <title>

Branch: <head> → <base>
Status: <state>

### Scope classification
<canonical / intake / unrelated>

### What this changes
<generic nodes, named skills, edges, removals, generated artifacts>

### Claim vs diff
<mismatches or none>

### Blocking failures
<items or none>

### Warnings
<items or none>

### Evidence pending verification
<items or none>

### Checks run
<commands and outcomes>

### Recommendation
MERGE SAFE | NEEDS REVIEW | CLOSE | ROUTE

Never merge or alter the branch as part of this skill.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

ci-churn

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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".

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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".

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

gaia-research のスキルをすべて見る

このスキルの問題を報告する