本文へ移動
cccskills
無料GitHub で公開

fp-review

Phase 3 of the feature-pipeline suite. Run this after /fp-implement has pushed all commits and printed the M2 stop hook. Spawns a sandboxed sub-agent (HEAVIER) in an isolated worktree to run RED/GREEN tests against the PR diff and post a structured review comment. Use when you need an independent agent to verify correctness of implementation changes before CI runs — especially for schema mutations, CLI surface changes, or doc-touching commits. Triggers on: "review the PR", "run sandbox review", "fp-review", "Phase 3", "check the implementation", "validate the changes", "run tests on the PR", or any instruction to verify what /fp-implement just pushed.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.8 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。

fp-review (Phase 3 — Sandbox Review)

Spawn HEAVIER in an isolated worktree to run RED/GREEN tests, then post a structured review comment to the PR. This phase is read-and-comment only — no commits leave this phase.

The sandbox isolation matters: it prevents a flawed review from dirtying the working branch, and it forces HEAVIER to reproduce failures from a clean state rather than relying on local cache.

Setup

STATE=".agents/skills/feature-pipeline/scripts/state.sh"
branch=$($STATE get branch)
pr=$($STATE get prNumber)
phase=$($STATE get phase)

Confirm phase == 4 (set by /fp-implement on completion). If it is not 4, print a clear message explaining the pipeline order and end your turn — running out of order will produce a review against incomplete or wrong commits.

HEAVIER brief

Spawn HEAVIER with isolation: worktree on $branch. Give it exactly this brief (substitute variables):

You are reviewing PR #$pr on branch $branch. Your job is to verify each changed public surface with RED/GREEN tests, then post a review comment. Do not push any commits.

  1. Read the full diff:

    git diff origin/main...HEAD
    
  2. For each changed public surface (function, CLI flag, schema field): a. Write a RED test that FAILS before the fix. Verify this by temporarily reverting that change, running the test, then re-applying it. b. Write a GREEN test that PASSES with the fix in place.

  3. For schema-touching commits, run:

    gaia dev validate
    
  4. For doc-touching commits, run:

    gaia dev docs --check
    
  5. Post this exact comment structure to the PR via gh pr comment:

## Sandbox Review

### RED tests
| Description | Result | Notes |
|-------------|--------|-------|

### GREEN tests
| Description | Result | Notes |
|-------------|--------|-------|

### Issues found
- [ ] <description> — `<file>:<line>`

### Verdict: APPROVE / REQUEST CHANGES

After HEAVIER finishes, capture the comment URL from its output.

Phase completion

$STATE set reviewCommentUrl "<url>"
$STATE set phase 5

Print the M3 stop hook and end your turn:

╔══ STOP HOOK M3 ══════════════════════════════════════════════════════════════╗
║  Sandbox review posted — PR #<N>                                             ║
║  Review the comment, then run /fp-iterate to address findings + watch CI.   ║
╚══════════════════════════════════════════════════════════════════════════════╝

Constraints

  • If HEAVIER fails to spawn, write .fp-handover.md with the diff URL and branch name so a human can complete the review manually. End your turn — do not attempt the review yourself; the sandbox isolation is the point.
  • Do not push any commits. This phase is read + comment only.

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