agentleFS
Jagoda11Jagoda11/the-jagoda-toolkit/skills/review/SKILL.md

review

Skill0 starsChanged 6 months agoMITView on GitHub

Smart router that detects branch changes and recommends which audit skill(s) to run. Use this when starting a review or when unsure which audit to run.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use three-dot diff (BASE...HEAD) to scope to this branch only.

    line 28
  2. Distinctive:

    If multiple categories are detected, combine the recommended audits.

    line 63
  3. Very specific:

    Use git commands only — do NOT use gh CLI or GitHub API.

    line 89
  4. Distinctive:

    Do not perform the audit yourself — only recommend.

    line 91
  5. Distinctive:

    If the change set is trivial (typo fix, comment update), say so explicitly.

    line 92
  6. Distinctive:

    If the change set is ambiguous, list what additional context would help.

    line 93
  7. Distinctive:

    If insufficient information to classify, state: "Insufficient information to conclude" instead of guessing.

    line 94

“Common” is measured: kept by at least 6 in 10 of the 157 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review — Smart Router

Purpose

Detect what changed and recommend which audit skill(s) to run. This skill does NOT perform the audit itself — it routes to the right one(s).

Instructions

Step 1 — Detect Changes

Detect the base branch (auto: develop for GitFlow, main/master for trunk-based, release if used as integration branch):

BASE=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@')
[ -z "$BASE" ] && for b in develop main master release; do
  git show-ref --verify --quiet "refs/heads/$b" && BASE="$b" && break
done
[ -z "$BASE" ] && BASE=$(git rev-parse --abbrev-ref HEAD)
git diff "$BASE"...HEAD --name-only

Use three-dot diff (BASE...HEAD) to scope to this branch only. Avoid git log BASE..HEAD for file detection.

Classify every changed file into one or more categories:

CategorySignals
Auth**/auth*/**, **/authn*/**, **/oauth*/**, **/oidc*/**, **/saml*/**, **/session*/**, JWT/token issuance, auth middleware
Database**/migrations/**, **/*.sql, **/schema*.{ts,prisma}, **/*.queries.ts, ORM model dirs, DB client config, DDL
Shared Packagepackages/** (excluding apps/**), shared util/contract/UI/i18n packages, anything imported by ≥2 workspaces
CI/CDChanges in .github/workflows/**, .gitlab-ci.yml, .circleci/config.yml, .azure-pipelines.yml, cloudbuild.yaml, buildspec.yml, .deploy/, skaffold.yaml, Dockerfile*, Kustomize overlays, Helm Chart.yaml, docker-compose*.yml
TestChanges in tests/**, __tests__/**, **/*.{test,spec}.{ts,tsx,jsx}, vitest.config.ts, playwright.config.*, test utilities, fixtures, coverage config
FrontendChanges in apps/web/**, apps/frontend/**, apps/client/**, packages/ui*/**, **/*.{tsx,jsx}, React components, hooks, routes
BackendChanges in apps/api/**, apps/server/**, apps/backend/**, services/**, route handlers, controllers, service-layer files, domain modules
ContractsChanges in **/contracts/**, **/schemas/**, **/*.openapi.{yaml,json}, zod/typebox schema files, route definition files
ConfigChanges in **/eslint.config.*, **/tsconfig*.json, package.json, build tool config (vite.config.*, tsup.config.*), shared config packages
DocsChanges in *.md, docs/

Step 2 — Route to Audits

Based on detected categories, recommend skill(s):

TriggerRun
Auth changes detected/review-auth
DB schema or query changes/review-test-strategy + /audit
Shared package changes/review-monorepo
CI/CD pipeline changes/review-cicd
New feature (backend + contracts + frontend)/audit + /review-design
Schema or contract changes/review-design
Refactor (structure changes, no new features)/review-ai-compat + /review-test-strategy + /review-design
Test-only changes/review-test-strategy
PR ready for merge/review-pr
Config or lint rule changes/review-ai-compat
Docs-only changesNo audit needed — verify links and accuracy only

If multiple categories are detected, combine the recommended audits. Deduplicate — never recommend the same skill twice.

Step 3 — Output

Produce a structured recommendation:

## Review Router — Recommendation

### Changes Detected
- [ category ]: [ list of changed files ]

### Recommended Audits
1. `/skill-name` — reason
2. `/skill-name` — reason

### Priority
[ Which audit to run first and why ]

### Scope Note
[ Any context about the size or risk level of the changes ]

Constraints

  • Use git commands only — do NOT use gh CLI or GitHub API. No PR lookups needed.
  • This skill works on branches, not pull requests.
  • Do not perform the audit yourself — only recommend.
  • If the change set is trivial (typo fix, comment update), say so explicitly.
  • If the change set is ambiguous, list what additional context would help.
  • If insufficient information to classify, state: "Insufficient information to conclude" instead of guessing.
  • Separate facts from assumptions.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.