mcpbeat Sign in

Stage Review Skill for Codex

Stage a finished local feature, run local verification, create a Conventional Commit, then send it through the no-mistakes gated review/fix loop before real upstream push/PR. Use when the user says a feature is done, asks for a professional stage-review flow, wants Codex to git add and commit safely, or wants no-mistakes review/verify/fix before pushing to origin.

3k tokens
context cost
the whole folder, loaded on every use
4
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
131
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/instructa/agent-skills --skill stage-review

What comes with it

8 121 bytes besides the instruction
README.md
agents/openai.yaml
scripts/stage_review.py

The instruction itself

10 sections, as written by the author

Stage Review

Overview

Use this as the finished-feature workflow: inspect changes, verify locally, stage explicit files, create a Conventional Commit, push through no-mistakes, attach to the run, fix findings, rerun, and let no-mistakes perform the real upstream push/PR only after the gate passes.

Core Rules

  • Never use git push origin in this workflow.
  • Never force-push.
  • Do not stage with git add .; use explicit paths or the bundled script's --all only after the user explicitly wants all current changes included.
  • Stop before committing on protected or detached branches.
  • Ask before any remote-affecting command, including git push no-mistakes.
  • Use Conventional Commits: feat|fix|refactor|build|ci|chore|docs|style|perf|test.
  • Prefer repo-local check commands from .no-mistakes.yaml, justfile, package.json, Makefile, go.mod, Cargo.toml, or equivalent project config.
  • Quote exact local check and pipeline errors before diagnosing.

Workflow

1. Preflight

Resolve scripts/stage_review.py relative to this skill folder, then run:

python3 <skill-dir>/scripts/stage_review.py --cwd . plan
python <skill-dir>/scripts/stage_review.py --cwd . plan

Also run:

git status --short --branch
git diff --stat

Stop and ask if:

  • branch is protected or detached
  • merge/rebase/cherry-pick is in progress
  • changed files include unrelated work
  • no origin exists
  • no no-mistakes remote exists and no-mistakes init has not been approved

2. Local Checks

Run the repo's real local checks before staging. Prefer explicit commands from .no-mistakes.yaml:

commands:
  test: "..."
  lint: "..."
  format: "..."

If no config exists, inspect repo-local command surfaces and choose the canonical one. Examples:

  • just test, just lint, just fmt
  • make test, make lint, make fmt
  • pnpm test, pnpm lint, pnpm typecheck
  • go test ./..., go vet ./...
  • cargo test, cargo clippy --all-targets -- -D warnings

Do not commit if relevant local checks fail unless the user explicitly wants a broken checkpoint.

3. Stage And Commit

Pick the Conventional Commit subject from the actual diff:

feat(scope): concise summary
fix(scope): concise summary
refactor(scope): concise summary

Stage explicit files:

python3 <skill-dir>/scripts/stage_review.py --cwd . commit \
  -m "feat(scope): concise summary" \
  --body "Tests: <commands run>" \
  path/to/file1 path/to/file2

Use all changed files only when the user explicitly confirms all changes belong in the feature:

python3 <skill-dir>/scripts/stage_review.py --cwd . commit \
  -m "feat(scope): concise summary" \
  --body "Tests: <commands run>" \
  --all

4. Push Through no-mistakes

Confirm the exact command first:

Ready to push <branch> through no-mistakes:
git push no-mistakes <branch>

After confirmation:

git push no-mistakes <branch>
no-mistakes

5. Review/Verify/Fix Loop

For each no-mistakes finding:

  • identify the step: rebase, review, test, document, lint, push, pr, or ci
  • quote the exact finding/error
  • fix code/config only when the user wants you to fix it
  • run targeted local verification after fixing
  • commit follow-up fixes with the same script
  • run no-mistakes rerun or continue/attach as appropriate

Useful commands:

no-mistakes status
no-mistakes runs --limit 10
no-mistakes attach
no-mistakes rerun

6. Done Criteria

Finish only when you can report:

  • local checks run and result
  • commit SHA and Conventional Commit subject
  • no-mistakes run state
  • PR URL if created/updated
  • CI state if available
  • remaining blockers, if any

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take instructa/stage-review from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.