New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Develop Review Gate

by penwyp in penwyp/ClaudePreference

适用于这类请求：直接在当前 checkout 完成开发、固定做两轮自我 review/refactor、先把最终 review 结果给人类确认、确认后再继续改动、提交或进入下一步。用户可能会说："先开发再自审两轮"、"先 review 两次再给我确认"、"不要开 worktree，直接改"、"先输出 review 结论不要继续"、"做完先停在 gate"。

MITAuto-check passedAgent Workflows

Install Develop Review Gate

skills CLI
$ npx skills add penwyp/ClaudePreference --skill develop-review-gate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install penwyp/ClaudePreference develop-review-gate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/penwyp/ClaudePreference.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/develop-review-gate .claude/skills/develop-review-gate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
develop-review-gate
GitHub stars
136
Token cost
~846 tokens
SKILL.md length
456 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

适用于这类请求：直接在当前 checkout 完成开发、固定做两轮自我 review/refactor、先把最终 review 结果给人类确认、确认后再继续改动、提交或进入下一步。用户可能会说："先开发再自审两轮"、"先 review 两次再给我确认"、"不要开 worktree，直接改"、"先输出 review 结论不要继续"、"做完先停在 gate"。

  • Tasks that involve Human-in-the-loop approvals
  • SKILL.md covers Workflow, Review Output, After Confirmation and Guardrails
  • Calls git
  • Tasks that involve Git worktrees

What it does

Develop Review Gate is an agent skill from penwyp/ClaudePreference. 适用于这类请求：直接在当前 checkout 完成开发、固定做两轮自我 review/refactor、先把最终 review 结果给人类确认、确认后再继续改动、提交或进入下一步。用户可能会说："先开发再自审两轮"、"先 review 两次再给我确认"、"不要开 worktree，直接改"、"先输出 review 结论不要继续"、"做完先停在 gate"。

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Human-in-the-loop approvals and Git worktrees. The repository describes itself as: A comprehensive collection of development workflow commands for Claude Code. The licence is MIT.

When your agent uses it

  • Tasks that involve Human-in-the-loop approvals
  • Tasks that involve Git worktrees

Example prompts

  • “先开发再自审两轮”
  • “先 review 两次再给我确认”
  • “不要开 worktree，直接改”
  • “/develop-review-gate”

What it can do on your machine

Read from SKILL.md and the folder at commit a5eea54. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Develop Review Gate loads about 846 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 456 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~846

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from penwyp/ClaudePreference at commit a5eea54, republished under its MIT licence (© penwyp). 456 words, ~846 tokens.

Download SKILL.mdSave it as .claude/skills/develop-review-gate/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
develop-review-gate
description
适用于这类请求：直接在当前 checkout 完成开发、固定做两轮自我 review/refactor、先把最终 review 结果给人类确认、确认后再继续改动、提交或进入下一步。用户可能会说："先开发再自审两轮"、"先 review 两次再给我确认"、"不要开 worktree，直接改"、"先输出 review 结论不要继续"、"做完先停在 gate"。

Develop Review Gate

Workflow

  1. Confirm scope and current workspace state.
  • Work in the current checkout instead of creating a worktree.
  • Inspect the repository and any existing local changes before editing.
  • If the worktree is already dirty, preserve unrelated user changes and limit edits to the task scope.
  1. Implement the requested change in the current checkout.
  • Explore the relevant code before editing.
  • Finish the feasible scope instead of stopping at a partial patch.
  • Keep architecture consistent with the project; do not use temporary patch-style fixes unless the change is truly a local no-risk micro-fix.
  1. Run self-review pass 1.
  • Inspect the diff as a reviewer instead of as the original author.
  • Look for correctness bugs, regressions, missing tests, naming issues, leaky abstractions, and unnecessary complexity.
  • Apply the fixes that are clearly actionable.
  • Run the most relevant tests, lint, or build checks for the changed area.
  1. Run self-review pass 2.
  • Re-inspect the updated diff with the same reviewer mindset.
  • Focus on issues left after the first pass: edge cases, maintainability, API consistency, error handling, and test quality.
  • Apply the second-pass fixes that materially improve the result.
  • Re-run the most relevant verification after the refactor.
  1. Produce the approval gate output and pause.
  • Report the final review findings first. If no blocking findings remain, say that explicitly.
  • Summarize what changed, what was refactored during both self-review passes, what verification ran, and what did not run.
  • Include the current branch, touched files, and working tree status when relevant.
  • Call out residual risks or open questions.
  • End in a waiting state such as: Awaiting human confirmation: continue coding, request more changes, commit, or proceed with the next step.
  • Do not continue into extra scope, commit, or destructive cleanup unless the human explicitly confirms.
Show full SKILL.md (165 more words)Show less

Review Output

Use concise sections in this order:

  • Self-review findings
  • Change summary
  • Refactors applied
  • Verification
  • Residual risks
  • Awaiting confirmation

Include file references when calling out findings or material changes.

After Confirmation

Continue Coding
  • Keep using the same checkout.
  • Repeat the implement -> review pass 1 -> review pass 2 -> approval gate cycle.
  • Preserve any unrelated user changes already present in the worktree.
Commit Or Next Step
  • Re-check git status before committing or taking the requested next step.
  • Commit only when the human explicitly asks for it.
  • If verification is stale after follow-up edits, run the most relevant checks again before committing or proceeding.

Guardrails

  • Always run two self-review passes for this workflow unless the human explicitly asks to shorten it.
  • Never hide failed verification. Report the failure and stop for direction.
  • Never overwrite or revert unrelated user changes in the current checkout.
  • Never claim the branch is ready without describing what was verified and what was not.
  • Never continue past the approval gate without explicit human confirmation.

© penwyp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/develop-review-gate of penwyp/ClaudePreference.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit a5eea54

Compare with similar skills

Develop Review Gate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Develop Review Gate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Develop Review Gate this skillpenwyp/ClaudePreference136—~846Automated safety check: PassMIT
Orca CLIstablyai/orca87k2 repos~593Automated safety check: PassMIT
Using Git Worktreesjulianromli/opencode-template14428 repos~1.4kAutomated safety check: PassNone
Nagentdavidondrej/skills4.1k—~1.7kAutomated safety check: NotesMIT
Using Git Worktreesfarm-fe/farm5.6k13 repos~2kAutomated safety check: PassMIT
Agent of Empires Session Manageragent-of-empires/agent-of-empires3.3k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Orca CLI

    stablyai/orca

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

    87k GitHub starsUsed in 2 repos~593 tokens
    Agent WorkflowsAuto-check passed

  • Using Git Worktrees

    julianromli/opencode-template

    A skill your agent uses when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory…

    144 GitHub starsUsed in 28 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Nagent

    davidondrej/skills

    Launch a new bb worker thread with the right project, model, worktree, and task brief.

    4.1k GitHub stars~1.7k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Using Git Worktrees

    farm-fe/farm

    A skill your agent uses when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git…

    5.6k GitHub starsUsed in 13 repos~2k tokens
    Agent WorkflowsAuto-check passed

  • Agent of Empires Session Manager

    agent-of-empires/agent-of-empires

    Starts, monitors and organizes coding agent sessions that run in tmux through the aoe command, including groups, profiles and worktree-based parallel work.

    3.3k GitHub stars~2.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Agent Manager Fleet TUI

    YoanWai/agent-manager

    Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.

    576 GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from penwyp/ClaudePreference

  • Local Project Runtime

    penwyp/ClaudePreference

    Diagnose and stabilize local project setup after clone or checkout.

    136 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check: notes

  • Image Converter

    penwyp/ClaudePreference

    Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil.

    136 GitHub stars~955 tokensUpdated 4 mo ago
    Auto-check passed

  • Explain

    penwyp/ClaudePreference

    Analyze a code snippet, file path, symbol name, or the current conversation context against the local repository and explain what it does in the project.

    136 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed

  • Refactor Design Report

    penwyp/ClaudePreference

    Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract…

    136 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed

  • Doc Code Review Report

    penwyp/ClaudePreference

    Review text input or documents against the local codebase and produce a structured review report with findings and refactor suggestions.

    136 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed

  • Browser Flow Fallbacks

    penwyp/ClaudePreference

    Diagnose flaky browser automation flows (login, OAuth, signup, multi-step forms).

    136 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Develop Review Gate

What does Develop Review Gate do?

适用于这类请求：直接在当前 checkout 完成开发、固定做两轮自我 review/refactor、先把最终 review 结果给人类确认、确认后再继续改动、提交或进入下一步。用户可能会说："先开发再自审两轮"、"先 review 两次再给我确认"、"不要开 worktree，直接改"、"先输出 review 结论不要继续"、"做完先停在 gate"。. Develop Review Gate is an agent skill from penwyp/ClaudePreference.

When should I use Develop Review Gate?

Develop Review Gate fits situations like: tasks that involve Human-in-the-loop approvals; tasks that involve Git worktrees.

How do I install Develop Review Gate in Claude Code?

Run `npx skills add penwyp/ClaudePreference --skill develop-review-gate -a claude-code`. Or copy the skill folder (skills/develop-review-gate in penwyp/ClaudePreference) into .claude/skills/develop-review-gate in your project. Claude Code loads it when a task matches its description.

How do I install Develop Review Gate in Codex?

Run `npx skills add penwyp/ClaudePreference --skill develop-review-gate -a codex`. Or copy the skill folder (skills/develop-review-gate in penwyp/ClaudePreference) into .agents/skills/develop-review-gate in your project. Codex loads it when a task matches its description.

Can I use Develop Review Gate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add penwyp/ClaudePreference --skill develop-review-gate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/develop-review-gate, .gemini/skills/develop-review-gate, .github/skills/develop-review-gate and .opencode/skills/develop-review-gate in your project.

What does Develop Review Gate need to run?

Going by SKILL.md and its folder, Develop Review Gate needs the command-line tools its instructions call (git).

Does Develop Review Gate access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Develop Review Gate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Develop Review Gate use?

Develop Review Gate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Develop Review Gate use?

About 846 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Develop Review Gate?

Skills that share tags, products or a category with Develop Review Gate: Orca CLI (stablyai/orca, 87k stars), Using Git Worktrees (julianromli/opencode-template, 144 stars), Nagent (davidondrej/skills, 4.1k stars) and Using Git Worktrees (farm-fe/farm, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Develop Review Gate?

penwyp (a GitHub user) maintains it in penwyp/ClaudePreference, which has 136 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on May 27, 2026.

Source: penwyp/ClaudePreference on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.