Agent skill

Comet Review

by rpamis in rpamis/comet

手动审查当前 Comet change 的实现差异,只报告正确性、安全和边界问题,不推进工作流. An agent skill from rpamis/comet.

MITAuto-check passedDevelopment

Install Comet Review

skills CLI
$ npx skills add rpamis/comet --skill comet-review -a claude-code

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

GitHub CLI
$ gh skill install rpamis/comet comet-review --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/rpamis/comet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assets/skills-zh/comet-review .claude/skills/comet-review && 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
comet-review
GitHub stars
3.2k
Token cost
~892 tokens
SKILL.md length
211 words
Files
2
Skills in repo
52
Repo updated
First seen
Licence
MIT

At a glance

手动审查当前 Comet change 的实现差异,只报告正确性、安全和边界问题,不推进工作流. An agent skill from rpamis/comet.

  • Works in 5 steps: 定位项目与当前 change → 收集审查上下文 → 确定实现差异 → …
  • Development work in your project
  • SKILL.md covers 只执行读取和审查操作, 1. 定位项目与当前 change, 2. 收集审查上下文 and 3. 确定实现差异, plus 2 more sections
  • Calls git

What it does

Comet Review is an agent skill from rpamis/comet. 手动审查当前 Comet change 的实现差异,只报告正确性、安全和边界问题,不推进工作流。

Its SKILL.md is about 890 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 Development. It works with Git. The repository describes itself as: Comet: agent skill harness for turning ideas into evaluated workflows. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/comet-review”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 定位项目与当前 change
  2. 收集审查上下文
  3. 确定实现差异
  4. 执行审查
  5. 输出

What it can do on your machine

Read from SKILL.md and the folder at commit c28e724. 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

Comet Review loads about 892 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 211 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~892

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 rpamis/comet at commit c28e724, republished under its MIT licence (© rpamis). 211 words, ~892 tokens.

Download SKILL.mdSave it as .claude/skills/comet-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
comet-review
description
手动审查当前 Comet change 的实现差异,只报告正确性、安全和边界问题,不推进工作流。
disable-model-invocation
true

Comet 手动代码审查

对当前选中的 Comet change 执行一次按需、只读的代码审查。这个入口不属于任何阶段,也不替代 Build 或 Verify 的验证和审查。

本入口独立于 review_mode。review_mode 控制流程内的自动审查策略,/comet-review 则由用户手动触发,只执行一次审查;调用本入口不得读取、修改或覆盖当前 change 的 review_mode。

只执行读取和审查操作

本 Skill 的整个调用必须保持只读:

  • 不修改、创建或删除文件;
  • 不暂存、提交、切换分支、创建分支或创建 worktree;
  • 不运行 comet state select、comet native select、comet state set、comet state transition、阶段守卫、comet native next 或归档命令;
  • 不修复发现的问题,不推进 phase,不更新 tasks、状态、验证报告或审查记录;
  • 不把本次结果称为 Verify 通过,也不把“没有发现”视为测试已经通过。

只允许执行读取文件、查询状态和查看 Git 差异所需的命令。任何可能运行项目代码、安装依赖或产生文件的检查都不属于本入口。

1. 定位项目与当前 change

  1. 使用只读 Git 查询确定项目根目录;如果不是 Git 仓库,则使用当前 Comet 项目根目录。

  2. 在项目根目录运行:

    bash
    comet status . --json
  3. 读取 .comet/current-change.json,并按以下顺序确定审查对象:

    • 文件包含有效的 comet.selection.v2 时,使用其中的 workflow 和 change;
    • 没有 selection 记录,且状态输出中只有一个未归档的 Comet change 时,只在本次审查中使用该 change,不写入 selection;
    • 没有 selection 记录且存在多个 change 时,列出名称、workflow 和 phase,请用户指定一个,然后停止当前调用;
    • selection 指向缺失、已归档或状态无效的 change 时,报告当前选择已过期或无效(stale/invalid selection),然后停止,不自行修复。

忽略不受 Comet 管理的普通 OpenSpec change。不得因为默认 workflow 与 selection 不同而改用默认 workflow。

2. 收集审查上下文

只读取当前 change 的必要上下文,并为每个事实保留来源路径或命令。

Classic
  1. 先读取并遵守 comet-classic/reference/classic-layout.md,解析当前项目的 Classic 逻辑根。

  2. 读取当前 change 的 proposal.md、design.md、tasks.md 和 specs/*/spec.md;存在关联 Design Doc 时一并读取。

  3. 使用以下只读状态查询获得 phase、基线和已有证据引用:

    bash
    comet state get <change-name> phase
    comet state get <change-name> base_ref
    comet state get <change-name> plan
    comet state get <change-name> verification_report
  4. 读取已有的 plan、验证报告,以及 comet status . --json 返回的 build/verify 命令检查结果。缺失的证据应标为“未提供”,不能推断为失败或通过。

Native

运行以下只读命令:

bash
comet native show <change-name> --json
comet native status <change-name> --details --json

根据返回的引用,读取 brief、完整的拟议规格(proposed Specs)、acceptance、Builder handoff、checks、verification、risks、blockers 和验证报告(verification report)。只使用当前 candidate/iteration 的证据;历史轮次只用于解释尚未消除的风险,不能据此覆盖当前状态。

3. 确定实现差异

  1. 先运行 git status --short --untracked-files=all,列出工作区中全部已暂存、未暂存和未跟踪的文件。
  2. 结合当前 change 的需求、工作区绑定、Git 历史和工作树状态,确定最可信且与当前 change 相关的审查范围。对于 Classic,优先使用有效的 plan base-ref;不存在或无效时回退到状态中的 base_ref,不要求两者一致。只有两者均无效时,才将 Classic 基线视为缺失。对于 Native,将状态中的工作区关系和当前 candidate 的实现范围证据作为判断依据。
  3. 查看从可信基线到当前工作树的完整差异,包括已提交、已暂存和未暂存修改。对属于当前 change 的所有未跟踪文件,包括源码、测试、文档、配置和元数据(例如 SKILL.md 与 agents/openai.yaml),直接读取内容并明确标注其未跟踪状态。
  4. 排除明确归属于其他 change 或用户无关工作的差异。只有歧义会实质影响审查结论时才询问用户;否则基于现有证据继续审查,并在结果中说明范围判断和假设。

如果结合上述证据仍无法确定可信且可验证的基线,继续审查当前可见的工作树差异,并在结果中显著标注“审查范围不完整”。

4. 执行审查

根据需求、任务和当前差异进行一次聚焦审查,只检查:

  • 实现正确性和明显逻辑错误;
  • 安全风险、权限或路径边界问题;
  • 错误处理、兼容性和重要边界条件;
  • 任务遗漏、实现与当前 change 明确要求不一致;
  • 测试是否覆盖本次行为变化,以及已有测试证据能否支撑相应结论。

不要把风格偏好、无关重构或没有具体影响的猜测列为审查问题。每条问题都必须指向具体文件和行号,并说明什么情况会触发错误或风险。证据不足时,降低严重程度或放入“开放问题”。

严重度仅使用:

  • CRITICAL:安全破坏、数据丢失或核心流程不可用;
  • IMPORTANT:明确的正确性错误、核心验收遗漏或高概率回归;
  • WARNING:真实但非阻塞的边界风险或测试缺口;
  • SUGGESTION:有明确收益但不影响当前正确性的改进。

5. 输出

先列出发现的问题,按严重程度排序。每条使用以下格式:

text
[IMPORTANT] 简短标题 — path/to/file.ts:123
影响:什么输入或场景会出现什么错误。
依据:与 diff、任务、规格或证据的具体对应关系。

随后输出:

  • 审查范围:workflow、change、phase、基线、纳入的差异和任何范围限制;
  • 证据状态:已读取哪些测试、构建和验证记录,以及这些记录是否仍适用于当前改动;不重新执行测试;
  • 开放问题:只有确实阻碍判断的问题;
  • 结论:汇总发现的问题数量,或明确写“未发现具体问题”。

即使没有发现问题,也必须说明尚存的风险和未执行的检查。结尾固定提醒:

这是只读的手动审查,不会推进 Comet phase,也不能替代 /comet-verify 或 Native Verify。

如果用户随后要求修复审查发现的问题,将修复作为新的写入任务处理:退出本 Skill,按仓库当前工作流规则重新进入开发流程。

© rpamis, 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 assets/skills-zh/comet-review of rpamis/comet.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit c28e724

Compare with similar skills

Comet Review 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.

Comet Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Comet Review this skillrpamis/comet3.2k—~892Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins11k9 repos~2.6kAutomated safety check: PassNone
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Finishing A Development Branchfarm-fe/farm5.6k34 repos~1.8kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    11k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • A skill your agent uses 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…

    5.6k GitHub starsUsed in 34 repos~1.8k tokens
    DevelopmentAuto-check passed
  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    56k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed

More from rpamis/comet

All 52 skills in this repo
  • Comet

    rpamis/comet

    A skill your agent uses when 用户要启动或恢复 Comet 工作流,需要根据 active change、.comet.yaml、hotfix/tweak 意图路由到对应阶段 Skill。

    3.2k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Comet

    rpamis/comet

    Comet workflow entry. An agent skill from rpamis/comet.

    3.2k GitHub stars~686 tokensUpdated today
    Auto-check passed
  • Comet

    rpamis/comet

    Comet — OpenSpec + Superpowers dual-star development workflow.

    3.2k GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Comet Archive

    rpamis/comet

    Archive and deliver a Classic change. An agent skill from rpamis/comet.

    3.2k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Comet Classic

    rpamis/comet

    Comet Classic workflow entry. An agent skill from rpamis/comet.

    3.2k GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Comet Design

    rpamis/comet

    Complete the Classic technical design and obtain user confirmation.

    3.2k GitHub stars~4.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Comet Review

What does Comet Review do?

手动审查当前 Comet change 的实现差异,只报告正确性、安全和边界问题,不推进工作流. An agent skill from rpamis/comet. Comet Review is an agent skill from rpamis/comet.

When should I use Comet Review?

Comet Review fits situations like: development work in your project.

How do I install Comet Review in Claude Code?

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

How do I install Comet Review in Codex?

Run `npx skills add rpamis/comet --skill comet-review -a codex`. Or copy the skill folder (assets/skills-zh/comet-review in rpamis/comet) into .agents/skills/comet-review in your project. Codex loads it when a task matches its description.

Can I use Comet Review 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 rpamis/comet --skill comet-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comet-review, .gemini/skills/comet-review, .github/skills/comet-review and .opencode/skills/comet-review in your project.

What does Comet Review need to run?

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

Does Comet Review 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 Comet Review 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 Comet Review use?

Comet Review 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 Comet Review use?

About 892 tokens (SKILL.md is roughly 3.6k 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 Comet Review?

Skills that share tags, products or a category with Comet Review: Finishing a Development Branch (obra/superpowers, 297k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Code Design Rationale Investigator (cursor/plugins, 11k stars) and Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Comet Review?

rpamis (a GitHub organization) maintains it in rpamis/comet, which has 3,172 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 9, 2026.

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