MCP HubMCP Hub
SKILL·DBB6C3

crit-cli

tomasz-tomczyk
更新日 27 days ago
6 閲覧
990
74
990
GitHubで表示
ドキュメントautomation

について

crit-cliスキルは、開発者がCLIコマンドを通じてプログラム的にcritインラインコメントとレビューを作成・管理できるようにし、共有成果物に対するマルチエージェントワークフローをサポートします。レビューの公開/非公開、GitHub PRとのプッシュ/プルによる同期、critレビューJSONファイルの読み書きが可能です。これは自動化されたレビューワークフローに使用し、対話型レビューセッション（`/crit`コマンドで処理）には使用しないでください。

クイックインストール

Claude Code

推奨
メイン
npx skills add tomasz-tomczyk/crit -a claude-code
プラグインコマンド代替
/plugin add https://github.com/tomasz-tomczyk/crit
Git クローン代替
git clone https://github.com/tomasz-tomczyk/crit.git ~/.claude/skills/crit-cli

このコマンドをClaude Codeにコピー＆ペーストしてスキルをインストールします

ドキュメント

Crit CLI Reference

If a plan was just written and the user said /crit or crit, invoke the /crit command — do not use this reference skill. This skill covers CLI operations like crit comment, crit pull/push, and crit share.

Comments have three scopes:

  • Line comments (scope: "line") — tied to specific lines, stored in files.<path>.comments
  • File comments (scope: "file") — about a file overall, stored in files.<path>.comments with start_line: 0
  • Review comments (scope: "review") — general feedback, stored in the top-level review_comments array

The review file path is shown by crit status.

Reading comments

When crit completes a review round, read stdout and follow its instructions. Unresolved comments are often embedded in that prompt as JSON. Check stderr for approved: true or approved: false.

When you need to read comments separately:

crit comments            # human-readable, unresolved only (default)
crit comments --json     # flat JSON for agents
crit comments --all      # include resolved comments
crit comments --plan <slug>   # plan reviews
crit comments [path]     # explicit review.json or .crit directory

Review-level comments are listed first — easy to miss in raw review.json. Uses the same review resolution as crit comment (--output, --plan, daemon session).

Multiple active sessions

When more than one review session matches the current directory and branch, crit comment refuses to guess. Run crit status (or crit status --json) to list every active session, then target the intended review explicitly:

crit comment --session <id> --author <name> <path>:<line> <body>
crit comment --session <id> --json --file comments.json --author <name>

The JSON status output exposes the candidates in sessions.

<important if="you are reading or parsing the review file"> 
{
  "review_comments": [
    {
      "id": "r_f1e2d3",
      "body": "Overall the architecture looks good",
      "scope": "review",
      "author": "User Name",
      "resolved": false,
      "replies": [
        { "id": "rp_b4a5c6", "body": "Thanks, addressed the minor issues", "author": "Claude" }
      ]
    }
  ],
  "files": {
    "path/to/file.go": {
      "comments": [
        {
          "id": "c_a1b2c3",
          "start_line": 5,
          "end_line": 10,
          "body": "Comment text",
          "quote": "the specific words selected",
          "anchor": "The sessions table needs a complete rewrite...",
          "author": "User Name",
          "resolved": false,
          "replies": [
            { "id": "rp_c7d8e9", "body": "Fixed by extracting to helper", "author": "Claude" }
          ]
        }
      ]
    }
  }
}

Field rules:

  • resolved: false or missing — both mean unresolved. Only true means resolved.
  • quote (optional): the specific text the reviewer selected — narrows scope within the line range. Focus changes on the quoted text rather than the entire range.
  • anchor (line comments): full text of the commented lines when placed. When edits shift line numbers, locate content by anchor rather than trusting start_line/end_line.
  • drifted: true: original content was removed or heavily rewritten — line numbers are approximate at best.
  • Unresolved comments may have replies — read them before acting. </important>
<important if="you are authoring or replying to comments via crit comment"> 
# Review-level (general feedback)
crit comment --author 'Claude Code' '<body>'

# File-level (whole file, no line numbers)
crit comment --author 'Claude Code' <path> '<body>'

# Line (single line or range)
crit comment --author 'Claude Code' <path>:<line> '<body>'
crit comment --author 'Claude Code' <path>:<start>-<end> '<body>'

# Reply to an existing comment
crit comment --reply-to <id> --author 'Claude Code' '<body>'

Hard rules:

  • Always pass --author 'Claude Code' (or your agent name) so comments are attributed correctly.
  • Always single-quote the body — double quotes break on backticks and shell metachars.
  • Line numbers reference the file on disk (1-indexed), not diff line numbers.
  • Reply bodies support markdown — use code fences and inline code where helpful.
  • Only pass --resolve when the user explicitly asks. Never resolve proactively. </important>
<important if="you are leaving 3+ comments in one operation">

Use --json for atomicity (single write, no partial state) and speed (one process). Two ways to feed the JSON:

# Short, single-line bodies — pipe via stdin:
echo '[
  {"body": "overall feedback", "scope": "review"},
  {"path": "session.go", "body": "restructure", "scope": "file"},
  {"file": "src/auth.go", "line": 42, "body": "Missing null check"},
  {"file": "src/auth.go", "line": "50-55", "body": "Extract to helper"},
  {"reply_to": "c_a1b2c3", "body": "Fixed — added null check"},
  {"reply_to": "r_f1e2d3", "body": "Done"}
]' | crit comment --json --author 'Claude Code'

Prefer --file <path> for any multi-paragraph body. Shell-quoted JSON breaks the moment a "body" string contains a raw newline — JSON forbids them, and the shell happily passes them through. Use the Write tool to author the JSON to a temp file, then point crit at it:

# After Write-ing /tmp/replies.json:
crit comment --json --file /tmp/replies.json --author 'Claude Code'

--file - reads stdin (same as omitting the flag).

Per-entry schema:

FieldTypeRequiredNotes
file / pathstringline/file commentsRelative path. path alone (no line) → file-level.
lineint/stringline comments42 or "45-47"
end_lineintoptionalDefaults to line
bodystringalways
authorstringoptionalPer-entry override; falls back to --author
scopestringoptional"review" / "file" — usually inferred
reply_tostringrepliesComment ID (c_… or r_…)
resolvebooloptionalOnly when user explicitly asks

Scope inference (when scope omitted): has reply_to → reply; no file/path and no line → review-level; path but no line → file-level; file/path + line → line. </important>

<important if="crit comment errored with 'comment found in multiple files'"> Comment IDs are unique per session, but the same ID can collide across files. Disambiguate with `--path`: 
crit comment --reply-to c_a1b2c3 --path src/auth.go --author 'Claude Code' 'Fixed the null check'

In --json mode, set the file field on the entry. Review-level IDs (r_…) are globally unique and never need this. </important>

<important if="you are responding to plan-mode comments (review file under ~/.crit/plans/)"> Plan reviews (via `crit plan` or the ExitPlanMode hook) store the review file in `~/.crit/plans/<slug>/`. **Always pass `--plan <slug>`** — without it, `crit comment` looks in the project root and won't find the comments. The slug is shown in the review feedback prompt. 
crit comment --plan my-plan-2026-03-23 --reply-to c_a1b2c3 --author 'Claude Code' 'Updated the plan'
</important> <important if="you are syncing with a GitHub PR (pull or push)"> 
crit pull [pr-number]                                    # Fetch PR review comments into the review file
crit push [--dry-run] [--event <type>] [-m <msg>] [pr]   # Post review comments as a GitHub PR review

Requires gh CLI installed and authenticated. PR number is auto-detected from the current branch.

--event values: comment (default), approve, request-changes. -m adds a review-level body message. </important>

<important if="the user asked to share, get a URL, get a QR code, or unpublish a review"> 
crit share <file> [file...]                          # Upload and print URL
crit share --qr <file>                               # Also print QR code (terminal only)
crit share --org <slug> <file>                       # Share under an organization
crit share --org <slug> --visibility unlisted <file> # Org share with explicit visibility
crit unpublish [file...]                              # Remove shared review
  • No server needed — reads files directly from disk. If a review file exists, comments for the shared files are included automatically.
  • Always relay the output — copy the URL (and QR if used) into your response. Don't make the user dig through tool output.
  • --qr is terminal-only — skip in mobile apps, web chat UIs, or anywhere Unicode block characters won't render correctly.
  • --org <slug> shares under an organization. Visibility defaults to organization (members only). Override with --visibility (organization, unlisted, public).
  • Unpublish uses the persisted delete token in the review file — no extra args needed. </important>

GitHub リポジトリ

tomasz-tomczyk/crit
パス: integrations/claude-code/skills/crit-cli
0
agentic-codingai-agentsai-toolsclicode-reviewdeveloper-tools
FAQ

よくある質問

crit-cli Skillとは何ですか？

crit-cli はtomasz-tomczyk が作成した Claude Skillです。Skillは、Claudeが必要に応じて読み込む指示とリソースをまとめ、追加の指示なしで crit-cli に関連するタスクを実行できるようにします。

crit-cli をインストールするには？

このページのインストールコマンドを使用してください。crit-cli をプラグインとして Claude Code に追加するか、リポジトリを skills ディレクトリにクローンし、Claudeを再起動してSkillを読み込みます。

crit-cli はどのカテゴリに属しますか？

crit-cli は ドキュメント カテゴリに属します。

crit-cli は無料で利用できますか？

はい。crit-cli は AIMCP に掲載されており、無料でインストールできます。

関連スキル

railway-docs
ドキュメント

このスキルは、Railwayの機能や仕様、特定のドキュメントURLに関する質問に答えるために、最新のRailwayドキュメントを取得します。開発者がRailwayの公式情報源から正確かつ最新の情報を直接受け取れるようにします。ユーザーがRailwayの動作方法について尋ねたり、Railwayドキュメントを参照する際にご利用ください。

スキルを見る
n8n-code-python
ドキュメント

このClaudeスキルは、n8nのコードノードでPythonコードを記述するための専門的なガイダンスを提供します。具体的には、Pythonの標準ライブラリの使用方法や、`_input`、`_json`、`_node`といったn8n独自の構文の扱い方を解説します。n8n環境内におけるPythonの制限事項を開発者が理解できるよう支援し、ほとんどのワークフローではJavaScriptの使用を推奨しながらも、特定のデータ変換ニーズに対応するPythonソリューションを提案します。

スキルを見る
archon
ドキュメント

Archonスキルは、RAGを活用したセマンティック検索とプロジェクト管理をREST APIを通じて提供します。ドキュメントの検索、階層的なプロジェクト/タスクの管理、ドキュメントアップロード機能を備えたナレッジ検索の実行にご利用いただけます。外部ドキュメントを検索する際は、他の情報源を利用する前に常にArchonを最優先で使用してください。

スキルを見る
n8n-code-javascript
ドキュメント

このClaudeスキルは、n8nのCodeノードでJavaScriptコードを書くための専門的なガイダンスを提供します。`$input`/`$json`変数、HTTPヘルパー、DateTime処理などの重要なn8n固有の構文を網羅し、一般的なエラーのトラブルシューティングも行います。CodeノードでカスタムJavaScript処理を必要とするn8nワークフローを開発する際にご利用ください。

スキルを見る