pr-review
Skill2 starsChanged 5 months agoMITView on GitHub
「この PR レビューして」「#123 確認して」「PR どう思う」と頼まれたら、opshub MCP の recall.search で関連 source / decision / 過去 review を引き、必要に応じて gh pr diff の出力を組み合わせてレビュー観点を提示する。read 系のみで構成され、PR への comment 投稿は外部送信扱いで本 skill では行わない。
196 other projects use a version of this.
Adopted by
Most recently taken up by
- IntelRealSense/librealsensetheir own version, first seen Nov 16, 2026
- wikimedia/wikipedia-iostheir own version, first seen Nov 16, 2026
- realsenseai/librealsensetheir own version, first seen Nov 16, 2026
- minio/skillstheir own version, first seen Nov 16, 2026
- lumlaolao/spike-evaltheir own version, first seen Nov 16, 2026
- AshrafDurjoy/genai-shared-patternstheir own version, first seen Nov 16, 2026
Used with
Projects with it also use clack-cli-patterns, drag-to-reorder 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.
openchamberSkillclack-cli-patterns
Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.
Also in 3 projects that use this
openchamberSkilldrag-to-reorder
Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.
Also in 3 projects that use this
jtenniswoodSkillexpert-reset
Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.
Also in 3 projects that use this
CES-LtdSkilloss-pr
Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.
Also in 3 projects that use this
CES-LtdSkillpr-automation
PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".
Also in 3 projects that use this
- +7 more from openchamber
Other versions196 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 196
- Significant-Gravitas/AutoGPT★ 188ksame name
- pytorch/pytorch★ 106ksame name
- rtk-ai/rtk★ 87ksame name
- saadeghi/daisyui★ 43ksame name
- rustfs/rustfs★ 36ksame name
- dotnet/maui★ 23ksame name
- NVIDIA/Megatron-LM★ 18ksame name
- MiniMax-AI/skills★ 14ksame name
- btriapitsyn/openchamber★ 13ksame name
- openchamber/openchamber★ 13ksame name
186 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- announcement-draftSkill
- catchupSkill
- decision-rationaleSkill
- external-briefSkill
- find-documentSkill
- handoff-draftSkill
- inbox-triageSkill
- meeting-followupSkill
- meeting-prepSkill
- next-actionsSkill
- personal-briefSkill
- pr-reviewSkill
- reply-draftSkill
- researchSkill
- source-extractSkill
- announcement-draftSkill
- catchupSkill
- decision-rationaleSkill
- external-briefSkill
- find-documentSkill
- handoff-draftSkill
- inbox-triageSkill
- meeting-followupSkill
- meeting-prepSkill
- next-actionsSkill
- personal-briefSkill
- reply-draftSkill
- researchSkill
- source-extractSkill
The file
Files
pr-review — opshub の記憶を引いて PR レビューを補強する
opshub MCP server (opshub mcp serve、ADR-0022) の read 系 tool で、GitHub PR レビューに必要な「過去にこのコンポーネントで何が決まったか」「関連する task / decision / source は何か」を引いてホスト側 LLM に渡す。
opshub 単体では LLM 推論ループを持たない (ADR-0004 §(a) 形A)。実際の差分理解とコメント生成は外部ホスト (Claude Code 等) 側が行う。本 skill はあくまで opshub の記憶層からどう情報を引くか の手順書。
何が起きるか
- ユーザーが「PR #123 レビュー」「この差分どう?」と頼む
- ホストが本 skill を発火
- ホストは GitHub 側情報 (差分・既存コメント) を
ghCLI で取得 (skill 範囲外、ホスト側責務) - 同時に opshub MCP の
recall.searchで関連記憶を引く - 2 種の情報を組み合わせて指摘事項を組み立てる
- PR への comment 投稿は 本 skill 外 (外部送信、ADR-0010 §禁止事項 7 のスピリットに従いユーザーが手で
gh pr reviewを実行)
呼び出し順 (MCP tool)
Step 1: PR 番号 / リポ名から関連 source を recall
tool: recall.search
input:
query: "PR #<N> <component-name>"
limit: 15hits[] から GitHub source (PR / issue / commit) と関連する task / decision を抽出。本文ベース embedding (Sub-issue B、ADR-0012 改訂) によりコメント内容や commit message も hit する。
Step 2: 過去の同コンポーネントの decision を確認
decision.list は Phase 12 H1 (ADR-0022 改訂) で physical-column ベースの時間フィルタ recorded_after / recorded_before (ISO 8601、decisions.recorded_at) を取れるようになった。直近 N 週間の decision だけ引きたい場合は:
tool: decision.list
input:
recorded_after: "<N 週間前 ISO 8601>"
limit: 30component / module path で絞り込みたい場合は recall.search を component 名で発火し、戻り値 hits[] を entity_type == "decision" で post-filter する経路を取る:
tool: recall.search
input:
query: "<component or module path>"
limit: 30ホスト側で hits[] から entity_type が decision のものだけを抽出し、上位 10 件程度を「過去の同コンポーネントの意思決定」として表示する。本文ベース embedding (Sub-issue B、ADR-0012 改訂) により module path や component 名が decision 本文に含まれていれば hit する。
Step 3 (任意): 同コンポーネントの open task を確認
tool: task.list
input:
state: "active"
limit: 50過去に「ここは Phase X.x で直す」と pin されている open task が無いか確認。レビュー指摘の重複を避ける。
Step 4 (任意): 関連 entity の graph を追う
recall.search で hit した task / decision / source の周辺に何が紐付いているか確認するなら graph 系 tool が使える。指摘候補の根拠付けに使える。
tool: graph.related
input:
entity_type: "<task|decision|source>"
entity_id: "<ULID>"
direction: "both"
limit: 30過去の意思決定が現在どの task / source に波及しているかを追うなら graph.trace (provenance 方向、backward) や graph.expand (双方向 N-hop) も有効。すべて read-only。
tool: graph.trace
input:
entity_type: "source"
entity_id: "<該当 PR の source ULID>"
depth: 3出力フォーマット (ホスト側)
# PR #N レビュー観点
## 関連する過去の意思決定
- ADR-XXXX で ... と pin 済
- decision #M で ... と決定済
## 関連する未完了 task
- [P1] #task-id ...
## 指摘候補 (ホスト LLM が差分と合わせて生成)
- ...
## コメント投稿
- 良ければユーザーが `gh pr review --comment` で投稿 (opshub は GitHub への書き戻しを行わない)自律範囲
- read tool のみ —
recall.search/decision.list/task.listはすべてreadOnlyHint=true - PR へのコメント投稿 / approval は 本 skill 範囲外。ユーザーが
ghCLI で手動実行
できないこと / やらない
- GitHub PR への comment 投稿 / approval / merge (ADR-0010 §禁止事項 7、Phase 10 plan §1 #6)
- task や inbox への自動追記 (write は別 skill / 確認経路)
- 「LGTM」の自動承認 — レビューの最終判断は人 (ホスト LLM ではなく、ユーザー自身)
参考
- ADR-0004 (Agent Runtime Boundary、形A)
- ADR-0010 §禁止事項 7 + §改訂 (外部 SaaS 書き戻し禁止、Phase 11 で Teams 追加)
- ADR-0012 改訂 (本文 embedding で recall 品質)
- ADR-0020 §改訂 (Outlook body deep retention、Phase 11)
- ADR-0025 (Office 文書本文抽出)
- Phase 11 plan (
docs/phase-11-plan.md) - docs/assistant-agent.md
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
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.

