agentleFS
odakinodakin/claude-config/skills/wrap/SKILL.md

wrap

Skill4 starsChanged 19 days agoMITView on GitHub

作業の仕上げ (締めの sweep)。 user が `/wrap` (または「仕上げ」「締め」「wrap up」) と打ったら起動する。 この session と、 この session が使った agent・子 session・別 session への依頼で得た知見・手順・使い捨ての script を正しい層の正本へ移し、 正本と参照・SESSION・TODO を整え、 repo ごとに commit + push して報告する。 claude-config の改善案は PR で出す。 Closing sweep for any claude-config user (Claude Code and Codex).

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use start, update 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.
  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 5 projects that use this

  • AnthropicSkill

    update

    Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email.

    Also in 3 projects that use this

  • LangChainSkill

    remember

    Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.

    Also in 3 projects that use this

  • termdockSkill

    recall

    Retrieves cross-session memories about past decisions, lessons, and patterns. Use when user asks about prior work, past decisions, or mentions a feature. Triggers include check memory, what did we decide, how did we solve.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 7 projects that use this

  • +1 more from anthropics

The file

Files
SKILL.md

wrap — 締めの sweep (claude-config の汎用版)

手順の正本 = claude-config の conventions/closing-sweep.md — 0 から 5 まで順に読んで、 そのとおりにする (この file は claude-config の skills/wrap/。 claude-config の root = この file の 2 つ上、 普通は ~/Claude/claude-config)。 手順・OS ごとの違い (macOS / Linux / Windows)・Codex での読み替えは、 その doc の §0.9 と §0.95 が持つ = ここに写さない。

この版の値

段値
0.3 / 0.5 の <id8>この session の id の先頭 8 文字 (Claude Code = 会話記録の file 名の uuid。 Codex = 渡された session id)
道具claude-config の scripts/ (search-agent-transcripts.py / session-scripts-report.py / codex-wrap-inventory.py / session-claims-report.py / session-reply-knowledge-report.py / session-open-questions-report.py / session-fetched-docs-report.py / subagent-reports.py / headless-worker-reports.py / replay-session-scripts.py / fix-md-links.py、 最後の段の背景の見張りの数え上げ = lib/session_background_tasks.py self) (OS ごとの起動の違い = 上の §0.9)。数値照合の正本 = lib/output_numbers.py、候補の扱い = 0.3
0.5 / 1.5 の掲示板掲示板を使っていなければ飛ばし、 報告に「使っていない」 と書く
作業した repo の約束各 repo の CLAUDE.md (暗号化・平文に書かないもの・commit message の規則・公開か非公開か) を全段に当てる
個人の値個人層に同名の skill (/wrap) があればそちらが起動する。 その skill は本 file を手順の正本として指し、 その人の値だけを持つ (closing-sweep.md#personal-skill)

claude-config への改善案は PR で出す (既定)

1 の表で「層1」 に置くと決めたもの (誰にでも効く手順・道具の壊れ方・規約の穴・雛形の不足) は手元だけに置かず、 claude-config に入れる。 claude-config に push できない人は fork して PR を出す。 出すのが既定 = 1 件ごとに user に可否を聞かない (止めるのは user が止めたときだけ)。 手順・境界・確かめ方の正本 = closing-sweep.md#upstream-pr。 出した PR は link と要約を報告に書く。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.