context-session-end
- Repo stars 39
- Author updated Live
- Author repo awesome-omni-skill
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @diegosouzapw · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: context-session-end
description: AI behavioral guideline for autonomously detecting work session boundaries and proposing updates…
category: other
runtime: no special runtime
---
# context-session-end output preview
## PART A: Task fit
- Use case: AI behavioral guideline for autonomously detecting work session boundaries and proposing updates to current_focus.md. The AI monitors conversation flow for natural breakpoints and acts without explicit invocation..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “基本方針 / 検知パターン / 手順” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “AI behavioral guideline for autonomously detecting work session boundaries and proposing updates to current_focus.md. The AI monitors conversation flow for natural breakpoints and acts without explicit invocation.”.
- **02** When the source has headings, the agent prioritizes “基本方針 / 検知パターン / 手順” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “基本方針 / 検知パターン / 手順”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: context-session-end
description: AI behavioral guideline for autonomously detecting work session boundaries and proposing updates…
category: other
source: diegosouzapw/awesome-omni-skill
---
# context-session-end
## When to use
- AI behavioral guideline for autonomously detecting work session boundaries and proposing updates to current_focus.md.…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “基本方針 / 検知パターン / 手順” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "context-session-end" {
input -> user goal + target files + boundaries + acceptance criteria
context -> 基本方針 / 検知パターン / 手順
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Context Session End
作業の自然な区切りをAIが自律的に検知し、current_focus.md への追記を提案する行動規範。
基本方針
ユーザーが「セッション終了スキルを実行して」と言う必要はない。AIは会話の流れから作業の区切りを自然に検知し、記録すべき内容があれば自分から提案する。
検知パターン
以下の自然な区切りを検知したら自動的に追記を提案する:
- 「ありがとう」「助かった」
- 「一旦ここまで」「今日はこれで」
- まとまった作業（複数ステップ）が一段落したとき
提案しない場合: 短い質問応答（「このSQL正しい？」→「OK」）程度の場合。
手順
1. AI作業分の要約
セッション中にAIが関与した作業を振り返り、以下を抽出:
- やったこと（コード作成、設計レビュー等）
- 決まったこと（あれば）
- 残っていること
2. 追記案の提示
📝 current_focus.md に追記しますか？
【最近あったこと】に追加:
+ [AI] CRUD API 5本作成完了
+ [AI] SQLインデックス追加
【次やること】に追加:
+ E2Eテスト作成
（はい / 修正あり / 不要）3. Decision Log 提案（該当する場合のみ）
重要な決定があった場合のみ、1行で:
💡 「ページネーションをcursor方式に決定」→ Decision Logに記録しますか？4. Tensions 更新提案（該当する場合のみ）
以下のいずれかに該当する場合のみ提案する:
新たな未解決課題が発生した場合:
⚠️ tensions.md に追記しますか？ → {未解決課題の要約}既存の tensions.md 項目が解決した場合:
tensions.md の「{項目名}」はこのセッションで解決しました。削除しますか？5. 更新実行
承認後:
- current_focus.md の該当セクションに追記（既存内容は触らない）
[AI]プレフィックスをつける- 末尾の「更新」日付を更新
ルール
- ✅ AI作業分のみ追記提案する
- ✅ 既存の人間が書いた行はそのまま残す
- ✅
[AI]プレフィックスで区別する - ✅ 3-5行以内で簡潔に
- ❌ 人間が書いた行を編集・削除しない
- ❌ current_focus.md を全面書き換えしない
- ❌ 承認なしにファイルを更新しない
Decide Fit First
Design Intent
How To Use It
Boundaries And Review