菜单
Save session wrap-up documentation before clearing context by running the session-documenter workflow and writing `.agents/sessions/YYYY-MM-DD.md`. Use when ending a session, preparing to run `/clear`, or asked to document what changed before context is reset.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | session-end |
| description | Save session wrap-up documentation before clearing context by running the session-documenter workflow and writing `.agents/sessions/YYYY-MM-DD.md`. Use when ending a session, preparing to run `/clear`, or asked to document what changed before context is reset. |
| metadata | {"version":"1.0.0","tags":"session, workflow, documentation, productivity"} |
Document your session before clearing context. This is a TWO-STEP process: /session-end documents, then user manually runs /clear.
Inputs:
Outputs:
Creates/Modifies:
.agents/sessions/YYYY-MM-DD.md.agents/ task or summary files when delegated to session-documenterExternal Side Effects:
Confirmation Required:
Delegates To:
session-documenterrules-capture for unresolved reusable preferencesskill-capture for reusable workflows that should become skillsWhen invoked, immediately:
session-documenter skill to save a redacted session summaryCross-platform note: If your agent platform doesn't support skill invocation, follow the session-documenter workflow manually by reading the
session-documenterskill definition.
After documentation is complete, tell the user:
Session documented to .agents/sessions/YYYY-MM-DD.md
NEXT STEP: Run /clear to clear the conversation context.
Your session is safely preserved and will be loaded on next /session-start.
/clear manually after[REDACTED_SECRET] and summarize the surrounding context.Regenerate catalog counts, layout claims, and README summaries from canonical sources. Run after adding, removing, or renaming skills, commands, or bundles.
Audit the skills library for duplicates, stale content, spec violations, and structural issues. Run periodically or before releases.
Validate SKILL.md files against the Agent Skills spec and Claude Code extensions. Run on new or modified skills before committing.
Audit AI agent instruction files (AGENTS.override.md, AGENTS.md, configured fallbacks, CLAUDE.md, hooks, and settings) across workspaces in read-only report mode. Use when agent configs drift, rules duplicate, files go stale, or after workspace restructuring; apply fixes only when explicitly requested.
Exercises rejection of an unsupported Codex project command path.
Design and operate LLM-as-a-Judge evaluation systems using direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment. Use when building LLM-as-judge systems, comparing model responses, calibrating rubrics, debugging inconsistent evaluations, or designing A/B tests for prompt or model changes.