メニュー
Append a structured entry to the agent log with automatic rotation
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Definitive reference for how Claude Code works — disambiguates skills vs hooks vs subagents vs MCPs vs slash commands vs memory vs settings. Use when asked "how does Claude Code X work", "what's the difference between X and Y", "where should this live", "build me a [skill|hook|agent|mcp|slash command]", "configure Claude Code", or when picking the right surface for a new capability.
Scribe — the project-documentation skill. Generate or maintain a project's Claude-facing documentation (CLAUDE.md, .claude/docs/*, project-context.md, README) from verified facts. Use when the user says "document this project", "write the docs for X", "the docs are stale", "fill in the .claude docs", or "/scribe". Detects existing doc state and routes between from-scratch and update. Verify-before-assert is the core discipline — confirmed facts go to committed docs, inferred/uncertain ones go to a separate hazards artifact, never silently into the repo.
Speak content aloud via Kokoro neural TTS (local, offline). Use when the user says "read it for me", "read it to me", "play it in audio", "say it", "speak it", "read that aloud", "/say-it", or asks to hear something spoken instead of reading it.
Install a local neural voice interface for Claude Code on macOS Apple Silicon. Wires mlx-whisper (STT) + Kokoro TTS (offline neural voices) into voice-claude and vtranscribe CLI scripts. Two voice contexts — personal (af_heart) and tech (af_bella). Multi-session safe — concurrent sessions speak in turn (global lock) and announce their name. No cloud APIs, no API keys.
Collect the user's daily work activity from Slack, Jira, Confluence, GitHub, and Google Drive with source links
Collect a team member's daily work activity from Slack, Jira, Confluence, and GitHub
| name | log |
| description | Append a structured entry to the agent log with automatic rotation |
| user_invocable | false |
| args | run_id=<id> skill=<name> status=<SUCCESS|FAILED|WARNING> detail=<message> |
Append a structured log entry to <workspace>/.claude/memory/agent-log.md. This skill owns the log format, creation, and rotation. All other skills and agents call this instead of writing to the log directly.
Setup — Resolve <workspace>: The skill's base directory is <workspace>/.claude/skills/log/; walk up three directory levels and validate that <workspace>/.claude/.workspace exists. Use this <workspace> for all path references below. Abort with a setup-broken error if validation fails.
Parse input: Extract the fields from the arguments:
run_id — Identifier linking related entries (e.g., cos-2026-04-11-1). Use manual if no run ID was provided.skill — Name of the skill or agent that produced this entrystatus — SUCCESS, WARNING, or FAILEDdetail — Brief description (item counts on success, error reason on failure)Check if log file exists: Read <workspace>/.claude/memory/agent-log.md.
# Agent Log
| Timestamp | Run ID | Skill | Status | Detail |
|-----------|--------|-------|--------|--------|
Append the entry: Add a new row with the current timestamp in ISO 8601 format (e.g., 2026-04-11T17:30Z).
Rotate: Count the data rows (excluding the header and separator lines). If there are more than 200, remove the oldest rows to keep exactly 200. Historical entries are preserved in git history.
No output: This skill is silent — it does not print anything to the user. It is a utility called by other skills.