メニュー
Log decisions, progress, deviations, and discoveries during any workflow phase
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
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
Capture feedback about wf, util, or vault plugins and file it as a GitHub issue for improvement. Use after any session where the tooling fell short — wrong agent behavior, missing skill coverage, misleading prompts, workflow friction, or convention gaps. Only for generic plugin improvements that would help ANY project, not repo-specific config. Files to JSai23/claude-tooling with the plugin-feedback label.
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
| name | wf-logging-a |
| description | Log decisions, progress, deviations, and discoveries during any workflow phase |
| metadata | {"source-plugin":"wf","source-skill":"logging-a"} |
Action skill — Structured logging: decisions, progress, deviations, discoveries.
$ARGUMENTS
Record a structured log entry in the active plan doc or decision log.
decision)Record a decision with rationale in design-docs/plans/{name}/{name}_decisions.md:
## [YYYY-MM-DD] {Decision Title}
Context: {What prompted this decision}
Decision: {What was decided}
Rationale: {Why — include tradeoffs considered}
Impact: {What this changes about the plan or system}
progress)Add a timestamped entry to the Progress section of the active plan doc:
- [YYYY-MM-DD HH:MM] {What was completed or what state we're in}
surprise)Record an unexpected discovery in the Surprises section of the active plan doc:
### [YYYY-MM-DD] {What was surprising}
Expected: {What we thought would happen}
Actual: {What actually happened}
Implication: {How this affects the plan or approach}
deviation)Record a deviation from the plan. Adds to both the decision log and the plan doc:
## [YYYY-MM-DD] Deviation: {title}
Original plan: {What the plan doc said}
Actual approach: {What we're doing instead}
Reason: {Why the change was necessary}
Impact: {Effect on remaining milestones}
design-docs/plans/ for active plans or locate the active plan in the relevant scope)