القائمة
Generate or update project documentation
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | util-doc |
| description | Generate or update project documentation |
| metadata | {"source-plugin":"util","source-skill":"doc"} |
$ARGUMENTS
Generate or update documentation following strict principles.
Documentation that doesn't get read is useless. Every line must earn its place.
Before writing, ask:
Cut ruthlessly. Then cut more.
api)Auto-generated. Never manually written.
Extract from code:
Format: Generated reference, not prose. Tables and signatures, not paragraphs.
howto)Mini-tutorials that set contracts.
Structure:
# How to {do thing}
## What You Need
- {prerequisite}
- {prerequisite}
## Steps
1. {step}
2. {step}
## What the System Expects
- {contract/requirement}
- {contract/requirement}
## Common Mistakes
- {mistake} → {fix}
Keep it scannable. Bullet points over prose.
arch)High-level system design. Must stay current.
Structure:
# Architecture: {component/system}
## Overview
{One paragraph max}
## Components
{Diagram or list with one-line descriptions}
## Data Flow
{How information moves through the system}
## Key Decisions
- {decision}: {why}
## Boundaries
- {what's in scope}
- {what's out of scope}
Update this when the system changes. Stale architecture docs are worse than none.
/doc after significant code changesReview ALL existing documentation against current code. Update anything stale. Report what was changed.