From agent-skills
Rewrites documentation into scannable Markdown with quickstarts first, workflows, tables, Mermaid diagrams, and approval-gated file edits for humans and agents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-skills:cmd-docs-idiot-proofThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this command to write or rewrite documentation so it is simple, fast to scan, and easy to execute.
Use this command to write or rewrite documentation so it is simple, fast to scan, and easy to execute.
<details><summary>...</summary>...</details>Correct pattern:
Start the server:
make start_server
Run a command:
make run_command
Incorrect pattern (separate steps combined in one unlabeled block):
make start_server
make run_command
Use only sections that add value for the specific document. Default section set:
If environment variables or configuration values are required, use this format:
| Name | Purpose | Default |
|---|---|---|
APP_ENV | Runtime environment | development |
API_URL | Base URL for API calls | http://localhost:8000 |
Move long explanations, implementation notes, and low-priority reference material into details blocks:
<details>
<summary>Deep dive: request lifecycle</summary>
Detailed explanation here.
</details>
.md).npx claudepluginhub olshansk/agent-skills --plugin agent-skillsGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Resolves in-progress git merge or rebase conflicts by analyzing history, understanding intent, and preserving both changes where possible. Runs automated checks after resolution.