docs-from-code
- Repo stars 1
- Author updated Live
- Author repo claude-skills
- Domain
- Documentation
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @00PrabalK00 · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: docs-from-code
description: Turn implementation details into practical documentation such as README updates, setup guides, a…
category: documentation
runtime: no special runtime
---
# docs-from-code output preview
## PART A: Task fit
- Use case: Turn implementation details into practical documentation such as README updates, setup guides, architecture notes, runbooks, changelogs, and internal reference docs. Use when code exists but docs lag behind or when shipping a feature requires clear documentation..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Overview / Core Workflow / Deliver” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Turn implementation details into practical documentation such as README updates, setup guides, architecture notes, runbooks, changelogs, and internal reference docs. Use when code exists but docs lag behind or when shipping a feature requires clear documentation.”.
- **02** When the source has headings, the agent prioritizes “Overview / Core Workflow / Deliver” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Overview / Core Workflow / Deliver”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: docs-from-code
description: Turn implementation details into practical documentation such as README updates, setup guides, a…
category: documentation
source: 00PrabalK00/claude-skills
---
# docs-from-code
## When to use
- Turn implementation details into practical documentation such as README updates, setup guides, architecture notes, run…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Overview / Core Workflow / Deliver” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "docs-from-code" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Overview / Core Workflow / Deliver
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Docs From Code
Overview
Translate what the code does into documentation people can actually use.
Core Workflow
- Identify the audience first: developer, operator, customer, reviewer, or teammate.
- Read the code, scripts, config, and tests to extract accurate setup steps, behaviors, constraints, and terminology.
- Organize the document around real user needs such as setup, architecture, usage, troubleshooting, or change impact.
- Add examples and commands only when they are supported by the repo or provided artifacts.
- Tighten for clarity and remove implementation noise that does not help the audience.
Deliver
- Produce docs that are specific, runnable, and easy to scan.
- Include caveats, prerequisites, and common failure points when they matter.
- Update existing docs instead of creating duplicates when a home already exists.
Guardrails
- Do not invent commands, file paths, or guarantees.
- Keep architecture explanations high-signal rather than encyclopedic.
- Prefer the repository's established tone and documentation structure.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review