plugins/autonomous-dev/skills/documentation-guide/SKILL.md
Documentation standards enforcing Keep a Changelog format, README structure, ADR templates, and Google-style docstrings. Use when writing CHANGELOG entries, updating READMEs, or documenting APIs. TRIGGER when: changelog, readme, documentation, docstring, ADR, API docs. DO NOT TRIGGER when: code-only changes, test files, config updates without API changes.
npx skillsauth add akaszubski/autonomous-dev documentation-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Ensures all documentation is consistent, current, and complete. Used by the doc-master agent.
All CHANGELOG entries MUST follow Keep a Changelog format.
# Changelog
## [Unreleased]
### Added
- New authentication module (#123)
### Fixed
- Token expiry off-by-one error (#124)
## [1.2.0] - 2026-02-15
### Added
- Batch processing support (#100)
The [Unreleased] section MUST always exist at the top for accumulating changes.
Every README.md MUST contain these sections in order:
All public functions MUST have Google-style docstrings.
def process_data(
data: List[Dict],
*,
validate: bool = True,
) -> ProcessResult:
"""Process input data with optional validation.
Args:
data: Input records as list of dicts with 'id' and 'content' keys.
validate: Whether to validate input before processing.
Returns:
ProcessResult with metrics and processed items.
Raises:
ValueError: If data is empty or missing required keys.
"""
Include Args, Returns, and Raises for every public function. Omit sections only if truly not applicable (e.g., no exceptions raised).
Documentation MUST stay in sync with code at all times.
FORBIDDEN:
REQUIRED:
| Change Type | README | CHANGELOG | Docstrings | ADR | |------------|--------|-----------|------------|-----| | API change | Yes | Yes | Yes | Maybe | | New feature | Yes | Yes | Yes | Maybe | | Bug fix | No | Yes | No | No | | Refactor (no behavior change) | No | No | Maybe | Maybe | | Architecture decision | No | No | No | Yes | | Config change | Yes | Yes | No | No | | Deprecation | Yes | Yes | Yes | Maybe |
For major architectural decisions, create an ADR (Architecture Decision Record).
# ADR-NNN: [Title]
**Date**: YYYY-MM-DD
**Status**: Proposed | Accepted | Deprecated | Superseded by ADR-NNN
## Context
What is the issue or decision we need to make?
## Decision
What did we decide and why?
## Consequences
What are the positive and negative outcomes?
## Alternatives Considered
What other options were evaluated and why were they rejected?
Store ADRs in docs/adr/ directory, numbered sequentially.
This project has 17 agents and 40 skills.
These numbers drift immediately. Verify against filesystem or use dynamic discovery.
# Count before documenting
ls plugins/autonomous-dev/agents/*.md | wc -l
ls plugins/autonomous-dev/skills/*/SKILL.md | wc -l
See [architecture guide](docs/ARCHITECTURE.md) for details.
If docs/ARCHITECTURE.md was renamed to docs/ARCHITECTURE-OVERVIEW.md, this link is broken.
Check all links exist before committing documentation changes.
Shipping a user-visible feature with no CHANGELOG entry. Users cannot discover what changed.
Write the CHANGELOG entry before or during implementation, not as an afterthought.
development
One topic, one home. Routes content to its canonical store (CLAUDE.md, PROJECT.md, MEMORY.md, docs/, memory/) and audits for duplication. TRIGGER when: auditing CLAUDE.md/PROJECT.md/MEMORY.md sizes, deduplicating docs, applying the content-allocation pattern to a new repo, running /align --content. DO NOT TRIGGER when: implementing features, writing tests, routine code edits, debugging.
development
GenAI-first testing with structural assertions, congruence validation, and tier-based test structure. Use when writing tests, setting up test infrastructure, or validating coverage. TRIGGER when: test, pytest, coverage, TDD, test patterns, congruence, validation. DO NOT TRIGGER when: production code implementation, documentation, config-only changes.
testing
Prompt engineering patterns for writing agent prompts and skill files — constraint budgets, register shifting, HARD GATE patterns, anti-personas. Use when writing or reviewing agents/*.md or skills/*/SKILL.md. TRIGGER when: agent prompt, skill file, prompt engineering, model-tier compensation, HARD GATE, prompt quality. DO NOT TRIGGER when: user-facing docs, README, CHANGELOG, config files.
testing
7-step planning workflow for pre-implementation design. Enforced by plan_gate hook, critiqued by plan-critic agent. Use when creating plans, design documents, or architecture decisions before implementation. TRIGGER when: plan, planning, /plan, design document, architecture decision. DO NOT TRIGGER when: implementation, coding, testing.