Agent skill
mcaf-documentation
Create or refine durable engineering documentation: docs structure, navigation, source-of-truth placement, and writing quality. Use when a repo’s docs are missing, stale, duplicated, or hard to navigate, or when adding new durable engineering guidance.
Stars
47
Forks
6
Install this agent skill to your Project
npx add-skill https://github.com/managedcode/MCAF/tree/main/skills/mcaf-documentation
SKILL.md
MCAF: Documentation
Trigger On
- docs are missing, stale, duplicated, or hard to navigate
- a repo needs a cleaner source-of-truth structure
- durable engineering guidance needs to be added without bloating pages
Value
- produce a concrete project delta: code, docs, config, tests, CI, or review artifact
- reduce ambiguity through explicit planning, verification, and final validation skills
- leave reusable project context so future tasks are faster and safer
Do Not Use For
- writing a specific feature spec or ADR when that skill already fits
- dumping large template content into public pages
Inputs
- current docs structure and entry pages
- the code, policy, or workflow that the docs should reflect
- duplicate or conflicting sources of truth
Quick Start
- Read the nearest
AGENTS.mdand confirm scope and constraints. - Run this skill's
Workflowthrough theRalph Loopuntil outcomes are acceptable. - Return the
Required Result Formatwith concrete artifacts and verification evidence.
Workflow
- Decide the canonical location for each fact before writing.
- Prefer navigational docs that link to detail instead of copying detail.
- Keep bootstrap pages small; move workflow scaffolds into skills.
- Update stale docs in the same change as the code or policy they describe.
Deliver
- cleaner docs structure
- better source-of-truth placement
- docs that reflect the code and workflow that actually exist
Validate
- each durable fact has one clear home
- entry pages route the reader correctly
- pages do not bloat with template or reference dumps
- docs match the real repo, not the intended future repo
Ralph Loop
Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.
- Brainstorm first (mandatory):
- analyze current state
- define the problem, target outcome, constraints, and risks
- generate options and think through trade-offs before committing
- capture the recommended direction and open questions
- Plan second (mandatory):
- write a detailed execution plan from the chosen direction
- list final validation skills to run at the end, with order and reason
- Execute one planned step and produce a concrete delta.
- Review the result and capture findings with actionable next fixes.
- Apply fixes in small batches and rerun the relevant checks or review steps.
- Update the plan after each iteration.
- Repeat until outcomes are acceptable or only explicit exceptions remain.
- If a dependency is missing, bootstrap it or return
status: not_applicablewith explicit reason and fallback path.
Required Result Format
status:complete|clean|improved|configured|not_applicable|blockedplan: concise plan and current iteration stepactions_taken: concrete changes madevalidation_skills: final skills run, or skipped with reasonsverification: commands, checks, or review evidence summaryremaining: top unresolved items ornone
For setup-only requests with no execution, return status: configured and exact next commands.
Load References
- read
references/documentation.mdfor structure and documentation-quality guidance
Example Requests
- "Clean up this docs mess."
- "Move process clutter out of public pages."
- "Make the repo docs navigable for an agent."
Didn't find tool you were looking for?