skills/documentation-state-auditor/SKILL.md
Audit repository docs for confusion between implemented state, intended or planned state, and unresolved questions, then recommend documentation boundaries, structure, progressive disclosure, and writing rules.
npx skillsauth add sjunepark/custom-skills documentation-state-auditorInstall 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.
Use this skill when a repository's docs may blur:
The goal is not to enforce one documentation system. The goal is to make those kinds of truth legible with the lightest structure that fits the project, and to make the tree readable enough that readers can move from overview to detail without guesswork.
This skill should answer:
When reviewing docs, classify content into these buckets:
current: factual present-state repository or runtime realitytarget: intended or accepted future-state designquestion: unresolved areas that should not be read as settledhistory: optional rationale or decision context, only when it still helps future readersDo not assume every project needs a separate home for every bucket. Some projects need explicit directories. Others only need better section boundaries.
AGENTS.md, ARCHITECTURE.md, README.md, and the docs index if they exist.current, target, question, or mixed.current/, target/, and questions/Use these heuristics when judging documentation quality:
Do not prescribe these mechanically. Pick one based on the repository.
Use when:
Approach:
Current State, Target State, and Open QuestionsTrade-offs:
Use when:
Approach:
docs/current/, docs/target/, and docs/questions/Trade-offs:
Use when:
Approach:
architecture/, database/, and workflows/Trade-offs:
Recommend rules like these when they fit:
will, should, target, or equivalent language for intended state.Use this shape unless the user asks for something else:
Do not:
current/ and target/ directories?"development
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, empty states, UX review, visual hierarchy, information architecture, accessibility, performance, responsive behavior, theming, typography, spacing, layout, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, design systems, tokens, live browser iteration, and ambitious visual effects. Not for backend-only or non-UI tasks.
development
Manually integrate Git branch work without blind mechanical merges. Use when merging, transplanting, or refactoring branch work; resolving conflicts; preserving source-branch intent in a clean current-branch structure; or auditing that source additions, removals, tests, and docs landed intentionally.
testing
Prepare, audit, set up, and guide Release Please releases. Use when releasing, preparing or reviewing a release PR, adding Release Please, classifying SemVer impact or breaking changes, writing Release Please-compatible Conventional Commit guidance, or documenting release criteria. Release work requires existing Release Please config; setup requires an explicit setup request.
development
Teach how code, a subsystem, architecture area, feature flow, module, API/data boundary, or relevant technical concept works for reviewers and maintainers. Use when the user asks to understand code or concepts; focus on design, responsibilities, contracts, data flow, invariants, tradeoffs, and maintenance implications, not syntax or line-by-line execution. Use `change-explainer` for diffs, commits, or patches.