agentleFS
haruharu/redmine_ai_helper/.claude/skills/speckit-wiki-status/SKILL.md

speckit-wiki-status

Skill107 starsChanged 9 months agoMITView on GitHub

Compact wiki snapshot: counts, freshness, open lint issues, and one

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read-only snapshot of the wiki's state, ending in exactly one recommended next action.

    line 17
  2. Very specific:

    Read SCHEMA.md (scope section only), INDEX.md, sources.md, and lint-report.md if present.

    line 41
  3. Very specific:

    Never linted, or last lint older than the oldest ingest since → /speckit.wiki.lint.

    line 61
  4. Very specific:

    No pages yet → /speckit.wiki.ingest (suggest the newest feature's research.md).

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Wiki Status Skill

Wiki Status

Read-only snapshot of the wiki's state, ending in exactly one recommended next action. This is the session-resume entry point: because the wiki lives in files, a brand-new agent session rebuilds its working picture from this command in one step — nothing depends on any previous conversation.

User Input

$ARGUMENTS

Optional: a page type (decision, concept, …) to list that type's pages, or full for larger slices.

Steps

1. Resolve the wiki

Load configuration exactly as /speckit.wiki.init does. If WIKI_DIR/SCHEMA.md does not exist, report that no wiki exists yet and recommend /speckit.wiki.init <scope> — that is the whole output.

2. Load slices, not files

Read SCHEMA.md (scope section only), INDEX.md, sources.md, and lint-report.md if present. Do not read the pages themselves — the snapshot is assembled from the index and registries.

3. Render the snapshot

  • Scope — the wiki's mission sentence(s).
  • Pages — count per type, and the most recently updated 5 (from INDEX + frontmatter dates when cheaply available).
  • Sources — total registered; the 3 most recent ingests with dates.
  • Freshness — sources re-ingested more recently than their dependent pages; pages older than lint.stale_after_days.
  • Open issues — top rows from lint-report.md by severity (semantic > structural > mechanical), or "never linted" if absent.

4. Recommend exactly one next action

Priority order — pick the first that applies:

  1. Unresolved conflict in the lint report → resolve it (name the page).
  2. Never linted, or last lint older than the oldest ingest since → /speckit.wiki.lint.
  3. No pages yet → /speckit.wiki.ingest (suggest the newest feature's research.md).
  4. A feature shipped since the last ingest → ingest its artifacts.
  5. Otherwise → /speckit.wiki.query <the scope's most central open question> to probe coverage.

Guardrails

  • Writes nothing, ever.
  • Fits on one screen for the default invocation; full may triple the slices but still never loads page bodies.
  • The recommendation must name a concrete command with concrete arguments — "consider maintaining the wiki" is not a recommendation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.