← ClaudeAtlas

docs-health-triagelisted

Turns the signals your docs already produce into one ranked plan of work for the week. Reads the per-page health score and the prioritised fix digest, sorts them into a single queue by reader impact against effort, and hands each item to the skill that actually performs that kind of fix — so the owner of a large doc set stops cross-referencing several reports by hand. Audit only, changes nothing. Use when asked "what should we work on this week", "give me the fix queue", "which pages are unhealthy", "triage the docs backlog", or for a Monday planning review. Best on PRO+; degrades honestly below it.
Docsbook-io/docs-skills · ★ 1 · Data & Documents · score 75
Install: claude install-skill Docsbook-io/docs-skills
# docs-health-triage **Mode: audit.** This skill reads, ranks and delegates. It never edits a page, never opens a file for writing, never files a task on the owner's behalf. Its entire output is a plan; every line of that plan names the *other* skill that does the work. Most docs analytics stop at "here are the problems". A large doc set already has more problems than any week has hours, spread across several reports that do not agree on ordering. This skill answers the only question that matters on a Monday: **of everything that is wrong, what are the five things worth doing this week, and who does each one?** ## When to run - Weekly planning: one command produces the week's work queue. - After a release, once at least a week of reader behaviour has accumulated. - When someone asks "which page should I rewrite first" and the honest answer is that nobody has compared the reports. - Before handing docs work to a contractor or a writer who needs a scoped list. Do **not** run it to discover a new class of defect. It ranks signals the system has already computed; it does not go looking for evidence of its own. ## Before you start Read `metrics/metric-dictionary.json` for every id in `metadata.measures`. The confounders there are not decoration — skipping them is how this skill produces a confident, expensive, wrong plan. Four things bite specifically here: - **Pages people leave from after succeeding are not defects, and the score already knows this.** The per-page he