From pagekit
Runs skeptical claim-check audits on PageKit first-page drafts at light/normal/hard severity to validate claims, catch slop, and produce corrected versions before publishing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pagekit:pagekit-claim-checkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are running the optional durability pass on a first-page draft.
You are running the optional durability pass on a first-page draft.
./references/prompt.md./references/framework.md — claim-check flag types, severity calibration, principle./references/template.md../pagekit/references/anti-slop.md — the slop pattern catalogruns/<run-name>/first-page-draft.mdruns/<run-name>/proof-map.mdnormal.Invoke the pagekit-claim-checker subagent (agents/pagekit-claim-checker.md). Pass:
The subagent runs read-only, produces the audit, and writes:
runs/<run-name>/claim-check.md — the audit (flagged lines, types, rewrites, recurring patterns)runs/<run-name>/first-page-draft-corrected.md — the corrected draft (only if any line was rewritten)Use scripts/claim-check.sh <draft> <proof-map> --severity <severity> to expand the canonical prompt for paste. Save outputs to the same paths.
working-log.md with the severity used, count of flags by type, and any recurring patterns.../pagekit/references/anti-slop.md (or strengthen the existing entry) and to ../pagekit-page-argument-shape/references/template.md's drafting-constraints list. The framework absorbs what the claim-check kept catching.A strong claim-check pass:
Do not stop at claim-check. Continue:
runs/<name>/evaluation.md — the run's own honest read of what worked, what stayed thin, where outputs drifted generic.pagekit-evaluator-pass to produce the adversarial second read.runs/<name>/working-log.md has real entries per step (replace all scaffold *[Fill in]* placeholders).pagekit-run-check — it must return tier: FULLY LOGGED or tier: PUBLISHABLE before the run is done.npx claudepluginhub hnshah/pagekit --plugin pagekitValidates that draft sections cover all claims from PRECIS.md before review. Prevents review of incomplete drafts.
Detects AI voice patterns, reviews prose quality with Strunk & White principles, analyzes readability metrics, audits consistency, and validates SEO in content drafts before publication.
Generates a point-by-point verification checklist from a draft article, categorizing claims by type (statistical, biographical, legal) and specifying required evidence. Useful before publication, editing, or legal review.