メニュー
Verify claims in a session/PR/transcript against on-disk reality. Produce a verification report (verified / false-positive / false-negative / partial) with explicit owners. STOP at verification — do not execute remediation without explicit approval.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Set up Cloudflare Turnstile end-to-end in a project: scan the codebase, create the widget via the Cloudflare API, deploy the managed siteverify Worker, write the frontend snippets, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form from bots, or fix a Turnstile integration. Mirrors developers.cloudflare.com/turnstile/spin.
Four-phase protocol for clearing accumulated drift between memory claims, CLAUDE.md citations, and on-disk reality. Detects stale citations, missing files, and orphan plans; classifies findings; emits proposed diffs; codifies prevention. Companion to closeout (closeout discovers orphans; this skill polishes them). Discovery ≠ remediation — Phase 3 emits proposed diffs only; constitutional doc edits require explicit conductor authorization.
Ingest a corpus of session logs (JSONL transcripts, chat exports) and extract a persona profile — vocabulary frequency, unique idioms and coinages, structural analogies — then synthesize an ideal_yearning and archetypal_pattern and append the result to a {persona_id}.lexicon.yaml. Triggers on "extract persona", "build a lexicon", "map the domain language", or any request to process conversation logs into a voice/vocabulary model.
Apply narratological scoring to a text, transcript, or recording transcript — rating contiguous spans for pathos, logos, ethos, kairos, and density — then extract the single highest-scoring contiguous block as the work's Natural Center, with a scoring table and justification. Triggers on "find the natural center", "extract the most dramatic moment", "what's the strongest passage", or pulling the peak block from a long artifact for a short, excerpt, or trailer.
Transform any data, document, deck, README, manifest, config, or report by (1) extracting every piece of dynamic information — names, links, statistics, costs, identifiers, dates, thresholds — into configurable variables instead of hard-coding, and (2) enforcing that every factual assertion carries at least two independent citations. Triggers on "remove branding," "make this reusable," "transmute this," "parametrize," "no hard-coded values," "configurable," "needs citations," "verify these claims," or any request to convert a one-off artifact into a parameterized template.
Scan rough markdown, session exports, or pasted prose and isolate each core intent into a structured prompt atom — classified as law, value, directive, constraint, question, or branch-vector — then rewrite it into machine-readable YAML frontmatter per the RAW → CLEANED/FORMALIZED → ELEVATED doctrine. Triggers on "prompt atom extraction pass", "atomize this", "formalize these prompts", or converting loose operator text into registry-grade atoms.
| name | qa-audit |
| description | Verify claims in a session/PR/transcript against on-disk reality. Produce a verification report (verified / false-positive / false-negative / partial) with explicit owners. STOP at verification — do not execute remediation without explicit approval. |
| license | MIT |
