AGENT SKILL

evidence-audit

Adversarial provenance audit of a draft deliverable before it ships — re-derive load-bearing claims at their sources, downgrade what fails. Use before publishing any client- or stakeholder-facing artifact containing numbers, ratings, prices, or "verified" language; or when the operator says "audit this", "check the claims", or "is this actually verified?"

License 许可
MIT
最近更新
2026-11-14
Stars
★ 2
Forks
0

01 前言 Front Matter

name
evidence-audit
description
Adversarial provenance audit of a draft deliverable before it ships — re-derive load-bearing claims at their sources, downgrade what fails. Use before publishing any client- or stakeholder-facing artifact containing numbers, ratings, prices, or "verified" language; or when the operator says "audit this", "check the claims", or "is this actually verified?"

03 SKILL.md 正文

Evidence Audit

Adversarial audit pass for outbound deliverables. The rule being enforced (working-style.md § Audit discipline): an artifact's claim to have been verified is not verification — and that applies to your own drafts most of all. Search-tool snippets are hearsay; a "verified" label you attached without fetching the source is self-attestation.

Procedure

Honor the request's scope throughout this pass. For an audit-only request, report the exact problem, its consequence, and the smallest remedy; do not rewrite the artifact. Apply corrections when the existing task authorizes editing, without asking again for authorization already given.

  1. Extract the load-bearing claims. Scan the draft for: prices/fees, ratings and review counts, statistics ("1 in 3...", "N% of..."), superlatives tied to numbers, and every instance of "verified / confirmed / checked directly / pulled directly." Load-bearing = a claim whose failure would change the recommendation or embarrass the sender. List them with locations.

  2. Trace each to its actual provenance — from the session transcript, not from memory. For each claim, answer: was the source page fetched in-session (WebFetch/browse-tool), or did this number arrive in a search-result summary? Who owns the domain it came from? Vendor self-comparisons and competitor "analyses" are marketing, not evidence — a competitor's stat about its rival is the same failure as the vendor's stat about itself.

  3. Re-derive what carries "verified" language. Fetch the source directly. Three outcomes:

    • Confirms → keep the label, note the fetch.
    • Contradicts → fix the claim, not the label.
    • Source blocks fetching (G2, Trustpilot 403s) → the claim cannot be labeled verified by anyone; downgrade to "search-corroborated," say the source blocks direct reads, and check whether the recommendation survives without the number. If it doesn't, the recommendation needs different footing.
  4. Check the deliverable's own confidence taxonomy against itself. If the doc promises "green = read at the source," every green tag must trace to a fetch in this session. A confidence system that lies on one row is worse than no confidence system.

  5. Hunt the cost/claim gaps. What does the draft imply is free, complete, or settled that isn't priced or checked? (Origin case: a "$0 to start" claim while the plan's only real recurring cost — video hosting — went unpriced.)

  6. Report findings and authorized corrections. Lead with what the evidence changes and why. In an authorized editing task, apply the corrections and retain conclusions only if the evidence still supports them. In an audit-only task, identify the required corrections and any conclusions that no longer hold.

Notes

  • forge-signal has a deterministic version of steps 1–2 as a pipeline role: src/pipeline/roles/fact-auditor.ts (claim extraction + provenance ledger). This skill is the full pass including re-derivation, which needs live fetches.
  • For client-facing artifact design provenance (palette/type grounded in the client's real brand), see forge-signal/scripts/harvest-brand.mjs.
  • Do not fabricate a fetch you didn't make. "I could not verify X" in the report is a valid, useful finding.

04 同仓库更多 Skills

nino-chavez
nino-chavez/agentic-ways-of-working

zoom-out

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

★ 2
nino-chavez
nino-chavez/agentic-ways-of-working

write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

★ 2
nino-chavez
nino-chavez/agentic-ways-of-working

triage

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

★ 2
nino-chavez
nino-chavez/agentic-ways-of-working

tdd

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

★ 2
nino-chavez
nino-chavez/agentic-ways-of-working

symbol-surgery

Symbol-first refactoring discipline using the native LSP tool — locate by symbol, check blast radius before changing, edit at symbol boundaries, verify references after. Use when renaming, changing a signature, moving/extracting/inlining, or deleting code that other code depends on; or whenever the question is "where is this used and what breaks if I change it?" Mechanical-execution complement to `deepen` (which decides what to refactor) and `simplify` (which decides what's clean).

★ 2
nino-chavez
nino-chavez/agentic-ways-of-working

ship

Deploy, release, or run migrations against production for a project. Use when user says "deploy", "ship", "push to prod", "release", "run the migration", "apply migrations", or asks how a project gets deployed / where it lives. Reads per-project DEPLOY.md as source of truth; falls back to inference + offer to scaffold one.

★ 2