Audits pitch documents for factual accuracy against research dossiers.

Install

mkdir -p .claude/skills/audit-pitch && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16757" && unzip -o skill.zip -d .claude/skills/audit-pitch && rm skill.zip

Installs to .claude/skills/audit-pitch

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Cross-check every factual claim in output/<name>/pitch.html against the sourced lines in research/companies/<name>.md, write AUDIT-<name>.md classifying each claim (BACKED / UNVERIFIED / NO BACKING), and end with a SEND-READY or NEEDS-MY-REVIEW verdict. Use when the user runs /audit-pitch <company name> or asks to audit/verify a pitch artifact.
346 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Extract factual claims from `pitch.html`
  • Cross-check claims against `research/companies/<kebab-name>.md`
  • Classify claims as BACKED, UNVERIFIED, or NO BACKING
  • Verify numerical figures for exact matches
  • Generate an audit report `AUDIT-<kebab-name>.md`

How it works

The skill reads a pitch document, extracts factual claims, and cross-references them against a company dossier to classify each claim's backing and generate an audit report with a verdict.

Inputs & outputs

You give it
A company pitch in `output/<kebab-name>/pitch.html` and its dossier in `research/companies/<kebab-name>.md`
You get back
An audit report `AUDIT-<kebab-name>.md` with a SEND-READY or NEEDS-MY-REVIEW verdict

When to use audit-pitch

  • Audit pitch factuality
  • Verify business pitch data
  • Check pitch vs dossier

About this skill

audit-pitch

Usage: /audit-pitch <company name>

Audit the pitch artifact against its dossier. You are checking the pipeline's honesty, not improving the pitch. Do not edit pitch.html. Do not silently fix anything. If a file is missing (no pitch, no dossier), stop and report which one — that is the failed stage.

Procedure

  1. Read output/<kebab-name>/pitch.html and extract every factual claim — any statement about the company (metrics, customers, funding, tech, quotes) or about the market. Skip: candidate self-descriptions from PROFILE.md/placeholders, rhetorical framing, and the proposal itself ("I'd build X" is an offer, not a claim — but any company-fact embedded in it counts).
  2. Read research/companies/<kebab-name>.md. For each extracted claim, find the dossier line that backs it and classify:
    • BACKED — matches a dossier line that carries a source URL. Record the URL.
    • UNVERIFIED — matches a dossier line explicitly marked UNVERIFIED. (This is a rule violation: UNVERIFIED claims must not appear in pitches — flag it.)
    • NO BACKING — no dossier line supports it. Hallucination risk. Flag loudly. Include the exact quoted sentence from the pitch.
  3. Also check numbers: a claim counts as BACKED only if the figure in the pitch matches the dossier figure exactly (no rounding up, no "over X" inflation of "X").

Output — AUDIT-<kebab-name>.md in the repo root

# AUDIT: <Company>

Audited: <date> | Pitch: output/<kebab-name>/pitch.html | Dossier: research/companies/<kebab-name>.md

## Claims fully backed (N)
| # | Claim (as written in pitch) | Source URL |

## Claims marked UNVERIFIED in dossier (N)   ← must be 0 for SEND-READY
| # | Claim | Dossier line |

## Claims with NO BACKING (N)   ← hallucination risks, must be 0 for SEND-READY
| # | Exact pitch quote | Why nothing in the dossier covers it |

## Placeholder status
PROFILE.md present: yes/no. {{PLACEHOLDER}} slots remaining in pitch: N.

## VERDICT: SEND-READY | NEEDS-MY-REVIEW
<one line of reasoning>

Verdict rules

  • SEND-READY only if: zero UNVERIFIED claims in the pitch, zero NO-BACKING claims, and zero {{PLACEHOLDER}} slots remaining.
  • Otherwise NEEDS-MY-REVIEW, with the blocking items named in the verdict line.
  • Placeholders alone (all claims clean) still force NEEDS-MY-REVIEW — an artifact with placeholders is not sendable.

When not to use it

  • When the task is to fix issues in the `pitch.html` directly

Limitations

  • The skill does not edit `pitch.html` or silently fix any issues.
  • The skill focuses on factual claims and their backing, not rhetorical framing.

How it compares

This skill automates the factual verification of a pitch against a source dossier, providing a structured audit report, which is more rigorous than a manual review.

Compared to similar skills

audit-pitch side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
audit-pitch (this skill)01moNo flagsIntermediate
literature-review5592moReviewAdvanced
openalex-database488moReviewIntermediate
market-research-reports388moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

literature-review

K-Dense-AI

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

5591,298

openalex-database

davila7

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

48202

market-research-reports

davila7

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.

38162

scientific-brainstorming

davila7

Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.

37155

exa-search

benjaminjackson

Search the web for content matching a query with AI-powered semantic search. Use for finding relevant web pages, research papers, news articles, code repositories, or any web content by meaning rather than just keywords.

9106

scientific-critical-thinking

davila7

Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.

1888

Search skills

Search the agent skills registry