Audit Claims

Parallel subagent-driven claim extraction and citation integrity audit for research PRs. Extracts claims by section, matches against available evidence, classifies unsupported claims as findings, and emits a verdict for recipe routing.

5 stars 1 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill audit-claims
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/audit-claims ~/.claude/skills/audit-claims

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Audit Claims Skill

Perform a two-phase citation integrity audit on an open GitHub research PR using
parallel subagents. Phase 1 extracts claims by report section; Phase 2 matches
each claim against available evidence and generates findings. Posts inline review
comments and emits a verdict for recipe routing.

## Arguments

`/autoskillit:audit-claims <worktree_path> <base_branch> <pr_url>`

- **worktree_path** — Absolute path to the research worktree (skill derives
  `feature_branch` from `git rev-parse --abbrev-ref HEAD` inside it)
- **base_branch** — The base branch the PR targets (e.g., "main")
- **pr_url** — Explicit PR URL passed by the recipe (avoids re-discovering the PR)

## When to Use

- Called by the research recipe orchestrator after `review_research_pr`
- Both read-only gates complete before any resolution step begins
- Can be invoked standalone to audit citation integrity for any open research PR

## Critical Constraints

**NEVER:**
- Create files outside `{{AUTOSKILLIT_TEMP}}/audit-claims/`
- Approve a PR that has `changes_requested` findings
- Post review comments when `gh` is unavailable — output `verdict=approved` and exit 0
- Review files outside the PR diff — scope all audit to diff content only
- Modify any source code
- Run deterministic diff annotation (claim positions are report-level, not line-level)
- Generate findings for `experimental` claims — they are self-evidencing by definition
Read the full skill on GitHub

Details

Skill name
audit-claims
Path
src/autoskillit/skills_extended/audit-claims/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Audit Claims skill do?

Parallel subagent-driven claim extraction and citation integrity audit for research PRs. Extracts claims by section, matches against available evidence, classifies unsupported claims as findings, and emits a verdict for recipe routing.

How do I install the Audit Claims skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill audit-claims. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Audit Claims popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.