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.
Install
npx skills add TalonT-Org/AutoSkillit --skill audit-claimsgit 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-claimsPersonal 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 definitionDetails
- Skill name
audit-claims- Repository
- TalonT-Org/AutoSkillit
- 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
Analyze Prs
5TalonT-Org/AutoSkillit
Analyze all open PRs targeting a base branch — determine merge order, identify file overlaps, and tag each PR as simple or needs_check for complexity. Use at the start of a PR consolidation workflow.
Arch Lens C4 Container
5TalonT-Org/AutoSkillit
Create C4 Container architecture diagram showing static structure, building blocks, and technology choices. Anatomical lens answering "How is it built?
Arch Lens Concurrency
5TalonT-Org/AutoSkillit
Create Concurrency architecture diagram showing parallel execution patterns, thread pools, synchronization, and barriers. Physiological lens answering "How does parallelism work?
Generate Report
5TalonT-Org/AutoSkillit
Synthesize experiment results into a structured research report in the research/ folder. Supports --inconclusive flag.
User Activity Report
5npow/claude-skills
Use when researching what someone has been working on, getting up to speed on a colleague's recent activity, or preparing for a 1:1. Trigger phrases: what has X been working on, catch me up on X, person report, activity report for X, what's X been up to.
Resolve Claims Review
5TalonT-Org/AutoSkillit
Fetch claim findings from audit-claims, run citation-aware intent validation (ACCEPT/REJECT/DISCUSS), apply targeted citation fixes, escalate findings requiring experiment reruns, and post inline replies.
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.