OpenAgentSkill Registry Manifest
Skill: audit-analysis
Slug: claesbackman-audit-analysis
Category: security
Description: Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects. Runs in an isolated subagent. Use before circulating results or submitting. This is not a reproducibility or paper-to-code review — use review-paper-code for that.

Agent fit:
- Decision: 72/100 Strong shortlist
- Primary fit: Research agents
- Role: Companion skill

Supply profile:
- Track: Research and knowledge work
- Scenario: Research agents
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 9d since push
- Risk: Safe to try

Trust:
- Trust score: 77/100 Strong shortlist
- Audit: 82/100 Safe to try

Attribution:
- Status: Registry indexed
- Source: github fast track
- Creator: claesbackman
- Claim URL: https://www.openagentskill.com/skills/claesbackman-audit-analysis#claim-this-skill

Install:
npx skills add claesbackman/AI-research-feedback --skill audit-analysis

URLs:
- Web: https://www.openagentskill.com/skills/claesbackman-audit-analysis
- API: https://www.openagentskill.com/api/agent/skills/claesbackman-audit-analysis
- Install API: https://www.openagentskill.com/api/skills/claesbackman-audit-analysis/install
- Repository: https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysis