experiment-audit
This Agent Skill runs deterministic, receipt-backed audits over agent-run experiments (AutoDiscovery outputs or CodeScientist directories), checking reported numbers against printed output, statistical validity (Benjamini–Hochberg correction, power analysis), and detecting hard-coded results or unused components. It triggers on audit requests like "check the AutoDiscovery results" or "validity audit" and verifies nine audit criteria (A1–A7, R1–R5) spanning reproducibility, statistical rigor, and experimental integrity.
Install
Installs via the community skills CLI (works with Claude Code and other agents).
Source: https://github.com/Anuja-Khatri/consilience-ai2/tree/HEAD/plugins/consilience-audit
What it's made of
1 skill
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (Anuja-Khatri).