agentsclimarketplace
Sign in

Evidence research

Skill BaoBao1996121/crazy-harness/.agents/skills/evidence-research

Collect independent browser evidence and produce a machine-validated cited report.From its SKILL.md

Install
npx -y skills add BaoBao1996121/crazy-harness --skill evidence-research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

0.9 KB, 139 tokens by cl100k_base, as published. Nobody here has run it

Evidence Research Method

  1. Read source metadata before opening any page.
  2. Open at least two independent allowlisted sources through the browser tool.
  3. Treat returned evidence IDs as facts; never invent an identifier.
  4. Use the canonical citation form [source:<source_id>#<evidence_id>] next to supported claims.
  5. Write Recommendation, Findings, Risks, and Sources sections to report.md.
  6. Run research.report.validate and copy its report hash and citation list exactly into the final artifact.

The allowed-tools field is a workflow hint, not authority. ToolPolicy, approval, Ledger, budget, and CompletionGate remain authoritative.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.