agentleFS
Sign inStart free
f0909172434f0909172434/rigorgraph/skills/capture-claim/SKILL.md

capture-claim

Skill1 starsChanged 4 months agoMITView on GitHub

Capture a research claim and its scoped supporting evidence in a RigorGraph project. Use when recording a theorem target, literature result, empirical observation, benchmark result, synthesis, source, dataset, computation, proof packet, or human review.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read rigorgraph.yaml, current claims, evidence, and verifications.

    line 8
  2. Very specific:

    Create evidence JSON first and run rigorgraph evidence add.

    line 13
  3. Very specific:

    When the input is a versioned RigorGraph evidence bundle, preserve it with rigorgraph evidence import BUNDLE.json --claim CLAIM_ID instead …

    line 14
  4. Very specific:

    Run rigorgraph audit. If it fails, report the exact issue codes and leave the epistemic status unchanged.

    line 15
  5. Distinctive:

    Use localized result headings:

    line 17
  6. Distinctive:

    Do not invent a locator, digest, author, verifier, experimental condition, or dependency.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Capture a claim

  1. Read rigorgraph.yaml, current claims, evidence, and verifications.
  2. Reply in the explicit or configured language: English, Traditional Chinese, Simplified Chinese, or Japanese. Keep claim statements, quotations, formulas, identifiers, and source titles in their original language.
  3. Classify the claim as formal, literature, empirical, benchmark, or synthesis.
  4. State the exact scope. For a source, record its URI and precise locator. For a local artifact, record a project-relative path and SHA-256 digest.
  5. Classify each evidence record as proof, source, dataset, computation, benchmark_run, or human_review. Never relabel numerical evidence as proof.
  6. Create evidence JSON first and run rigorgraph evidence add. Then create a DRAFT or PROPOSED claim JSON and run rigorgraph claim add.
  7. When the input is a versioned RigorGraph evidence bundle, preserve it with rigorgraph evidence import BUNDLE.json --claim CLAIM_ID instead of rewriting producer metadata. Bundle hashes record observed bytes; they do not prove producer identity, runner authenticity, or correctness.
  8. Run rigorgraph audit. If it fails, report the exact issue codes and leave the epistemic status unchanged.

Use localized result headings:

enzh-TWzh-CNja
Claim recorded已記錄命題已记录命题主張を記録しました
Evidence class證據類別证据类别証拠区分
Supported scope支持範圍支持范围支持される範囲
Remaining gap剩餘缺口剩余缺口残るギャップ

Do not invent a locator, digest, author, verifier, experimental condition, or dependency.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free