agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/knowledge-structuring/skills/strength-scoring/SKILL.md

strength-scoring

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

SOP for assigning calibrated strength scores to claims — evaluate evidence weight, count independent sources, check defeaters, produce scored assessment.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Update claim page frontmatter with strength: <score> and strength-reasoning: <one-line>

    line 29
  2. Distinctive:

    Must provide explicit reasoning for the score.

    line 34

≈ “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

Strength Scoring

Assign a calibrated strength score (0-10) to a claim based on its evidential support.

Tool

vault_query_graph + CC reasoning

Protocol

  1. Query graph for all edges connected to the target claim
  2. Count and classify:
    • Supporting evidence (by quality: strong/moderate/weak)
    • Contradicting evidence (by quality)
    • Independent source count
  3. Apply scoring rubric:
    • 0-2: No evidence or only weak indirect support
    • 3-4: Some moderate evidence, significant contradictions
    • 5-6: Multiple moderate sources, few contradictions
    • 7-8: Strong direct evidence from independent sources
    • 9-10: Overwhelming convergent evidence, no undefeated contradictions
  4. Update claim page frontmatter with strength: <score> and strength-reasoning: <one-line>

HARD-GATE

<HARD-GATE> Must provide explicit reasoning for the score. A number without justification is not valid. </HARD-GATE>

Yield

Returns: { claim: string, score: number, supporting: number, contradicting: number, reasoning: string }

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