agentleFS
45ck45ck/research-literature-review-skills/.claude/skills/evidence-strength-scorer/SKILL.md

evidence-strength-scorer

Skill4 starsChanged 8 months agoMITView on GitHub

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer matrices, theme groupings, claim-evidence structures, and explicit comparison criteria.

    line 49
  2. Distinctive:

    Keep facts, synthesis, and speculation distinct.

    line 50
  3. Distinctive:

    Do not confuse summary volume with analytical depth.

    line 55
  4. Distinctive:

    Do not treat all sources as equally credible or equally relevant.

    line 56
  5. Distinctive:

    Do not fabricate consensus where the literature is mixed or thin.

    line 57
  6. Distinctive:

    Do not hide exclusion reasons, scope limits, or methodological weaknesses.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

evidence-strength-scorer

Purpose

Assess the weight and credibility of evidence behind claims in the literature.

Trigger this skill when

  • You are doing literature review, related work, comparative research, or evidence-driven design.
  • The user needs structured research outputs instead of scattered notes or ad hoc summaries.
  • You need traceable justification for claims, gaps, methods, or future directions.

Expected inputs

  • selected papers
  • claim set or themes
  • quality criteria
  • context of use

Deliverables

  • evidence strength ratings
  • confidence notes
  • high-risk claim list

Operating procedure

  1. Clarify the research objective, boundary, and decision the output is meant to support.
  2. Distinguish source evidence from inference, synthesis, or speculation.
  3. Produce the skill-specific artifact in a structured, reusable form.
  4. Preserve source-to-theme, theme-to-gap, or claim-to-evidence traceability where relevant.
  5. Recommend the next best handoff instead of collapsing the whole literature workflow into one output.

Quality gates

  • The output is scoped to the actual research question rather than generic background.
  • Contradictions, uncertainties, and evidence limitations are surfaced explicitly.
  • The structure is reusable in a report, review, appendix, or research memo.
  • The synthesis adds value beyond a paper-by-paper summary.

Handoff targets

  • critical-analysis-writer
  • related-work-synthesizer
  • future-work-generator

Output style

  • Prefer matrices, theme groupings, claim-evidence structures, and explicit comparison criteria.
  • Keep facts, synthesis, and speculation distinct.
  • Preserve traceability from conclusions back to sources or evidence buckets.
  • Surface missing evidence and unresolved questions instead of smoothing them over.

Failure modes to avoid

  • Do not confuse summary volume with analytical depth.
  • Do not treat all sources as equally credible or equally relevant.
  • Do not fabricate consensus where the literature is mixed or thin.
  • Do not hide exclusion reasons, scope limits, or methodological weaknesses.

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.