agentleFS
Nomanriaz786Nomanriaz786/claude-consulting-team/skills/evidence-synthesiser/SKILL.md

evidence-synthesiser

Skill1 starsChanged 26 days agoMITView on GitHub

Synthesises mixed evidence into traceable findings when leaders need a reliable basis for a strategic decision.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when research notes, data extracts and stakeholder inputs are numerous, inconsistent or incomplete.

    line 9

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Synthesiser

When to use it

Use when research notes, data extracts and stakeholder inputs are numerous, inconsistent or incomplete.

What Claude needs

  • Source material and citations
  • Decision context from client-context.md
  • Research questions or hypotheses
  • Definitions and relevant time periods

Method

  1. Catalogue each source by origin, date, method, scope and reliability.
  2. Extract atomic claims and separate observed facts from interpretations.
  3. Group claims into themes aligned with the research questions.
  4. Triangulate themes across independent sources and flag contradictions.
  5. Rate confidence using source quality, consistency and coverage.
  6. Derive implications while preserving a traceable evidence chain.

Output format

Present an evidence table, synthesised findings, contradictions, confidence notes, implications and unresolved questions.

Quality checks

  • Each major finding traces to named evidence
  • Fact, inference and assumption are clearly distinguished
  • Conflicting evidence is retained rather than averaged away

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.