agentleFS
yogsoth-aiyogsoth-ai/knowledge-structuring/skills/synthesis-report/SKILL.md

synthesis-report

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

SOP for producing argument synthesis reports — aggregate evidence, resolve contradictions, identify surviving claims, write structured summary.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

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

    Write wiki/topics/<topic-slug>-synthesis.md with sections:

    line 24
  2. Very specific:

    Add addresses edges from synthesis page to relevant question pages

    line 29
  3. Distinctive:

    Must categorize ALL claims for the topic — no claim left unclassified.

    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

Synthesis Report

Produce a synthesis report that identifies which claims survive scrutiny.

Tool

vault_query_graph + vault_graph_stats + CC file write

Protocol

  1. Query graph for all claims and evidence in the target domain
  2. Classify claims by survival status:
    • Survived: strength ≥ 7, no undefeated contradictions
    • Contested: strength 4-6, active contradictions with comparable evidence
    • Undermined: strength ≤ 3, or defeated by stronger contradicting evidence
  3. For each contested claim, summarize the state of the debate
  4. Write wiki/topics/<topic-slug>-synthesis.md with sections:
    • Surviving claims (high confidence)
    • Contested claims (ongoing debate)
    • Undermined claims (low confidence / refuted)
    • Remaining gaps (claims lacking sufficient evidence either way)
  5. Add addresses edges from synthesis page to relevant question pages

HARD-GATE

<HARD-GATE> Must categorize ALL claims for the topic — no claim left unclassified. Synthesis is comprehensive or it is not synthesis. </HARD-GATE>

Yield

Returns: { topic: string, survived: number, contested: number, undermined: number, gaps: number }

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.

Reviews can't be read right now.

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.