agentleFS
yogsoth-aiyogsoth-ai/de-anthropocentric-research-engine/skills/surface-assumptions/SKILL.md

surface-assumptions

Skill505 starsChanged 52 days agoApache-2.0View on GitHub

Enumerate explicit and implicit assumptions in a claim, model, method, decision, or design.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every assumption has a type, explicit/implicit status, evidence assessment, and criticality rating.

    line 36
  2. Distinctive:

    Do not replace enumeration with a generic risk paragraph.

    line 38

≈ “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

surface-assumptions

Purpose

Enumerate explicit and implicit assumptions in a claim, model, method, decision, or design and expose their evidential status.

Input contract

required: [artifact, claim_or_decision, context]
optional: [causal_claims, evidence, stakeholder_views, assumption_taxonomy]
constraints: [separate explicit from implicit assumptions; preserve the artifact's wording; attach evidence strength and criticality to each assumption]

Procedure

  1. Parse the artifact into claims, dependencies, conditions, and unstated background requirements.
  2. Enumerate assumptions and classify each as explicit or implicit and by type.
  3. Attach supporting or contradicting evidence and rate assumption strength and criticality.
  4. Mark assumptions whose failure would change the conclusion and return the assumption register.

Output contract

produces: [assumption_register, evidence_assessments, critical_assumptions, dependency_notes]
delta_fields: [findings, evidence_updates, uncertainties, recommended_jumps]

Quality gates

  • Every assumption has a type, explicit/implicit status, evidence assessment, and criticality rating.
  • The register distinguishes load-bearing assumptions from decorative assumptions and preserves interaction effects when supplied.
  • Do not replace enumeration with a generic risk paragraph.

Parameterization

The caller must provide the artifact or claim, the context and intended conclusion, any known causal claims, the assumption taxonomy, evidence sources, and the rating scale for strength and criticality.

Failure and counterexamples

Reject when the artifact or conclusion is missing, assumptions are asserted without relation to the claim, or contradictory evidence is silently omitted.

Provenance map

  • concept: creative-ideation/assumption-surfacing
  • concept: deep-insight/assumption-enumeration
  • concept: convergence/assumption-extraction
  • resolved: stress-test/key-assumptions-check

Preserved source criteria ledger

sourcephysical linekindsource criterion
stress-test/key-assumptions-check11gateEnumerate all assumptions, classify them, and assess evidence strength and criticality.

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.