surface-assumptions
Skill504 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
- ahmadrishi/agentic-mahoragatheir own version, first seen Nov 1, 2026
- yogsoth-ai/de-anthropocentric-research-engineword for word, first seen Sep 25, 2026
Other versions2 projects use a version of this.
Word for word · 1
- yogsoth-ai/de-anthropocentric-research-engine★ 505100% same
Edited · 0
None found.
Wrote their own version · 1
- ahmadrishi/agentic-mahoraga★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository270 other files it gives its agents.
- abstract-structureSkill
- adjudicate-exchangeSkill
- adjust-abstraction-scopeSkill
- adversarial-deliberationSkill
- aggregate-rankingSkill
- analogical-discoverySkill
- analyze-constraints-readinessSkill
- analyze-experiment-resultsSkill
- analyze-future-scenariosSkill
- analyze-heterogeneitySkill
- analyze-interventionSkill
- analyze-leaderboard-dynamicsSkill
- analyze-patent-citation-networkSkill
- analyze-scaling-regimeSkill
- analyze-temporal-trajectorySkill
- apply-perturbationSkill
- apply-question-frameworkSkill
- apply-separation-principleSkill
- apply-stage-gateSkill
- apply-veto-filterSkill
- appreciative-reframeSkill
- assess-construct-validitySkill
- assess-evidence-saturationSkill
- assess-goal-feasibilitySkill
- assess-patent-claim-scopeSkill
- assess-patent-legal-statusSkill
- assess-prior-art-and-claimsSkill
- assess-problem-wickednessSkill
- assess-publication-biasSkill
- assess-question-qualitySkill
- assess-ranking-consistencySkill
- assess-readiness-dimensionSkill
- assess-removabilitySkill
- assess-sensitivitySkill
- assess-system-boundarySkill
- assumption-stress-testSkill
- atomize-claimSkill
- atomize-conceptSkill
- attach-evidence-to-relationSkill
- audit-benchmark-validitySkill
- audit-convergence-independenceSkill
- audit-data-contaminationSkill
- audit-explanatory-compressionSkill
- audit-reporting-qualitySkill
- audit-structural-equivalenceSkill
- audit-structure-consistencySkill
- audit-study-validitySkill
- audit-validator-independenceSkill
- biologize-problemSkill
- biomimetic-transferSkill
- build-concept-fanSkill
- build-current-reality-treeSkill
- build-domain-ontologySkill
- build-failure-chainSkill
- build-noncircularity-matrixSkill
- calibrate-adversarial-confidenceSkill
- calibrate-probability-forecastSkill
- canonicalize-entitySkill
- categorize-evidenceSkill
- challenge-assumptionSkill
- The first 60 shown.
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
- Distinctive: line 36
Every assumption has a type, explicit/implicit status, evidence assessment, and criticality rating.
- Distinctive: line 38
Do not replace enumeration with a generic risk paragraph.
≈ “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.
Files
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
- Parse the artifact into claims, dependencies, conditions, and unstated background requirements.
- Enumerate assumptions and classify each as explicit or implicit and by type.
- Attach supporting or contradicting evidence and rate assumption strength and criticality.
- 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
| source | physical line | kind | source criterion |
| stress-test/key-assumptions-check | 11 | gate | Enumerate all assumptions, classify them, and assess evidence strength and criticality. |
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
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.

