assumption-audit
Skill4 starsChanged 49 days agoMITView on GitHub
Extract every assumption hidden in a claim, plan, or belief, classify each by load-bearingness and testability, and identify which single assumption would collapse the whole structure if false. Use when a plan feels solid but untested, or before committing to a decision built on unexamined premises.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Walsworth-Group/physkittheir own version, first seen Nov 8, 2026
- opelpleple/meta-skillstheir own version, first seen Oct 11, 2026
- kalshamsi/fable-discipline-skillstheir own version, first seen Oct 8, 2026
- Natan-Mohart/24-strategy-skills-for-claudetheir own version, first seen Aug 8, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- Natan-Mohart/24-strategy-skills-for-claude★ 41same name
- Walsworth-Group/physkit★ 7same name
- kalshamsi/fable-discipline-skills★ 0same name
- opelpleple/meta-skills★ 0same 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 repository48 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/AGENTS.mdAGENTS.md
- .agents/skills/assumption-audit/AGENTS.mdAGENTS.md
- .agents/skills/decision-matrix/AGENTS.mdAGENTS.md
- .agents/skills/direct-setup/AGENTS.mdAGENTS.md
- .agents/skills/direct-verify/AGENTS.mdAGENTS.md
- .agents/skills/first-principles-thinking/AGENTS.mdAGENTS.md
- .agents/skills/percolate-kb/AGENTS.mdAGENTS.md
- .agents/skills/percolate-reading/AGENTS.mdAGENTS.md
- .agents/skills/phase-final-reviewer/AGENTS.mdAGENTS.md
- .agents/skills/phase-implementer/AGENTS.mdAGENTS.md
- .agents/skills/phase-orchestrator/AGENTS.mdAGENTS.md
- .agents/skills/phase-reviewer/AGENTS.mdAGENTS.md
- .agents/skills/plan-kb/AGENTS.mdAGENTS.md
- .agents/skills/pr-cleanup/AGENTS.mdAGENTS.md
- .agents/skills/query-kb/AGENTS.mdAGENTS.md
- .agents/skills/question-forge/AGENTS.mdAGENTS.md
- .agents/skills/reclaim-disk-space/AGENTS.mdAGENTS.md
- .agents/skills/refresh-kb/AGENTS.mdAGENTS.md
- .agents/skills/riff/AGENTS.mdAGENTS.md
- .agents/skills/save-pdf-kb/AGENTS.mdAGENTS.md
- .agents/skills/save-url-kb/AGENTS.mdAGENTS.md
- .agents/skills/write-phase-plan/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- kb/AGENTS.mdAGENTS.md
- personal-website/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- decision-matrixSkill
- direct-setupSkill
- direct-verifySkill
- first-principles-thinkingSkill
- percolate-kbSkill
- percolate-readingSkill
- phase-final-reviewerSkill
- phase-implementerSkill
- phase-orchestratorSkill
- phase-reviewerSkill
- plan-kbSkill
- pr-cleanupSkill
- query-kbSkill
- question-forgeSkill
- reclaim-disk-spaceSkill
- refresh-kbSkill
- riffSkill
- save-pdf-kbSkill
- save-url-kbSkill
- write-phase-planSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
5
Distinctive
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 8
Use this skill to surface and stress-test the premises hiding inside a claim, plan, or belief.
- Distinctive: line 25
Load: if this is false, does the plan break entirely, degrade, or barely notice?
- Distinctive: line 34
Use this concise structure unless the user asks otherwise:
- Distinctive: line 59
Do not pad the register with trivially safe assumptions to look thorough.
- Distinctive: line 60
If everything checks out, say so — the audit passing is a valid result.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Assumption Audit
Use this skill to surface and stress-test the premises hiding inside a claim, plan, or belief. Most plans fail not at the visible steps but at an assumption nobody wrote down.
Purpose
Every plan is a conclusion resting on premises, most of them implicit. An assumption audit makes the full list explicit, sorts it by how much weight each premise carries and how cheaply it can be tested, and names the keystone — the single assumption whose failure takes the whole structure down. This converts vague confidence into a concrete testing agenda.
Procedure
- State the claim, plan, or belief being audited.
- Extract assumptions exhaustively. Look in these categories:
- Factual: things believed true about the world
- Causal: "doing X will produce Y"
- People: what others want, know, or will do
- Continuity: "current conditions will persist"
- Capability: "we can execute this part"
- Definitional: the framing of the problem itself
- For each assumption, rate:
- Load: if this is false, does the plan break entirely, degrade, or barely notice?
- Confidence: how strong is the actual evidence (not the felt certainty)?
- Testability: can this be checked cheaply, expensively, or only in hindsight?
- Identify the keystone: highest load × lowest confidence.
- Propose the cheapest test for the keystone and the top 2–3 risky assumptions.
- State what the plan looks like if the keystone fails — is there a fallback?
Output format
Use this concise structure unless the user asks otherwise:
## Claim / plan under audit
...
## Assumption register
| # | Assumption | Category | Load | Confidence | Testability |
|---|---|---|---|---|---|
| 1 | ... | Causal | Breaks plan | Low | Cheap |
## Keystone assumption
...
## Cheapest tests
- ...
## If the keystone fails
...Guardrails
- Include at least one definitional assumption — the framing of the problem is always an assumption.
- Rate confidence by evidence, not by how long the assumption has been held.
- Do not pad the register with trivially safe assumptions to look thorough; focus on the load-bearing ones.
- If everything checks out, say so — the audit passing is a valid result.
Canonical questions
- "We're about to spend 6 months building this feature — sanity-check the plan."
- "My startup thesis is that restaurants will pay for X."
- "I'm planning to move to Austin for the lower cost of living."
- "Our hiring plan assumes we close the Series A by Q3."
- "I believe my best customers come from word of mouth."
Poor fits: decisions already made and irreversible (use inversion for damage control instead), and pure preference questions with no factual premises.
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.

