pressure-test
Skill15 starsChanged 5 months agoMITView on GitHub
Use when the user wants an existing plan attacked rather than built, they have a roadmap, plan, PRD, bet, or strategy and want you to find what's wrong with it before they commit. Triggers on any adversarial-critique intent: tear it apart, find the holes, poke holes, play devil's advocate, stress-test, pressure-test, challenge the assumptions, what are we missing / not seeing, where will this break, why might this fail, talk me out of this, red-team it. The defining signal is skeptical scrutiny of a decision the user is about to make. Surfaces thin evidence, hidden or unexamined assumptions, wrong scope, and drift, then returns blocking issues, suggestions, strengths, and a ready/needs-fixes/not-ready verdict. Do NOT use for generating new ideas, brainstorming directions, writing or updating a plan/PRD/roadmap, or reviewing metrics and status updates, this only critiques something that already exists.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- captkernel/claude-thinking-toolstheir own version, first seen Oct 15, 2026
- justEstif/pi-shelftheir own version, first seen Oct 13, 2026
- ericthlai/skillstheir own version, first seen Sep 3, 2026
- tmoody1973/pressure-testtheir own version, first seen Aug 3, 2026
- naticorrea-03/claude-code-skillstheir own version, first seen Jul 1, 2026
- daniil2711/pressure-testtheir own version, first seen Jun 22, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- SanketSapkal/founder-skills★ 10same name
- naticorrea-03/claude-code-skills★ 4same name
- tmoody1973/pressure-test★ 2same name
- AmmarHassona/pressure-test★ 0same name
- captkernel/claude-thinking-tools★ 0same name
- daniil2711/pressure-test★ 0same name
- ericthlai/skills★ 0same name
- justEstif/pi-shelf★ 0same name
- robmcquade/claude-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 repository13 other files it gives its agents.
- calibrateSkill
- critiqueSkill
- decision-readinessSkill
- design-testSkill
- discover-sourcesSkill
- drift-checkSkill
- gather-evidenceSkill
- prioritize-backlogSkill
- scorecardSkill
- startSkill
- synthesizeSkill
- to-build-briefSkill
- write-briefSkill
The file
Files
Pressure Test
Adversarial review of an existing plan, roadmap, PRD, bet, or strategy, find what's wrong before the user commits. This is critique pointed at a whole artifact: it runs the same independent adversarial engine, so there is one critic, not two.
Workflow
- Take in the artifact and its supporting evidence/scores from
.product-eval/<scope>/. - Run
critiqueon it: the multi-lens panel (skeptical customer, competitor, CFO, engineer, contrarian, security) plus thecritic-checklist.mdchecks (evidence→solution, solution→ship, cross-stage consistency) and a scope-mode recommendation (Expand / Hold / Reduce). Run it independently (a fresh-context subagent; a different model if available) so it does not rubber-stamp. - Hunt counter-evidence and force hidden assumptions into the open; check that metrics are not vanity and that success criteria are falsifiable.
- Terminate each point as resolved / open (→ a gap routed to
gather-evidence) / contested (→ logged dissent), never argue to consensus.
Output
Blocking issues (with fixes), suggestions, strengths, a scope-mode call, and an overall ready / needs fixes / not ready verdict. Append the findings to .product-eval/<scope>/decisions-log.md. Lead with the verdict and the blocking issues. End with Next move: and recommend fixing the blockers, writing the decision memo, making the build brief, or using critique if the artifact is only a finding/problem statement rather than a full plan.
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.