pmf
Skill1 starsChanged 5 months agoMITView on GitHub
Alias for /ground — the demand-evidence gate on the build decision. Binds every product bet to real demand evidence (revealed-&-costly > specific-stated > vanity proxy) and REFUSES to license a build on anything weaker than specific stated demand: defaults to UNKNOWN/PUSH and ships the cheapest test that would settle it. Stops craft drifting into impressive-but-unwanted. Modes: <bet|product> (extract + falsify + verdict) | audit | apply.
In this repository33 other files it gives its agents.
- architecture-blueprintSkill
- burnSkill
- calm-ui-auditSkill
- capitalizeSkill
- cardSkill
- commit-mineSkill
- continuity-contextSkill
- elonizeSkill
- frontierSkill
- full-throttleSkill
- grade-sessionSkill
- groundSkill
- harmonizeSkill
- harvestSkill
- honeSkill
- milkSkill
- mirrorSkill
- moonwalkSkill
- nightshiftSkill
- page-auditSkill
- postSkill
- promptSkill
- publishSkill
- razeSkill
- redlineSkill
- relaySkill
- snipSkill
- stashSkill
- tasteSkill
- tidySkill
- untilSkill
- vacationSkill
- vaultSkill
The file
Files
<!-- mirror:transform — intentional divergence: private path + prediction-infra references genericized -->Alias for /ground. Follow the ground skill (ground/SKILL.md) exactly — same modes (<bet|product> | audit | apply), same evidence-hierarchy refusal criterion (PULL ≥ Tier-1, vanity caps at UNKNOWN, cite-or-declare-UNKNOWN), same falsification + founder-bias guard, same gates-and-grades enforcement (verdict gates ship via /redline; each bet emits a falsifiable demand-prediction to your prediction ledger), same propose-on-approval + PUSH-caught/prediction-hit-rate metric.
Why two names: ground is the self-documenting verb — keep the product grounded in real demand, do not float on proxy and conviction (a cold reader infers the method). pmf is the recognizable term for the goal it serves (product-market fit). Use whichever reads truer; they run the identical procedure.
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.