Pmf
Armor for coding agents: a playbook of Claude Code skills that make an agent prove its work, not describe it.
npx -y skills add yiyaw-lab/agent-armor --skill pmfAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
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.
SKILL.md
1.5 KB, as published. Nobody here has run it
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.