caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Ten evidence-aware discovery motions with a human decision at every gate. Each skill labels what is actual data, inferred, estimated or unknown, and stops before anything gets built.
Plugin dlab from marketplace ai-augmented-discovery-lab in deanpeters/AI-Augmented-Product-Discovery-Lab. Commands read from the repo's manifest — 1 month ago.
dlab-step01-market-intelUse for “what is changing in this market?” Turn a scope and partial notes or sources into a Market Intelligence Brief to choose where to investigate; no demand proof.
dlab-step02-segmentUse for “how big could this be?” Turn a possible segment and notes into a Segment Selection Brief with TAM/SAM/SOM populations and potential dollars; estimates are not sales forecasts.
dlab-step03-personaUse for “who has this problem?” Turn a role, situation and notes into a Situational Persona with jobs, pains, gains and problem framing; synthetic people are not customer evidence.
dlab-step04-opportunity-solution-treeUse to explore a solution request. Turn a person, outcome and partial notes into an Opportunity Solution Tree of needs, options and tests; explore branches before selecting a winner.
dlab-step05-value-prop-differentiationUse for “why would customers choose and pay?” Turn ideas, alternatives and notes into a Value Prop vs. Differentiation 2x2; compare customer payoff without claiming proven savings or a moat.
dlab-step06-positioning-statementUse to explain why a concept is worth choosing. Turn customer, need, concept and alternative notes into a Positioning Statement to test; a promise is not purchase evidence.
dlab-step07-solution-hypothesisUse for “what must be true?” Turn an idea and partial context into a Solution Hypothesis with small tests and a decision rule; a plan is not validation.
dlab-step08-storyboardUse to show a person solving a problem. Turn story notes or a hypothesis into a six-frame Storyboard to critique or test; a fictional happy ending is not observed success.
dlab-step09-minimum-viable-narrativeUse for “turn this story into a builder prompt.” Turn notes into a Minimum Viable Narrative with 3–6 internal action–response pairs; describe a test, not production requirements.
dlab-step10-prototypingUse for “how could we find out this is wrong?” Turn an assumption and constraints into a Prototype Experiment Brief for the smallest brutal-truth test; no automatic build or invented results.
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.