caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Domain discovery and RDFS/OWL modeling workflow: elicitation, variation exploration, formalization, round-trip validation, decision logging.
Plugin domain-workbench from marketplace driky-claude-plugins in Driky/driky-claude-plugins. Commands read from the repo's manifest — 1 month ago.
decision-logUse whenever a domain decision is made during conversation — whenever the user answers "is X valid?" or resolves a variation. Records the decision in ontology/decisions.md. Cheap to invoke, should be used constantly.
domain-elicitationUse when the user wants to explore and describe domain use cases before formalizing. Guides Socratic questioning, use case capture, and gap detection. Does NOT write ontology code.
domain-formalizationUse when the user wants to turn elicited use cases and decisions into RDFS/OWL vocabulary. Enforces RDFS-first discipline, justification-required axioms, and marked assumptions.
domain-workflowUse at the start of a working session, or whenever the user is unsure what to do next. Orchestrates the other domain skills — inspects project state, proposes the next step, and walks the user through the flow. Does not do elicitation, formalization, or review itself.
ontology-instantiationUse after formalization to validate the model. Writes captured use cases back as concrete instances (Turtle individuals) and reports where the story and the model disagree.
ontology-reviewUse when the user asks to review, audit, or clean up the ontology. Covers assumption audit, orphan elements, over-formalization check, and competency question coverage.
variation-explorationUse when the user wants to stress-test captured use cases for variations — different actors, parameters, flows, errors, cardinalities, time. Produces a variation matrix and new open questions.
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.