/cad-config
Configure Cadence's config.json - workflow toggles, routing stakes, and interactive cross-model review-provider setup (live model detection + per-tier assignment)
$ npx -y skills add crenshawdev/cadence --skill cad-config --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/cad-config
Context preview
The summary Claude sees to decide when to auto-load this skill.
Configure Cadence's config.json - workflow toggles, routing stakes, and interactive cross-model review-provider setup (live model detection + per-tier assignment)
The failure that costs you is the one that looks like success: generated code that is present, plausible, and wired to nothing. Cadence is a planning and execution system for Claude Code built around refusing to let that pass.
Repo: crenshawdev/cadence
Other skills on cadence.
- /cad-assumptions-analyzer-contract
Internal role contract, preloaded into every cad-assumptions-analyzer rung agent. Not a user command.
Open skill - /cad-audit
Pre-ship requirement-traceability audit - every requirement traced to a phase, a plan, and a verification; orphan detection both directions; a FAIL gate that catches silently-dropped requirements before a milestone ships
Open skill - /cad-capture
Capture without losing your place - an actionable phase-linked todo (the queue mem-* lacks), a seed idea for a future milestone, or a note. One file: .planning/CAPTURE.md, which the builtin memory backend makes recallable at planning time
Open skill - /cad-context
Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one conversational pass
Open skill - /cad-coverage
Find which of a completed phase's requirements have zero failing-capable test coverage, then generate tests to close the gaps - using the project's own test framework, not a fixed one
Open skill - /cad-debug
Systematic debugging - scientific method with hypothesis state persisted across /clear, and a user-gated second-model consult at dead-ends. Single pass, no session-manager layer
Open skill