cad-adopt
Initialize .planning/ from a repo that already exists - PROJECT.md, REQUIREMENTS.md and a remaining-work ROADMAP.md derived from the code and the git history
Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends
$ npx -y skills add crenshawdev/cadence --skill cad-debug --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cad-debugContext preview
The summary Claude sees to decide when to auto-load this skill.
Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends
name: cad-debug description: "Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends" argument-hint: "[list | status <slug> | continue <slug> | --diagnose] [symptom]" allowed-tools: - Read - Write - Edit - Bash - Grep - Glob - AskUserQuestion
<objective> Debug a symptom by the scientific method - form hypotheses, run the cheapest discriminating test for each, confirm a root cause, fix it, verify the symptom is gone. The investigation is persisted to `.planning/debug/<slug>.md` after every step, so a `/clear` or a new session resumes it losslessly. At a genuine dead-end (repeated failed fixes, exhausted hypotheses), OFFER a second-model consult (references/consult.md) - user-gated, decision-support only.
Routing: parse `$ARGUMENTS` per the workflow's Route table (debug.md) - `list`, `status <slug>`, `continue <slug>`, `--diagnose`, else a new symptom. The table lives in the workflow, once. </objective>
<execution_context> @${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/debug.md </execution_context>
<process> Route on `$ARGUMENTS`, then run the debug workflow single-pass end-to-end. Persist the state file after every hypothesis test and fix attempt. Never auto-loop fixes and never auto-consult - both are deliberate, and the consult is always user-gated. </process>
Appearance is cheap. Verification is the work. Cadence is for developers using Claude Code on software they will still own after the session ends. Claude can write a convincing plan, produce working code, and tell you the job is finished.
Repo: crenshawdev/cadence
Initialize .planning/ from a repo that already exists - PROJECT.md, REQUIREMENTS.md and a remaining-work ROADMAP.md derived from the code and the git history
Internal role contract, preloaded into every cad-assumptions-analyzer rung agent. Not a user command.
Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both directions, a FAIL gate before shipping
Capture a phase-linked todo, a seed idea for a future milestone, or a note, without losing your place - .planning/CAPTURE.md, or --cadence for friction with…
Configure Cadence's config.json - workflow toggles, the per-role model and effort interview, and interactive cross-model review provider setup
Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one pass