cad-adopt
Initialize .planning/ from a repo that already exists - PROJECT.md, REQUIREMENTS.md and a remaining-work ROADMAP.md derived from…
@crenshawdevInstall SkillDevelopment
Skill
/cad-suggest
Turn the run record into evidence-backed retune suggestions - each with its config key, the value in force, a direction and a target - and offer to route the ones you accept to /cad-config
Claude Code
$ npx -y skills add crenshawdev/cadence --skill cad-suggest --agent claude-code
Codex
$ npx skills add crenshawdev/cadence --skill cad-suggest -a codex -y
Cursor
$ npx skills add crenshawdev/cadence --skill cad-suggest -a cursor -y
Gemini CLI
$ npx skills add crenshawdev/cadence --skill cad-suggest -a gemini-cli -y
GitHub Copilot
$ npx skills add crenshawdev/cadence --skill cad-suggest -a github-copilot -y
OpenCode
$ npx skills add crenshawdev/cadence --skill cad-suggest -a opencode -y
Windsurf
$ npx skills add crenshawdev/cadence --skill cad-suggest -a windsurf -y
SKILL.md
cad-suggest.SKILL.mdname: cad-suggest description: "Turn the run record into evidence-backed retune suggestions - each with its config key, the value in force, a direction and a target - and offer to route the ones you accept to /cad-config" argument-hint: "[phase]" allowed-tools: - SlashCommand
<objective> The retune the run record supports, read back to you: every tweak under a heading of its own carrying its config key, the value in force, the direction to move it and the target where the record prices one, with the receipts that ask for nothing kept separate below. Every figure comes from `planning.mjs trace suggest` - this command relays the record, it never recomputes it and it writes no config key itself. It ends by offering to route the tweaks you accept to `/cad-config`, which is where a write would happen. No argument spans the whole record; a phase number scopes it. </objective>
<execution_context> @${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/suggest.md </execution_context>
<process> Execute end-to-end. </process>
Ships withcadence
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.
834 skills30 agents
Stars on GitHub
Momentum
- stars in total
- 8
Other skills on cadence.
@crenshawdevInstall Skillcad-assumptions-analyz…
Role contract preloaded at spawn by the cad-assumptions-analyzer, cad-assumptions-analyzer-low, cad-assumptions-analyzer-medium,…
@crenshawdevInstall Skillcad-audit
Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both directions, a…
@crenshawdevInstall Skillcad-capture
Capture a phase-linked todo, a seed idea for a future milestone, or a note, without losing your place - .planning/CAPTURE.md, or…
@crenshawdevInstall Skillcad-config
Configure Cadence's config.json - workflow toggles, the per-role model and effort interview, and interactive cross-model review…
@crenshawdevInstall Skillcad-context
Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one pass
@crenshawdevInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about cad-suggest.
- Which coding agents can use cad-suggest?
- cad-suggest installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.