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-docs-verify
Verify docs claims against the live codebase - paths, commands, symbols, config keys - each reported accurate, stale or unverifiable. Reports; it does not rewrite docs
Claude Code
$ npx -y skills add crenshawdev/cadence --skill cad-docs-verify --agent claude-code
Codex
$ npx skills add crenshawdev/cadence --skill cad-docs-verify -a codex -y
Cursor
$ npx skills add crenshawdev/cadence --skill cad-docs-verify -a cursor -y
Gemini CLI
$ npx skills add crenshawdev/cadence --skill cad-docs-verify -a gemini-cli -y
GitHub Copilot
$ npx skills add crenshawdev/cadence --skill cad-docs-verify -a github-copilot -y
OpenCode
$ npx skills add crenshawdev/cadence --skill cad-docs-verify -a opencode -y
Windsurf
$ npx skills add crenshawdev/cadence --skill cad-docs-verify -a windsurf -y
SKILL.md
cad-docs-verify.SKILL.mdname: cad-docs-verify description: "Verify docs claims against the live codebase - paths, commands, symbols, config keys - each reported accurate, stale or unverifiable. Reports; it does not rewrite docs" argument-hint: "[path or glob | defaults to README + docs/]" allowed-tools: - Read - Grep - Glob - AskUserQuestion
<objective> Catch documentation that has drifted from the code - the failure that quietly misleads every new reader of a distributed project. Extract the checkable claims from the target docs and test each against the actual repo, then report each as accurate, stale, or unverifiable.
This is the docs-verifier engine only; the doc WRITER is collapsed out (DESIGN §2). cad-docs-verify never rewrites a doc - it produces the findings a human (or a later edit) acts on. </objective>
<execution_context> @${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/docs-verify.md </execution_context>
<process> Run the verify workflow end-to-end. Only claim `stale` when the code actually contradicts the doc; when a claim cannot be checked mechanically, mark it `unverifiable` rather than guessing. Do not edit any doc. </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-docs-verify.
- Which coding agents can use cad-docs-verify?
- cad-docs-verify 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.