All authors
crenshawdev avatar

Claude Skills by crenshawdev

github.com/crenshawdev
34 skillsA× 340 installs12 views
Cad AdoptA

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

ai-agentsbashgit
0
4
Cad Assumptions Analyzer ContractA

Internal role contract, preloaded into every cad-assumptions-analyzer rung agent. Not a user command.

ai-agentsgonode
0
4
Cad AuditA

Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both directions, a FAIL gate before shipping

ai-agentsbash
0
4
Cad CaptureA

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 Cadence itself

developmentgoshell
0
4
Cad ConfigA

Configure Cadence's config.json - workflow toggles, routing stakes, and interactive cross-model review provider setup

ai-agentsbash
0
4
Cad ContextA

Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one pass

ai-agentsbash
0
4
Cad CoverageA

Find a completed phase's requirements with no failing-capable test coverage and generate tests to close the gaps, in the project's own framework

ai-agentsbash
0
4
Cad DebugA

Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends

ai-agentsgobash
0
4
Cad Decision ReviewA

Adversarial refute-then-adjudicate pass over one load-bearing decision - a CONTEXT D-NN line or a PROJECT Key Decisions row - with per-objection rulings

ai-agentsbashapi
0
4
Cad Docs VerifyA

Verify docs claims against the live codebase - paths, commands, symbols, config keys - each reported accurate, stale or unverifiable. Reports; it does not rewrite docs

ai-agentsbashdocumentation
0
4
Cad ExecuteA

Execute a phase's plans - a subagent per plan, an atomic commit per task, a slim per-phase SUMMARY

ai-agentsbash
0
4
Cad Executor ContractA

Internal role contract, preloaded into every cad-executor rung agent. Not a user command.

developmentrustgo
0
4
Cad HealthA

Planning-health check - .planning's core docs present, the STATE cursor, ROADMAP and REQUIREMENTS parseable and consistent. Not a traceability audit (that is /cad-audit)

ai-agentsrustbash
0
4
Cad HelpA

Cadence's own help - the command reference for every /cad-* skill, grouped by cluster; pass a command name for just that entry

ai-agents
0
4
Cad LandA

Land finished work - report git state, then ask the mechanism (push / MR or PR / tag / leave local). Never decides how you publish

ai-agentsgobash
0
4
Cad MilestoneA

Cut a milestone - audit that nothing was dropped, tag when the project tags, prune completed phases from the roadmap, evolve PROJECT and refresh REQUIREMENTS

ai-agentsbashgit
0
4
Cad Minimalism ReviewA

Ranked delete-list over code that works and should not exist - reinvented stdlib, one-implementation abstractions, dead flexibility, config nobody sets

ai-agentsgobash
0
4
Cad New ProjectA

Initialize a project through deep questioning - PROJECT.md, REQUIREMENTS.md, a phased ROADMAP.md and .planning/ state

ai-agentsbash
0
4
Cad PauseA

Pause work cleanly - a WIP commit of in-flight changes plus a STATE cursor set to paused with a one-line resume pointer (/cad-progress offers to resume it)

ai-agentsgobash
0
4
Cad PhaseA

CRUD phases in ROADMAP - add, insert, remove, edit, with remove/insert renumbering the following phases, their .planning dirs and every phase reference

ai-agentsbashgit
0
4
Cad Plan Checker ContractA

Internal role contract, preloaded into every cad-plan-checker rung agent. Not a user command.

ai-agentsgorails
0
4
Cad Plan ReviewA

On-demand adversarial plan review of a phase PLAN.md before code - for a hand-written, imported or just-edited plan (/cad-plan fires this itself)

ai-agentsbash
0
4
Cad PlanA

Create an executable phase plan (PLAN.md) - planner subagent, optional check gate, plan review trigger

ai-agentsbash
0
4
Cad Planner ContractA

Internal role contract, preloaded into every cad-planner rung agent. Not a user command.

developmentgoshell
0
4
Cad ProgressA

Project progress - count-based status from files and git, finds incomplete or paused work and offers to resume it, --stats for a quick summary

ai-agentsbashgit
0
4
Cad ReportA

Render a phase's run record as a receipts narrative - what each dispatch cost, what the gates caught, what got refuted - straight from trace.jsonl and the phase artifacts

ai-agentsgobash
0
4
Cad Reviewer ContractA

Internal role contract, preloaded into every cad-reviewer rung agent. Not a user command.

ai-agentsrustgo
0
4
Cad SpikeA

Spike - a time-boxed experiment resolving one unknown before you bet on it, risk-first, with a validated | invalidated | inconclusive verdict

ai-agentsbashapi
0
4
Cad SuggestA

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

ai-agentsbash
0
4
Cad TaskA

Execute a small off-roadmap task with atomic commits - inline by default, --plan for multi-step work

ai-agentsbash
0
4
Cad UndoA

Safely undo a phase - roll back its commits from the SUMMARY manifest, revert (or --no-commit to re-do), and reset the phase status

ai-agentsbashgit
0
4
Cad Verifier ContractA

Internal role contract, preloaded into every cad-verifier rung agent. Not a user command.

developmentrustgo
0
4
Cad VerifyA

Verify a completed phase by conversational UAT - a persistent checklist that survives /clear, plus cross-phase and goal-backward passes

ai-agentsgobash
0
4
Cad WhyA

Why is this code like this - a git-log chain over one file[:line], joined to the phase, task, decision, deviation and review record on disk

ai-agentsbashnode
0
4