Hook-enforced development discipline for Claude Code. Skills teach methodology (TDD, debugging, verification, SDD); hooks enforce compliance (git gates, branch protection, test evidence); store survives compaction.
Plugin proctor from marketplace nalyk-skills in nalyk/nalyk-skills. Commands read from the repo's manifest — yesterday.
brainstormingUse before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores intent, requirements and design before implementation.
dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
executing-plansUse when executing an implementation plan yourself in the current session — your human partner chose inline execution, or no subagent tool is available
finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to integrate work
receiving-code-reviewUse when receiving code review feedback — requires technical rigor and verification, not performative agreement
requesting-code-reviewUse when completing tasks, implementing features, or before merging to verify work
subagent-driven-developmentUse when executing implementation plans with independent tasks in the current session
systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
test-driven-developmentUse when implementing any feature or bugfix, before writing implementation code
using-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing plans
using-proctorUse when starting any conversation — establishes skill discovery, enforcement hooks, and the rule that skills precede action
verification-before-completionUse when about to claim work is complete, fixed, or passing — evidence before assertions always
writing-plansUse when you have a spec or requirements for a multi-step task, before touching code
writing-skillsUse when creating new skills, editing existing skills, or verifying skills work before deployment
Multi-model adversarial debate. Claude defends positions against external CLI models (agy/Gemini, Codex, Mistral Vibe) in parallel rounds. Refuses to run Claude-only; outputs consensus, tradeoff documents, or ADRs.
2 skills · 3 commands · 4 agents
Deterministic SEO analysis: Python engine (98 atomic checks) with multi-page crawler, real CWV via PageSpeed, optional GSC data, link graph/PageRank, auto-fix generation, and audit history with regression detection. One orchestrator skill plus 7 specialist agents.
1 skill · 7 agents
Dr. House engineering persona plus four diagnostic protocol skills: critic (code autopsy), architect (system design), visual (UI/CSS/accessibility), core (algorithms/concurrency). Each protocol triggers on its own noun domain.
5 skills
Philosophical reasoning engine for engineering decisions and code reviews: 63 principles (0-62) from 20 philosophers, via /organon, /organon:decide, /organon:review.
1 skill · 3 commands · 1 agent
Audit commands: /jobs-audit (design simplification), /carlin-audit (BS detection), /vibe-audit (engineering quality), /multi-audit (parallel run + synthesis).
4 commands
Decompose a task into parallel subagent workstreams via /orchestrate, /parallel, /plan-only
1 skill · 3 commands
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.