Developer Tools plugins

A spec-driven, two-track agentic workflow: design track, delivery track with parallel implementers in worktrees, independent review and verification, and a dev to main release model.

26 skills

Go code-quality skills covering errors, concurrency, interfaces, generics, testing, and modules

25 skills

Planning, standup, grooming, RFC, ADR, change advisory board, steering committee, sign-off, retrospective and a self-auditing compliance audit - performed by real agents, recorded by hooks, around every request.

15 commands · 9 agents · hooks

Core operating skills for coding agents: plan execution, TDD, debugging, spec workflow, handoff, subagent protocol, security review, git discipline — plus safety hooks, subagent roles and the `at` CLI that seeds downstream repos.

18 skills · 6 agents · hooks

Composable Code Codex: composition-first, pure-function-friendly code quality enforcement for TypeScript, JavaScript, Python, Go, and Rust. Orchestrates 21 check sub-skills covering boundaries, purity, immutability, typed errors, types, naming, tests, security, observability, and strategic DDD.

22 skills · 1 command · 1 agent · hooks

観点別マルチエージェントでコード変更・PR をレビューするプラグイン（Anthropic 公式 code-review とは別）

9 skills · 3 commands · 13 agents

テスト設計→環境構築→実施→報告→再テストを支援するプラグイン。コードレビューの差分テスト（deep-code-review）とは別

14 skills · 2 commands · 9 agents

Claude Code engineering workflows, safety reviews, and local memory tools

23 skills · 1 MCP server · hooks

Durable project memory and lifecycle checkpoints shared across coding agents.

9 skills · 13 agents · 1 MCP server · hooks

Route engineering work through worktrail-go, capture and consume handoff briefs, and drain the work queue unattended

18 skills · 5 commands · hooks

Pandahrms-specific skills: development workflow orchestration, spec writing, cross-project bridge, system setup, EF Core migrations, React web frontend conventions, code review, and commit workflow

23 skills · hooks

Task ledger, knowledge base, workbooks, artifact registry and cross-repo workflows

24 skills

Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fjall + LanceDB.

15 skills · 6 commands · 2 MCP servers · hooks

The shared foundation of the Han suite: the specialist agent roster the other plugins dispatch, the project-discovery skill with its project-scanner agent, and the canonical evidence and YAGNI rule files. The documentation skills live in han-documentation, the pre-planning research skills in han-research, the planning skills in han-planning, and the coding skills in han-coding; each depends on han-core.

2 skills · 22 agents

Claude, Codex, and you — reviewing each other's work. A bounded audit loop with a live two-lane view.

3 skills · 18 commands · 2 agents · hooks

Cairn brings all the important questions up to be decided upfront, so you can hand long-running execution to your agent confidently.

22 skills · 2 agents

My own skills.

19 skills · 4 agents · hooks

Official Expo skills for building, deploying, upgrading, and debugging Expo apps.

23 skills · 1 MCP server

The full collection in one install: context-audit + decision-ledger + did-it-land + epistemic (the usage entry) + evidence-locked-uat + gauntlet + health + manifest + metacognate + open-questions + outsource + perspective + recon + resolve + triage + watch + write-goal.

17 skills · 5 agents · hooks

Rust authoring for compiler errors, design, domains, and code style.

22 skills · hooks

Drive the UsableNet AQA for Agents Chrome extension from your coding agent. Start QA sessions, run accessibility evaluations, summarize results, and export annotated HTML reports — with the AQA extension installed in the user's regular Chrome.

17 skills · 5 agents · 1 MCP server

Port of Cursor's pstack plugin for Claude Code: the poteto-mode router skill, its 21 engineering principles, and all 22 playbooks, adapted from Cursor-only infra to Claude Code primitives. Situational skills (how, why, arena, swarm, interrogate, unslop, ...) and the poteto-agent/Comment Sicko subagents are not yet ported.

22 skills

Integrate Ecart Pay with Claude Code using official docs and MCP

10 skills · 10 commands · 2 MCP servers

Software craftsmanship discipline skills: grill (the interview primitive — walk a design tree one question at a time, facts looked up by subagent rather than asked, no acting until shared understanding), grill-with-docs (that loop applied to vocabulary, against per-repo CONTEXT.md glossaries), diagnose, prototype, tdd, improve-codebase-architecture, grok (stateful multi-session codebase comprehension with supersession-aware understanding records), zoom-out (adapted in part from mattpocock/skills, MIT), infra-review (architecture/security review of Terraform+Atlantis PRs), quiz-me (opt-in active-recall comprehension check after a code explanation), interrogate-model (holistic representability review of a domain model — the legitimate scenarios and personas it cannot express), design-by-stories (design an artifact's shape — schema, template, data model, config — by modeling its actors and user stories first, then deriving the shape from the stories), and lucid-architecture-diagram (drive AWS cloud architecture diagrams in Lucid, including the two silent-failure modes of its API). derive-conventions (derive a repo's unwritten house style from its own code, adjudicate each inferred rule with the human, and write the approved set to CONVENTIONS.md so the review agents stop re-deriving it). wizard (author an interactive bash wizard that walks a human through the steps only they can perform — third-party dashboards, credentials, CI secrets, one-off cutovers — from a hardened template), resolve-conflicts (recover each side's intent from commits, PRs, tickets and NDR heads before resolving a merge, rebase, or jj conflict; detects git vs jj and follows that VCS's own mechanics), and wait-what (user-invoked: re-pitch a message that did not land, in Simplified Technical English using the repo's own vocabulary) — all three adapted from mattpocock/skills, MIT. screen-critique (critique a UI screen design in a fixed order — purpose against its neighbouring screens, then structure,

19 skills · 3 agents

Internal team workflows for CI, code review, shipping, local automation, and verification.

20 skills · 2 agents

An authenticated hosted MCP server that accesses your PlanetScale organizations, databases, branches, schema, and Insights data.

21 skills · 1 MCP server

The optional workflow bundle for awow: design and planning, meetings and retros, digests, strategy and OKRs, knowledge capture, and styled documents. Self-contained; expects a repo configured by awow's /setup-awow.

22 skills

Reusable Codex plugin and spec-driven engineering runtime with protected acceptance evidence

22 skills

WB plugin: deterministic worktree lifecycle, exact-head CI, and dedicated merger workflows for AI agents.

21 skills · 1 agent

HyperFrames by HeyGen. Write HTML, render video. Compositions, GSAP and runtime adapter animations, captions, voiceovers, audio-reactive visuals, and website capture for HyperFrames.

22 skills