Workflow plugins

Installs Charter, Craft and TARS together and wires them up in one pass. The one-command way in.

4 skills

Passphrase-based session handoff: write one note before /clear or a tool switch, resume by name in Claude Code, Codex, Gemini CLI, Antigravity, Cursor or any AGENTS.md-aware tool.

3 skills · hooks

Sinecure recruiting & platform skills, bundled natively.

4 skills

(pt-BR) Auditoria antes de subir: o diff da branch é auditado em arquitetura (guia do projeto), segurança, boas práticas da stack e ponytail, com critérios embutidos e contraprova adversarial; nos repositórios que versionam `.auditoria-pre-subida`, um hook bloqueia PR, merge e push na base sem veredito aprovado. Qualquer projeto, só Claude Code.

1 skill · 2 agents · hooks

Keeps the engineer in the architect seat: Claude implements, you decide.

3 skills · hooks

Session handoff and parallel fan-out planning for Claude Code. The handoff skill owns a durable RUNBOOK.md (inline packets, durable writes, rolling checkpoints with recorded review verdicts, resume); the slice skill cuts work into conflict-free, agent-sized partitions with a dependency-ordered wave plan and a pre-launch grilling gate. Works standalone or alongside conductor-okf.

2 skills · 2 commands

A backlog-to-branch task protocol, as four skills: /task:init, /task:task, /task:next-task and /task:clean-tasks.

4 skills

Delivery conventions for the gosleep harness — Jira+GitHub epic/task workflow, PRD authoring, handoff protocol.

4 skills

Build Compass workflows and agents and operate the compass CLI with Claude.

3 skills

Multi-story evidence gate, investigation protocol, verification grounding, early-stop guard, per-task routing.

1 skill · 1 command · hooks

Cross-repo working conventions for a one-person shop: shipping through PRs, and reporting from unattended cloud runs.

2 skills · 1 command

Triage each Claude Code session into per-session learnings, then consolidate them into stable principles.

2 commands · hooks

A multi-agent 'CTO' for Claude Code: plans work, classifies risk, routes to 12 specialist agents, enforces quality gates, runs testing automation + real-browser QA, and reports with proof. A generic, updatable engine + a per-project config generated by /project-cto:init.

1 skill · 2 commands

Clay & Claude guardrails — hooks for precision, redirection, and workflow discipline

1 skill · 1 command · hooks

Multi-model peer debate (claude + opencode + codex...) and a reusable backend-session abstraction

3 skills

All of BiswaViraj's agent workflows: reviewloop (clear every PR reviewer), ciloop (drive failing CI to green), standup (daily standup from your PRs).

3 skills

Parallel subagent dispatch framework and honest execution standards

2 skills · 1 command

Plays a cat meow sound when Claude Code finishes a turn or wants attention (Stop and Notification hooks). Drop your own .mp3/.wav into assets/ to override the bundled meow.

2 skills · hooks

Steps 1, 3 and 5 of the graphwing human loop: grilling, to-spec, to-tickets

3 skills

Code review workflows — CodeRabbit, multi-model review, and TDD.

3 skills

A Diretriz GZero: voce decide O QUE, a IA decide O COMO e executa. Comandos /diretriz:novo, /diretriz:adotar e /diretriz:atualizar instalam o template (CLAUDE.md + .projeto/) em qualquer pasta. Inclui o Design System GZero como sugestao visual opcional.

3 commands

One Playwright MCP daemon per machine instead of one per session — each session gets its own tabs, logins flow between sessions automatically, and the browser-profile contention between parallel sessions disappears. Registers the server itself, keeps the daemon up from a hook, installs a login service.

1 skill · 1 MCP server · hooks

Universal brainstorming with 5 modes and 3 design templates

3 skills

Structured prompt engineering: guides users step-by-step through a 6-phase framework to build high-quality, reusable prompts

1 skill · 1 command · 1 agent

Review skills for code, tests, and documentation. Finds code design and correctness, coverage, and doc-structure issues that linters miss.

3 skills

Skills for researching, deciding, and enforcing: create-research records a question investigated with per-finding confidence and cited sources, create-adr writes Architectural Decision Records (ADRs) as standalone, append-only policy in MADR format that cite the research they rest on, and review-policy checks code changes against accepted ADRs.

3 skills

End-of-day, end-of-session and agent-handover wrap skills: reconcile the Obsidian dashboard and prune git at day end; extract learnings for the next session; write a vault handover an agent with no context can act on

3 skills

Human-on-the-Loop(HOTL)開発ワークフローの設計・適用と、AIネイティブな開発運営のCTO判断支援。リポジトリ引き継ぎ・開発フロー構築、品質ゲート/CI/CD/evalゲートの段階導入、自律性の昇格判断、J-SOX/監査対応

3 skills

個人開発プロダクトの機会発見、需要検証、海外・多言語向けLPの設計、ローンチ、集客、定着、ユニットエコノミクス。証拠台帳と事前に宣言した判定ルールで進める

3 skills

Autonomous coding loops that keep Claude working until real completion criteria are met

3 skills