Productivity plugins

Apply the official EU Icons to AI-generated or AI-modified content, following Article 50(4) of the EU AI Act.

39 skills

A concise, spec-driven coding-agent workflow for Claude Code, Cursor, Grok, and Codex—adapted to your stack instead of copied by hand.

23 skills · 10 commands · 2 agents · hooks

Release-assurance evidence toolkit — 2 pillars (testing, liveness) + security transversal with its own runner, plus governance (DORA/DER metrics, stage gates, traceable receipts). Migrated quality-evidence commands from make-no-mistakes with shims.

24 skills · 12 commands

Agentic development framework for Claude Code — disciplined workflow routing, TDD enforcement, safety hooks, systematic debugging, and code review

32 skills · 2 agents · hooks

code-kb-powered development workflow skills. Fork of Superpowers with explicit code-kb integration.

32 skills · 1 agent · hooks

A coordinated product team as 33 skills: 23 role perspectives, an 8-skill delivery pipeline, a router that picks the right role, squad or workflow, and a Project Point of Truth practice for durable product knowledge. Includes a gate-enforcement hook; the optional CLAUDE.md routing brain is installed separately with install.sh.

33 skills · hooks

Agent memory layer with recall, reflect, consult, bullpen, and cross-agent coordination. Includes health monitoring and auto-wake. Hooks wire legion into every session automatically.

10 skills · 10 commands · 12 agents · hooks

Private financial research powered by the fo CLI.

28 skills · 5 agents

Eleven author personas (Hemingway, McCarthy, Didion, Baldwin, Morrison, McPhee, Wallace, Orwell, King, Le Guin, Vonnegut) plus Gottlieb the editor — prose craft and editorial work.

16 skills · 16 agents

Heli-Harness workspace governance for Codex.

31 skills · hooks

A gate-driven, evidence-traceable workflow for mathematical modeling contests, from problem framing to final paper audit.

32 skills

Take a product from a raw idea to a scaffolded codebase: structured discovery, schema-locked PRDs, agent-friendly tech stack selection, safe bootstrap, and brownfield assessment. Worktree-aware and safe to run inside an existing repo — shaping notes are shared across worktrees and never committed to host git history.

30 skills

Agent skills I use day-to-day with GitHub Copilot CLI and other coding agents.

30 skills

Opinionated developer-session workflow. Encodes one coherent session from first message to merged branch as a deterministic pipeline of skills that hand off to each other in a fixed order. 21 skills, 2 subagents, session-start hook, iron-law enforcement for TDD / systematic-debugging / verification / design-driven-development / accessibility-verification.

21 skills · 3 commands · 3 agents · hooks

Reusable AI agent skills for Codex, Claude Code, GitHub Copilot, and other Agent Skills-compatible tools.

28 skills

German finance and accounting assistant for HGB bookkeeping, SKR04 account mapping, journal entries, financial statements, tax checks, pension evaluation, real estate readiness, retirement projections, capital allocation, and integrated personal finance advisory.

11 skills · 14 commands · 2 agents

Manage Zilliz Cloud clusters and Milvus vector databases from Claude Code

24 skills · 2 commands

Claude Code, with receipts. Plans with you, hands each task to a specialist agent, and keeps a session from calling work done until a verification is logged. Its hooks run in every session, a guard holds destructive shell commands for review, and setup can point your status line at OMCA.

14 skills · 10 agents · 1 MCP server · hooks

Shared project memory, on-demand teams of specialist agents that talk to each other and verify each other's work, a searchable library of skills, commands and rules, and an end-of-task report that asks before applying changes.

25 skills · hooks

Every task gets an issue, a branch and a PR; every project gets defaults sized to its complexity.

24 skills · 1 agent · hooks

4 agent types, Core 10 phase skills (1 router + 9 phase), five-phase spine (Define → Plan → Build → Review → Ship). Pre-merge gate (check-work status, CI, review reports, R4 security + adversarial pass) catches integration issues before ship.

20 skills · 4 agents · hooks

Ticket-anchored AI development for Linear, JIRA, and GitHub Issues, built on one idea: stop slop before it goes in, instead of reviewing it out afterwards. Work starts from a ticket, not a prompt. Claude writes failing tests for what the ticket requires — not for what the code already does — then implements against a written scope boundary and asks before wandering outside it. Nothing merges without a simplify pass over the uncommitted diff and an adversarial review that checks every finding against the real code, and each ticket keeps a durable plan, findings, and progress log outside the repo so a fresh session resumes where the last one stopped. Preventing slop does not mean working alone. The same guarantees scale to a fleet: :design interviews you into a PRD, :tickets cuts an adversary-approved ticket tree from it, and :run drives parallel headless agents — one per ticket, each isolated in its own git worktree — toward that tree, across four model tiers where every tier's work is checked by the tier above it, with frozen-test tamper checks, independent handoff verification before any branch is integrated, and a human gate at each stage boundary. Eighteen commands in all — more details at https://github.com/iansmith/slopstop

19 skills · 5 agents

Full-stack web application delivery platform. Orchestrates requirements, architecture review, frontend (FDS), backend (Koa + PostgreSQL), build verification, testing, code review, and deployment across a team of specialist agents.

13 skills · 10 agents · 1 MCP server

Lucas's engineering stack: evidence, clear writing, and portable workflows.

23 skills · hooks

Full SDLC orchestration with 21 agents (harness, analyst, scaffolder, implementer, deployer, documenter, QA coordinator, 9 QA reviewers incl. cloud compliance, RAI reviewer, release manager) and 24 skills covering code quality, security, architecture, testing, scaffolding, and AWS/GCP/Azure cloud patterns.

24 skills

Lucas's engineering stack: evidence, clear writing, and portable workflows.

23 skills · hooks

Code Engine ACE - Intelligent pattern learning with continuous auto-search for Claude Code. Learns from your coding sessions and automatically surfaces relevant strategies, code snippets, APIs, and pitfalls as you work. v8.2.4. Requires: Claude Code >= 2.1.311, ace-cli >= 4.4.2 (pinned in package.json; @ace-sdk/core >= 3.8.2), Python >= 3.10 for the fallback hooks. Windows not supported (WSL2 works). Full changelog: https://github.com/ce-dot-net/ce-ai-ace/releases

22 commands · hooks

Backlog, planning and parallel-round skills for Claude Code; /rota:rota-install fetches the matching rota binary.

22 skills · hooks

Production documentation for an app you built, in a fixed layout modelled on Harvester: subject-first directories and a Docusaurus site whose navigation is the filesystem. Every page declares both what it is and who it is for, with sections from The Good Docs Project and quality checks from the ISO/IEC/IEEE 26514 characteristics: type mixing, alt text, heading order, and reading grade measured against that page's own reader. Extracts the reference material, anchors every claim to a file and line, measures drift against a recorded manifest, and refuses to state what it could not check.

11 skills · 4 commands · 6 agents

Portable AI skills for Fulcrum app building, integrations, mapping, queries, access, and migrations

21 skills