Development plugins

Build games in Unity with Claude Code: engine-idiomatic C#, project and asset structure, and in-editor work.

13 skills

状态机驱动的 AI 编码工作流引擎。任务编排、进度持久化、JSONL 日志、跨会话恢复、自动审查门控、系统化调试。

4 skills · 7 commands · 1 agent · hooks

Capture tasks inline with task:/fix:/todo:/plan: prefixes, store in SQLite, group work under plans, dispatch to subagents, and auto-generate changelogs.

1 skill · 12 commands

A change flow for OpenSpec repositories with one human gate at merge, bracketed by an explicit start and stop, plus drift checks that hold a specification to the code it claims to describe.

9 skills · 4 commands

Intelligent toolchain orchestrator for Claude Code — recommends skills, plugins, MCPs, and agents for any task with dependency-aware ordering. v0.5.1: dependency bump (@huggingface/transformers ^4.0.1 → ^4.1.0) + README polish. v0.5.0: architectural overhaul closing 10-finding audit. Hot-path hook 387→85 lines via lib/advisor-nudge-core extraction; 4 architectural guards CI-enforced (DI-1 module-load purity, DI-2 layered dependency direction, DI-3 manifest version coherence, vault env single source); module-scoped mtime+size cache for embeddings/graph; unified filesystem walker; 812 tests (+24% from 654). BREAKING (restorable): default prompt-length threshold 5→12 chars; restore via ADVISOR_PROMPT_LENGTH=5. Deprecation runway through 0.6.0 for SKILL_ADVISOR_VAULT (use SKILL_ADVISOR_VAULT_PATH) and build-index.inferCategory re-export.

3 skills · 7 commands · 2 agents · hooks

Claude Code Swiss Army Knife — diagnose, configure, and build your Claude Code environment. Meta-skill /cc with triage menu + 9 specialized skills for context audit, MCP, hooks, agents, prompts, security, setup, and skill building.

11 skills · 1 command · hooks

Check, draw, import, generate and compare MassTransit saga diagrams (*.saga.yaml) with the ariadne CLI.

13 skills

Workspace manager with colored terminals, git worktrees, and per-workspace Claude context

12 skills · hooks

Stacklist engineering kit: repo registry, Linear agent-ready standard, /ready, /orchestrate with FE/BE/MCP/contract builders, /verify, /ship-pr, /angles, FE/BE architecture reviewers, rule-enforcer hook.

6 skills · 7 agents

Spec-Driven Development for AI assistants — requirements, RFC-2119 specs, and ADRs with stable identifiers, machine-checked traceability, and the delivery pipeline that runs on them: workers, review into a findings file, close-out; two profiles.

8 skills · 4 agents · hooks

Agent skills for using the yggdryl package from Rust, Python and Node.js.

12 skills

Evidence-bound coding governance for Claude Code with skills, agents, hooks, and native slash workflows.

6 skills · 5 agents · hooks

Eitri Expert Front-End Developer — builds mobile-first Eitri-Apps with Luminus + Bifrost, drives them on Android devices and iOS simulators, connects to the Eitri Manager MCP, and clones live websites into Eitri views.

10 skills · 1 MCP server · hooks

Claude Code harness — Gate A~E process automation skills + hooks integration plugin

11 skills · hooks

Brief, run, verify, checkpoint. One durable spec per project; effort chosen at launch; fresh-context verification. Built from Anthropic's Fable 5.1 docs.

7 skills · 4 agents · hooks

Generate game assets (sprites, characters, weapons, backgrounds, UI, logos, thumbnails, music, video) with a CONCEPT-first AI workflow. Bundles the minigame-assets-mcp server, 3 slash commands, and an auto-triggered workflow skill.

7 skills · 3 commands · 1 MCP server · hooks

Seven scoped Go agents with skill allowlists and enforcement hooks.

1 skill · 2 commands · 7 agents · 1 MCP server · hooks

AI coding assistant for building Angular apps with Kendo UI for Angular. Covers component usage, layout, theming, icons, and accessibility.

11 skills · 1 MCP server

Test, validate, and benchmark performance of LSP servers using only YAML. Configs for benchmarks, response assertions, multi-file consistency checks, file-edit sequences, lifecycle tests, version comparisons, and LSP session management — restart per benchmark (cold) or reuse one initialized session across steps (warm).

12 skills

Ship something with Lovable, Replit, Bolt, v0, Claude Code, or Codex and it works, but nobody with an engineering background has checked it before real customers arrive. craft-audit reviews the whole project the way a senior engineer would, across ten areas: not just security, but the database rules that keep one customer's data separate from another's, whether the money path is tested, and whether errors get seen before a customer has to report them. Findings are plain language, ranked by real consequence, so a broken invoice check beats a missing comment, and written to a workspace in your project so a long audit can pause and resume. The companion skill craft-fix drives the repairs but can never mark its own work fixed; only a fresh audit pass confirms that. A full worked example is included, so you can see exactly what it finds before you run it. Not a penetration test, not continuous monitoring, no numeric score.

12 skills

Build mobile-native zero-knowledge proof apps with mopro (Circom, Halo2, Noir → iOS, Android, Flutter, React Native, Web)

5 skills · 7 commands

Paved-path engineering skills: React, Next.js, Fastify, Drizzle, PostgreSQL, TypeScript, Zod, testing, security, architecture and Mermaid diagrams.

12 skills

Core development workflow skills: planning, TDD, debugging, code review, branch management, and parallel agent dispatching. Based on obra/superpowers.

12 skills

Development workflow skills for commits, linting, testing, code review, PRs, documentation, coverage, dependencies, project scaffolding, and task automation

11 skills · 1 agent

Brave Search API skills for web, news, image and video search, LLM context, AI answers, local places and query helpers.

12 skills

A design-first development workflow: agree on a design, work on its own branch, open a concise pull request, get a fresh-context review, and clean up after merge.

9 skills · 2 agents · hooks

Brainstorm → analyze → plan → parallel TDD (4 agents) → lightweight review

5 commands · 6 agents

Strict koment procedure, writable MCP tools, and completion policy checks.

1 skill · 8 commands · 1 MCP server · hooks

Generate interactive architecture diagrams from your codebase

11 skills

Parallel multi-area production-readiness audit with weighted scoring and a phased go-live plan.

1 skill · 1 command · 9 agents