fysoul17
UserAI development toolkit for Claude Code — ideate, auto-resolve, and ship with context engineering and agent orchestration
Categories
Indexed Skills (15)
dokkit
One-command document template filling. Put source files (회사소개서, 사업자료, 이미지 등) in a folder, provide a DOCX/HWPX template, and get a polished, complete document with AI-generated images. Auto-iterates until perfect. Supports Korean government forms: 사업계획서, 지원서, 신청서. Trigger on: "fill template", "사업계획서 작성", "문서 작성", "dokkit", "fill this form", "템플릿 채워줘", "complete this document", "fill document", "template automation", HWPX files, 한글 templates, document generation, or any task involving filling document templates with source materials. Also trigger when user drops files and asks to fill or complete a template.
devlyndesign-ui
Assemble a world-class design team (Creative Director, Product Designer, Visual Designer, Interaction Designer, Accessibility Designer) to generate N (default 5) radically distinct, portfolio-worthy UI style explorations. Pass a leading integer or `count:N` in the brief to change the count.
asset-creator
Generate consistent pixel art game assets using AI image generation + meta-prompting for style lock + HSL chroma-key background removal. Produces transparent PNGs ready for PixiJS, Phaser, or any 2D game engine. Use when building pixel art games, creating game sprites, generating isometric assets, making character sprites, or when user says "create asset", "generate sprite", "make game art", "pixel art asset", or "에셋 만들어".
better-auth-setup
Production-ready Better Auth integration for fullstack projects. Covers both the backend (Bun + Hono + Drizzle + PostgreSQL) and the frontend reverse proxy architecture (Next.js, Cloudflare Workers, or any framework proxying auth requests to a separate backend). Sets up email/password auth, session cookies, OAuth providers (Google, GitHub), API key auth, organization/multi-tenant support, email verification, CORS, security headers, auth middleware, tenant context, proxy forwarding headers, dynamic baseURL with allowedHosts, cookie prefix handling, and test infrastructure — all in one pass with zero gotchas. Use this skill whenever setting up Better Auth, adding OAuth/social login, configuring a reverse proxy for auth, debugging redirect_uri_mismatch errors, fixing state_mismatch cookie issues, session cookies not persisting after OAuth callback, or when the user mentions Better Auth, OAuth proxy, auth setup, login, signup, session management, API keys, multi-tenant auth, or "session cookie not working".
cloudflare-nextjs-setup
Set up Cloudflare Workers deployment for an existing Next.js project using OpenNext. Triggers on "deploy to Cloudflare", "set up Cloudflare Workers", "Cloudflare deployment", "add Cloudflare to this project".
devlynreap
Safely count and kill orphaned child processes (PPID=1) left behind by Claude Code MCP plugins, Superset terminal tabs, and codex wrappers. Use this whenever the user says "too many processes", "can't open terminals", "pty/process limit", "hundreds of bun/codex/workerd piling up", "clean up orphans", "reap processes", or reports new terminals failing to spawn on macOS. Also use proactively after long Claude sessions to prevent hitting kern.maxprocperuid or kern.tty.ptmx_max limits. ONLY touches a conservative whitelist of known leaks — never guesses on unknown processes.
generate-skill
Create well-structured Claude Code skills following Anthropic best practices. Generates SKILL.md files with proper frontmatter, workflow structure, and prompt engineering patterns for Claude 4.6. Use when building new skills, refactoring existing ones, or when user says "create a skill", "new skill", "generate skill", "make a command".
prompt-engineering
Claude 4 prompt optimization for creating, reviewing, or refining prompts. Applies official Anthropic best practices for explicit instructions, context framing, format control, and model-specific tuning. Proactively use this skill when writing system prompts, agent instructions, skill definitions, or meta-prompting.
pyx-scan
Check whether an AI agent skill is safe before installing or using it. Calls the PYX Scanner API to retrieve trust status, risk score, and safety recommendation. Use when agent needs to verify skill safety, or user says "is this safe", "check skill", "scan skill", "verify tool", "pyx scan".
devlynqueue
Manage and drain the intent queue (docs/specs/queue.md) — the backlog the loop-engineering contract runs on. Use when the user wants to stack work for later ("큐에 넣어줘", "queue this"), see what is queued, or start an unattended serial drain ("큐 드레인 시작", "밤새 돌려줘", "drain the queue") that takes each item through spec → /devlyn:resolve → verified done.
devlynresolve
Hands-free pipeline for any coding task — bug fix, feature, refactor, debug, modify, PR review. Free-form goal or formal spec input. Plan → Implement → Build-gate → Cleanup → Verify (fresh subagent, findings-only). Mechanical-first verification; Verify dual-judge is default-when-available. Use when the user says "resolve this", "fix this", "implement this", "refactor this", "debug this", "review this PR", or wants hands-off completion.
devlynengines
Show and pin engine roles for the devlyn pipeline (executor / pair judge). Reads and writes machine-local .devlyn/engines.json with fail-closed validation. Use when the user asks which models are configured, wants to force a specific model for pipeline work ("수동모드", "engine 고정", "use codex to implement"), or wants to clear pins back to auto-detection.
devlynideate
Extract a verifiable spec from a user's idea by driving the conversation with focused questions. Output is a single-feature `spec.md` + `spec.expected.json` that `/devlyn:resolve --spec` consumes directly. Use when the user has an idea but not a spec, or wants AI to elicit the missing engineering context. Modes — default (single spec, AI drives Q&A), `--quick` (assume-and-confirm from one-line goal), `--from-spec <path>` (normalize external spec), `--project` (plan.md index + N specs). Optional in the pipeline — `/devlyn:resolve` works standalone via free-form mode for users who skip ideate.
devlynpencil-pull
Pull Pencil designs into code with exact visual fidelity.
devlynpencil-push
Push codebase UI to Pencil canvas for design sync.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.