phuryn — 13 Open-Source AI Agent Skills
phuryn is the author of 13 open-source AI agent skills and MCP servers spanning agent-tool, claude-skill, codex-skill, mcp-server, with a combined 30,768+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 62/100) and security-graded where a README exists (12 of 13) — 12 verified safe.
Top skills by phuryn
- pm-skills — PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth. (27.5k★ · quality 70/100 · security: safe)
- claude-usage — A local dashboard for tracking your Claude Code token usage, costs, and session history. Pro and Max subscribers get a progress bar. This gi (2.2k★ · quality 71/100 · security: safe)
- product-engineering — Agent skills for shipping real products with coding agents, from the first idea to paying users. No coding. (279★ · quality 65/100 · security: safe)
- grok-build-vscode — Grok Build, Muse Code, Claude, Codex & more in one place; GUI; AFK Pilot (239★ · quality 58/100 · security: safe)
- bug-hunt-bench — Bug Hunt Bench: 105 real bugs in two production repos, frontier coding models (GPT-6, Claude, Grok, Gemini, DeepSeek...) find and fix them i (171★ · quality 51/100 · security: safe)
- mini-harness — An agent harness built for teaching: ~1,400 lines of Python with goal mode, permissions, skills, MCP and Claude's server-side compaction (115★ · quality 66/100 · security: safe)
- work-humanizer — A humanizer for work writing: takes the AI tone out without changing what your text says or commits to. Agent Skill + evidence: blind judges (96★ · quality 65/100 · security: safe)
- swarm-protocol — Coordination protocol for agent-first teams. No UI. No sprints. No Jira. Just state sync. (57★ · quality 70/100 · security: safe)
View phuryn on GitHub · Explore audited agent skills