blader — 10 Open-Source AI Agent Skills

blader is the author of 10 open-source AI agent skills and MCP servers spanning codex-skill, claude-skill, with a combined 56,199+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 55/100) and security-graded where a README exists (8 of 10) — 8 verified safe.

Top skills by blader

• humanizer — Agent skill that removes signs of AI-generated writing from text (52.7k★ · quality 71/100 · security: safe)
• Claudeception — A Claude Code skill for autonomous skill extraction and continuous learning. Have Claude Code get smarter as it works. (2.4k★ · quality 69/100 · security: safe)
• napkin — A Claude Code skill that gives the agent persistent memory of its mistakes via a per-repo markdown scratchpad. (617★ · quality 58/100 · security: safe)
• schematic — Claude Code / Codex skill: reverse engineer a product & technical spec from a git branch (238★ · quality 59/100 · security: safe)
• theorist — A Codex/Claude skill that maintains per-repo operating theory documents. (191★ · quality 59/100 · security: safe)
• razor — Minimize your branch diff against merge base with structured, explicit tradeoffs. A skill for Claude Code and Codex. (15★ · quality 66/100 · security: safe)
• arbitrage — A Claude Code skill for token arbitrage: keep premium model tokens for judgment, dispatch all code-writing to codex. (12★ · quality 56/100 · security: safe)
• adversarial-execution — Adversarial Execution — an execution-time review gate: two independent strong models must both prove your work actually works before it's ma (5★ · quality 39/100 · security: safe)

View blader on GitHub · Explore audited agent skills