tigerless-labs — 7 Open-Source AI Agent Skills

tigerless-labs is the author of 7 open-source AI agent skills and MCP servers spanning agent-tool, codex-skill, mcp-server, claude-skill, with a combined 22,454+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 66/100) and security-graded — 6 verified safe.

Top skills by tigerless-labs

• autoharness — Building the self-learning layer next-gen agents will ship with, learning skills from real work. (10.7k★ · quality 69/100 · security: safe)
• cost-xray — See what Claude Code and Codex actually send to the API — and what each part costs. (5.8k★ · quality 73/100 · security: safe)
• agent-memory — Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage (4.3k★ · quality 72/100 · security: caution)
• seo-ops — SEO foundation checks as an Agent Skill: give it a URL, get a crawler's-eye pass/fail report with evidence. 26 structural checks, zero LLM, (986★ · quality 66/100 · security: safe)
• influencer-discovery — Influencer discovery & contact enrichment pipeline that runs as a Claude Code skill — 15 channels, stdlib only, appends to a Google Sheet (219★ · quality 69/100 · security: safe)
• design-harness — Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas (213★ · quality 52/100 · security: safe)
• paper-radar — Finds the AI papers 28 tech companies put on arXiv over any date range, and splits lead authorship from bylines. A SKILL.md agent skill — no (204★ · quality 64/100 · security: safe)

View tigerless-labs on GitHub · Explore audited agent skills