humanlayer/skills
About the project
A collection of Claude Code skills from HumanLayer, installed via npx skills add and invoked as slash commands in a project. Includes improving CLAUDE.md, narrowing React prop types, building agentic loops, and generating explanatory diagrams.
Useful for
- Install the improve-claude-md skill and rewrite CLAUDE.md for better instruction adherence
- Narrow a React component's prop types to live code paths via narrow-react-prop-types
- Build an agentic loop with a GitHub Actions workflow via build-iterated-agentic-loop
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 65 expected by the end of the day.
- Interest is fading: the two-day pace is 23% of the previous week and a half.
- GitHub Trending this week: #19, +1,004 stars.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 3,996
- Stars in a day
- 65
- Forks
- 121
- Issues and pull requests
- 9
- Watchers
- 8
- Language
- TypeScript
- License
- MIT
- Created
- March 18, 2026
- Last push
- August 13, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 14, 2026GitHub Trending this week: #19, +1,004 stars
- September 13, 2026GitHub Trending this week: #10, +1,380 stars
Similar projects
-
6.2
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.2
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.0
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
5.5
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.
-
5.3
alphaXiv/OpenResearch
A local-first workspace for research agents that turns Claude Code, Codex, OpenCode, or Cursor into agents reviewing literature, forming hypotheses, and running experiments. Each direction gets an isolated git worktree…
-
5.2
TauricResearch/TradingAgents
A framework that simulates a trading firm with LLM agents (analysts, researchers, trader, risk manager) debating markets and producing trading decisions. Built for research, not real trading.