Developer tools Agent Skills
Code, repository, and engineering workflow integrations.
Evidence-grounded, lightweight guardrails for strong coding agents—Fact, Plan, Execute, Review, and Handoff.
FN2 skill for Hermes Agent — grounded stock/market research and schedulable research agents (agentskills.io, zero-dependency)
Locate every paper in the literature, not just in a summary.
Two supporting Agent Skills: one for harnesses, one for harness check-ups. Standard SKILL.md format, compatible with Claude Code / Codex / Cursor / OpenClaw, scripts can run directly as CLIs. Five-layer framework + visual reports, all destructive actions are proposed first and await your approval. Zero dependency.
OpenClaw skill for Privy agentic wallets - create wallets AI agents can control autonomously
面向迅投 QMT / 投研终端的 仓库：把量化策略开发的领域知识（因子回测、信号生成、实盘模板等）封装为标准 SKILL.md 技能，安装后可在 Claude Code、Cursor、Codex、Gemini CLI、Kimi Code 等 70+ AI 编程工具中直接使用。
Two Claude Code skills for reading one academic paper: /paper-review (journal-club appraisal, deterministic GRADE + CrossRef gate) and /paper-digest (fast content absorption).
Static analysis for Claude Code / Agent SDK skills. Audits SKILL.md against 10 QA checks to verify triggerability across LLMs (Claude, GPT, Gemini).
Lets an AI agent (Claude Code, Codex, etc.) query the user's locally-running desktop app over its built-in HTTP API.
Set of skills for AI agents
Agent-agnostic record & replay skill: watch a user demonstrate a workflow (browser via Playwright, desktop via OpenAdapt) and turn it into a reusable AI-agent skill.
The Anthropic API wrapper for Delphi leverages cutting-edge models, including Anthropic's advanced Claude series, to deliver powerful features for chat interactions, vision processing, caching,...
A curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts across 19 skills: SpoonOS Skills for Vibe Coding (build agents) + Web3 Skills for Skill...
One Agent can delegate multiple projects. Each project has one Project Runner that orchestrates its own authorized workers, and each worker can autonomously complete tasks through Kaola Workflow.
Kotlin Multiplatform task manager with AI assistance. Targets Android and JVM Desktop (no iOS).
Built for the agent trifecta: you, your team, and your AI agents.
Agent-friendly headless agent (ask/session) — the local-LLM-agent half split out of SHUKE-LABS/baton
A comprehensive Claude Code skill for managing Linear issues, projects, and teams. Provides patterns for MCP tools, SDK automation, and GraphQL API access.
Personal compute fabric: schedule AI agent work and jobs across machines you own. The brain stays home.
Jiang Hushuo · Oral Broadcasting Skill: Distilled from 433 verbal transcripts with 'Values Principles', able to answer questions, write oral scripts, and find topics
Installable Codex skills for goal-setting and marketing operator work.
Ten structured AI skills for evaluating and improving UI designs — covering visual hierarchy, typography, color, spacing, buttons, clutter, empty states, shadows, contrast, and grouping.
Official Agent Skill for building and continuously maintaining Git-native moldea project context and AI agent behavior.
Public read mirror of msgboard.dev, for agents that can reach GitHub but not the site. Updated every 10 minutes.