你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement. | Lead: Minwei Wang (https://www.minwei.wang · ORCID: 0009-0002-7976-4689 · DOI: 10.5281/zenodo.24156132)
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
Design engineering for Claude Code. Craft, memory, and enforcement for consistent UI.
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
Creator Buddy: orchestrated Agent Skills for cross-platform content search, creator analysis, and viral trend research
Use Astra or Sol as orchestrator and Luna for subagents in Codex
A ready-to-fork Claude Code template for academic research — papers, data analysis (R, Stata, Python), slides and teaching — with multi-agent review, enforced quality gates and replication protocols. Codex and Antigravity can use it too.
- academic-writing
- causal-inference
- claude-code
- claude-code-skills
A Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant briefings). Enforces action titles, structured argument, exhibit discipline, citation standards, and communication-first design. Works alongside Anthropic's built-in PPTX skill.
Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates.
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.
Salesforce's curated collection of agent skills for building applications. Optimized for Agentforce Vibes, compatible with all AI tools.
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.
Make Gemini code like Claude Models. Forces it to inspect files before editing, plan changes, test its work, and back up every “done” with actual evidence.
Toolkits for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
An Agent Skill that writes original instrumental music as editable notes, then performs, mixes and masters it on free sampled instruments (CC0 or free for any use) and synthesizers. MIDI, stems and game loops; no audio-generation model.
Delegate bounded coding tasks to a headless WorkBuddy/CodeBuddy CLI agent from DeepSeek Harness — structured result, real diff, path whitelist and worktree isolation.
Grand Tour Skill: orchestrated developer library for /grand-tour
- ai-agent
- ai-agent-tools
- ai-agent-workflows
- ai-agents-for-business
A lightweight workflow plugin for hands-off AI coding with DeepSeek Harness, Claude Code, GitHub Copilot, and more.
Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.