Turn people, methods, and experience into installable, reusable agent skills.
SkillAlchemy is an open-world agent skill creation system. It discovers omitted requirements, extracts executable procedures from public sources, and produces skills that agents can install and use directly.
We evaluate SkillAlchemy on 87 tasks from SkillsBench v1.1 across four agent–model configurations. SkillAlchemy achieves the highest overall task pass rate in 3 of 4 configurations.
Averaged across all configurations, SkillAlchemy reaches a 55.8% task pass rate, improving over no-skill execution by 19.9 percentage points. It also slightly surpasses human-curated skills on average.
| Skill Setting | Claude Code DeepSeek-V4-Pro |
Claude Code Opus 4.8 |
Codex DeepSeek-V4-Pro |
Codex GPT-5.5 |
Avg. |
|---|---|---|---|---|---|
| No Skill | 23.4 | 45.3 | 29.7 | 45.1 | 35.9 |
| Anthropic Skill-Creator | 31.7 | 49.2 | 32.9 | 48.5 | 40.6 |
| OpenAI Skill-Creator | 33.3 | 49.9 | 37.0 | 48.5 | 42.2 |
| OpenSkill | 42.3 | 51.5 | 40.7 | 49.4 | 46.0 |
| MUSE-Autoskill | 43.2 | 53.3 | 40.2 | 52.0 | 47.2 |
| Human-Curated Skill | 51.3 | 59.5 | 45.7 | 60.9 | 54.4 |
| SkillAlchemy | 54.7 | 60.9 | 43.9 | 63.7 | 55.8 |
- Distill people — Build Persona Skills from public evidence about decisions, failures, values, and communication patterns.
- Distill methods — Turn books, methodologies, repositories, or interviews into executable Skills with conditions, steps, branches, and failure handling.
- Fuse Skills — Combine existing workflows, domain knowledge, or working styles into a new capability.
- Stay evidence-grounded — Separate reusable procedures, scoped cases, and unsupported content to reduce unjustified generalization.
The easiest way to install SkillAlchemy is to ask Claude Code or Codex:
Install SkillAlchemy from https://github.com/agentsope/SkillAlchemy and show me how to use it.
Or use the command line:
npx skills add agentsope/SkillAlchemyThen describe the Skill you want to create:
Use SkillAlchemy to create a Skill for reviewing RAG systems. Use public documentation and research papers as sources.
Generated packages are written to output/ in the active project.
# Core components
npx skills add agentsope/SkillAlchemy/skills/Lens
npx skills add agentsope/SkillAlchemy/skills/LEAP
# Another bundled Skill
npx skills add agentsope/SkillAlchemy/skills/<skill-name>