Agent capability
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Compatible agent runtimes
19 files
225,474 bytes
Runtime provisioning
Provision this capability
The provisioning flow resolves the versioned manifest, verifies every SHA-256 digest, and applies the package atomically.
Shared Agent Skills
User scope: ~/.agents/skills/skill-creator
curl -fsSLo /tmp/mm-skills-install.sh __MM_RUNTIME_ORIGIN__/install.sh && bash /tmp/mm-skills-install.sh skill-creator --client agents --scope user --registry __MM_RUNTIME_ORIGIN__
Codex
User scope: ~/.agents/skills/skill-creator
curl -fsSLo /tmp/mm-skills-install.sh __MM_RUNTIME_ORIGIN__/install.sh && bash /tmp/mm-skills-install.sh skill-creator --client codex --scope user --registry __MM_RUNTIME_ORIGIN__
OpenCode
User scope: ~/.config/opencode/skills/skill-creator
curl -fsSLo /tmp/mm-skills-install.sh __MM_RUNTIME_ORIGIN__/install.sh && bash /tmp/mm-skills-install.sh skill-creator --client opencode --scope user --registry __MM_RUNTIME_ORIGIN__
Antigravity
User scope: ~/.gemini/config/skills/skill-creator
curl -fsSLo /tmp/mm-skills-install.sh __MM_RUNTIME_ORIGIN__/install.sh && bash /tmp/mm-skills-install.sh skill-creator --client antigravity --scope user --registry __MM_RUNTIME_ORIGIN__
Windows PowerShell
$installer = Join-Path $env:TEMP 'mm-skills-install.ps1'; Invoke-WebRequest '__MM_RUNTIME_ORIGIN__/install.ps1' -OutFile $installer; & $installer -Skill 'skill-creator' -Client 'agents' -Scope 'user' -Registry '__MM_RUNTIME_ORIGIN__'
Artifact integrity
Versioned package contents
| Path | Bytes | SHA-256 |
|---|---|---|
| agents/analyzer.md | 10,376 | bf68f4cac5a56c67… |
| agents/comparator.md | 7,287 | fe1fc9787c495d86… |
| agents/grader.md | 9,049 | 57134da0c1a4eea3… |
| assets/eval_review.html | 7,058 | ce477dcc74dc1c0d… |
| eval-viewer/generate_review.py | 16,365 | fc9d1b9243fe5ab6… |
| eval-viewer/viewer.html | 44,998 | a53213426ee11004… |
| LICENSE.txt | 11,345 | bc6b3af2f331cbc7… |
| references/schemas.md | 12,061 | 8e8876180a8989b4… |
| scripts/__init__.py | 0 | e3b0c44298fc1c14… |
| scripts/aggregate_benchmark.py | 14,386 | 123ef128ea5ccc01… |
| scripts/generate_report.py | 12,847 | 13df7118a3c50c83… |
| scripts/improve_description.py | 11,116 | 87d864570220b699… |
| scripts/package_skill.py | 4,234 | 1a33059b0db1ef73… |
| scripts/quick_validate.py | 3,972 | 67cf570340201393… |
| scripts/run_eval.py | 11,464 | 43e3b8f80dbf69c3… |
| scripts/run_loop.py | 13,605 | 7bd6f67420316852… |
| scripts/utils.py | 1,661 | 3af8ae62c40c73ab… |
| SKILL.md | 33,168 | dcd4803e61e913e6… |
| SOURCE.md | 482 | ec12ec1d33309587… |