All skills & plugins / Anthropic Agent Skills
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.
- Type
- Skill by Anthropic
- Catalog
- Anthropic Agent Skills
- Source
- anthropics/skills/skills/skill-creator (18 files scanned)
- Install and details
- Agent Skills Index entry
- License
- Apache-2.0 (LICENSE file)
- Signals
- Bundled scriptsSpawns processes
Pre-approved tools
No allowed-tools or tools list in its SKILL.md, command or agent files, so the agent asks before using tools as usual.
Hooks
No hooks.
MCP servers and apps
None.
Bundled code
10 code files (Python):
skill-creator/eval-viewer/generate_review.pyskill-creator/scripts/generate_report.pyskill-creator/scripts/__init__.pyskill-creator/scripts/improve_description.pyskill-creator/scripts/run_eval.pyskill-creator/scripts/run_loop.pyskill-creator/scripts/aggregate_benchmark.pyskill-creator/scripts/utils.pyskill-creator/scripts/quick_validate.pyskill-creator/scripts/package_skill.py
Network calls
No HTTP or socket call pattern found in the code.
Starts other programs
3 files. First match per file:
skills/skill-creator/eval-viewer/generate_review.py:291result = subprocess.run(
skills/skill-creator/scripts/improve_description.py:35result = subprocess.run(
skills/skill-creator/scripts/run_eval.py:85process = subprocess.Popen(
Credentials referenced
No key, token or secret environment variable found in code or MCP config.
Static scan of commit dbd4588 on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.