AGENT DEVELOPMENT / Anthropic
Anthropic Skill Creator
Develops skills through example tasks, baseline comparisons, human review and separate trigger-description evaluation.
“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”
01 / THE REASONING
Why this made the selection.
- Separates whether a skill activates from whether its instructions improve the resulting work.
- Includes evaluation and metadata-validation helpers rather than relying solely on a polished SKILL.md.
02 / THE REVIEW RECORD
What we actually inspected.
Source review has boundaries.
A clear record is more useful than a “safe” badge.
Material inspected
- skills/skill-creator/SKILL.md
- skills/skill-creator/scripts/quick_validate.py
- skills/skill-creator/scripts/run_eval.py
- skills/skill-creator/LICENSE.txt
Our findings
- The inspected evaluator creates a temporary Claude command file and removes it in a finally block.
- It launches Claude subprocesses and looks for Skill or Read events that reference the temporary name.
- The metadata helper validates YAML fields, name formatting and description constraints but does not execute the skill.
Not established by this review
- Source inspection only; no skill installation or workflow execution was performed.
The review applies to the material and revision named here. A newer upstream release can change its behavior.
03 / PUT IT TO WORK
Add a skill to your workflow.
DOCUMENTED COMMAND
npx skills add https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creatorCopying does not execute this command. It may retrieve a newer version than the reviewed source.
- Install the complete skill directory with its references and helpers; a copied SKILL.md alone may be incomplete.
- Choose the intended agent and project scope in the installer, then review its permissions before using the skill.
Before you start
- Node.js/npm for this installer
- An agent that supports the Agent Skills format
- Python/PyYAML for metadata validation
- Claude CLI and supported subagents for full evaluation
04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/SKILL.md
Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, compatibility, access
https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/scripts/quick_validate.py
Supports: review, limitations, access
https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/scripts/run_eval.py
Supports: review, limitations, access
https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/LICENSE.txt
Supports: license
https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md
Supports: install, compatibility, access
https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md
Supports: install
https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/git.ts
Supports: install