Skill of Skills
📄 skillActivePromisingOfficialmedium

anthropics/claude-agent-sdk-python

by anthropics

No description available

Supported Platforms

🤖 Claude Code

Stars

7.3k

Skill Type

📖 Library & API Reference

Quality Score

106/200

License

MIT

Forks

1.1k

Last Updated

Jun 11, 2026

Discovered

May 9, 2026

Validation

Passed

github.com/anthropics/claude-agent-sdk-python

Quality Breakdown

106/ 200

Content Signals

â—‹Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

Official

This skill is published by a platform vendor.

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Risk Assessment

  • Repository contains .claude/ configuration directory with agents, commands, and settings that could modify Claude's persistent behavior
  • Multiple GitHub Actions workflows present that could execute arbitrary code during CI/CD (claude-code-review.yml, claude-issue-triage.yml, auto-release.yml)
  • SDK bundles and auto-executes external CLI tool (Claude Code CLI) without explicit user approval gate - subprocess_cli.py indicates shell execution capability
  • Shell scripts in /scripts directory (edit-issue-labels.sh, gh.sh, test-docker.sh) for automation
  • Bootstrap automation via initial-setup.sh and pre-push hooks
  • CLAUDE.md file indicates persistent configuration of Claude agent behavior