Trusted — Risk Score 0/100
Last scan:1 day ago Rescan
0 /100
skills-best-practices
Build high-quality Agent Skills for Claude following official Anthropic best practices. Covers SKILL.md structure, frontmatter, description writing, progressive disclosure, testing, patterns, troubleshooting, and distribution across all surfaces (Claude.ai, Claude Code, API, Agent SDK). Use when creating new skills, reviewing skill quality, debugging skill triggering, structuring skill directories, writing skill descriptions, or improving existing skills. Triggers on 'build a skill', 'create a skill', 'skill structure', 'SKILL.md', 'skill best practices', 'skill not triggering', 'skill quality'.
This is a pure documentation/reference skill teaching Claude Agent Skill development best practices. It contains no executable code, scripts, credential access, network requests, or any hidden functionality.
Skill Nameskills-best-practices
Duration25.9s
Enginepi
Safe to install
This skill is safe to use. It consists entirely of markdown documentation and reference guides with no security concerns.
ResourceDeclaredInferredStatusEvidence
Filesystem NONE NONE No scripts or code files; only markdown documentation
Network NONE NONE External URLs are static documentation links only; no runtime network calls
Shell NONE NONE No shell scripts or executable code present
Environment NONE NONE No environment variable access in any file
Skill Invoke NONE NONE Documentation skill; no skill invocation code
Clipboard NONE NONE No clipboard access
Browser NONE NONE No browser automation
Database NONE NONE No database access
8 findings
🔗
Medium External URL 外部 URL
https://www.apache.org/licenses/
LICENSE.txt:3
🔗
Medium External URL 外部 URL
https://agentskills.io
SKILL.md:10
🔗
Medium External URL 外部 URL
https://agentskills.io/specification
SKILL.md:312
🔗
Medium External URL 外部 URL
https://code.claude.com/docs/en/skills
SKILL.md:313
🔗
Medium External URL 外部 URL
https://platform.claude.com/docs/en/build-with-claude/skills-guide
SKILL.md:314
🔗
Medium External URL 外部 URL
https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices
SKILL.md:315
🔗
Medium External URL 外部 URL
https://claude.com/blog/equipping-agents-for-the-real-world-with-agent-skills
SKILL.md:317
🔗
Medium External URL 外部 URL
https://resources.anthropic.com/hubfs/The-Complete-Guide-to-Building-Skill-for-Claude.pdf
SKILL.md:318

File Tree

6 files · 42.3 KB · 1341 lines
Markdown 5f · 1179L Text 1f · 162L
├─ 📁 references
│ ├─ 📝 checklist.md Markdown 108L · 3.7 KB
│ ├─ 📝 claude-code-features.md Markdown 233L · 5.9 KB
│ ├─ 📝 description-guide.md Markdown 169L · 5.1 KB
│ └─ 📝 patterns.md Markdown 351L · 8.1 KB
├─ 📄 LICENSE.txt Text 162L · 8.9 KB
└─ 📝 SKILL.md Markdown 318L · 10.5 KB

Security Positives

✓ Pure documentation/reference skill with no executable code
✓ No scripts, binaries, or code files — only markdown documentation and reference guides
✓ Content is clear, readable, and well-structured without any obfuscation
✓ No credential harvesting, environment variable access, or sensitive path access
✓ No network calls at runtime — only static documentation URLs to official Anthropic resources
✓ No supply chain risks — no dependencies, package files, or third-party scripts
✓ No persistence mechanisms, reverse shells, or C2 indicators
✓ Content accurately matches stated purpose: teaching Claude Agent Skill development best practices
✓ License (Apache 2.0) is appropriate for Anthropic-published documentation
✓ External URLs point exclusively to official Anthropic documentation and Apache License