SkillTrust — AI Skills Selection Assistant

Compare skills

Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.

Current comparison context

Comparison queue

Permalink Clear all

mcp-integration security-ownership-map Agent Sync

Selected skills (3/4)

Comparison queue

Ready

mcp-integration
anthropics/claude-code/tree/main/plugins/plugin-dev/skills/mcp-integration · Score 79
Remove
security-ownership-map
openai/skills/tree/main/skills/.curated/security-ownership-map · Score 82
Remove
Agent Sync
openclaw/skills · Score 84
Remove

Comparison matrix

Key differences

Highlights show current best; tooltip explains diff/best rules.

Only differences Show all rows Clear selection

Score-basis diff rules / risk tag notes

Start with the matrix. Open this section when you need to understand audit grades, top threats, control gaps, and best-value highlights.

Open notes

Suggested baseline

Suggested skills to compare

Convert documentation, GitHub repos, PDFs, codebases, videos, and more into structured AI skills using the skill-seekers CLI. Use this skill whenever the user wants to create an AI

Repository: openclaw/skills

Author: tenequm · Source status: Clear source

Score 88Clear source

Evidence missing

Convert documentation, GitHub repos, PDFs, codebases, videos, and more into structured AI skills using the skill-seekers CLI.

Score basis：Clear source · High execution risk · Claude · Evidence completeness 71%

Author unclaimed

Dimension	mcp-integration	security-ownership-map	Agent Sync
Pre-install decision
Pre-install score	79 · Manual review	82 · Manual review	84 · Manual review
Score basis	Clear source, High execution risk, Claude	Clear source, High execution risk, Claude	Clear source, High execution risk, Claude
Execution risk	High	High	High
Threat tags	data exfiltration, memory context poisoning, human approval gap	data exfiltration, human approval gap	prompt injection, tool poisoning, unexpected code execution
Control gaps	missing license, broad permissions, network without allowlist	missing license, broad permissions, network without allowlist	missing license, broad permissions, shell without guardrails
Permission summary	Permission review, Network, Command	Permission review, Network, Command	Permission review, Network, Command
Evidence completeness	65%	67%	67%
Source & provenance
Provenance	anthropics/claude-code/tree/main/plugins/plugin-dev/skills/mcp-integration	openai/skills/tree/main/skills/.curated/security-ownership-map	openclaw/skills
Category	Operations & Infra	Data & Analytics	Dev & Engineering
Freshness
Risk & permission signals
Audit signals	network access	writes files	network access, runs shell, writes files
Permission hints	registry access, remote metadata pull, runtime dependencies may be required	registry access, remote metadata pull, runtime dependencies may be required	target os: macos, target os: linux, verify source provenance before install
Install & compatibility
Supported tools	Claude, Codex, Cursor, Universal	Claude, Codex, Cursor, Universal	Claude, Codex, Cursor, OpenClaw, Windsurf, GitHub Copilot
Install method	registry-install	registry-install	script-backed
Install friction
Community
Stars	65.5K	7.3K	0

Compare skills

Key differences

Suggested skills to compare

Convert documentation, GitHub repos, PDFs, codebases, videos, and more into structured AI skills using the skill-seekers CLI. Use this skill whenever the user wants to create an AI

Github Anthropics Knowledge Work Plugins

Github Anthropics Claude Code Base Action

Github Anthropics Claude Plugins Official

Github Anthropics Claude Quickstarts