Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
Comparison matrix
Highlights show current best; tooltip explains diff/best rules.
SAS-v2.1 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.
Suggested baseline
Repository: claude-code-base-action
Author: anthropics · Source status: Clear source
This repo is a mirror of the contents of base-action in https://github.com/anthropics/claude-code-action.
Score basis：Clear source · Risk needs review · Universal
Search to add skills, or paste 2–4 comma-separated slugs.
How differences are detected
A row is marked different when selected skills have distinct values. Only-differences mode hides rows that are identical.
How best values are highlighted
Audit score, evidence confidence, trust score, and community signal prefer higher values; execution risk and install friction prefer lower values.
How to read risk tags
Risk tags come from SAS-v2.1 public-evidence signals and point to command, network, secret, context, or supply-chain items to review before install.
Selected audit signals
mcp-integration
Execution risk：High
Threat tags：data exfiltration, memory context poisoning, human approval gap
Control gaps：missing license, broad permissions, network without allowlist
knowledge-work-plugins
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, memory context poisoning
Control gaps：missing license, broad permissions, shell without guardrails
skill-seekers
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | mcp-integration | knowledge-work-plugins | skill-seekers |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Audit grade | C · Review first | C · Review first | D · Limited evidence |
Execution risk | High | High | High |
Threat tags | data exfiltration, memory context poisoning, human approval gap | unexpected code execution, data exfiltration, memory context poisoning | unexpected code execution, identity privilege abuse, data exfiltration |
Control gaps | missing license, broad permissions, network without allowlist | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails |
Permission summary | Permission review, Network, Command | Permission review, Network, Command | Permission review, Network, Secrets, Command |
Evidence confidence | 65% | 67% | 71% |
| Source & provenance | |||
Provenance | anthropics/claude-code/tree/main/plugins/plugin-dev/skills/mcp-integration | anthropics/knowledge-work-plugins | openclaw/skills |
Category | Operations & Infra | Automation & Workflows | Dev & Engineering |
Freshness | |||
| Risk & trust | |||
Trust score | 79 | 92 | 88 |
Audit signals | network access | metadata-only | needs credentials, network access, runs shell, writes files |
| Install & compatibility | |||
Supported tools | Claude, Codex, Cursor, Universal | Universal | Claude, Cursor, Windsurf |
Install method | registry-install | script-backed | script-backed |
Install friction | |||
| Community | |||
Stars | 65.5K | 11.2K | 0 |
Repository: claude-plugins-official
Author: anthropics · Source status: Clear source
Official, Anthropic-managed directory of high quality Claude Code Plugins.
Score basis：Clear source · Risk needs review · Universal
Repository: claude-quickstarts
Author: anthropics · Source status: Clear source
A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API
Score basis：Clear source · Risk needs review · Universal
2026-02-04 |
2026-04-10 |
2026-04-04 |
Permission hints |
|---|
registry access, remote metadata pull, runtime dependencies may be required |
repository clone |
verify source provenance before install |
50 |
75 |
65 |
