Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
This comparison came from collection: Claude pack
Best for comparing 2–4 candidates for the same app.
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
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
Anthropic
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
Anthropic Token Optimizer
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
claude-automation-recommender
Execution risk：High
Threat tags：data exfiltration, human approval gap
Control gaps：missing license, network without allowlist, no human approval
| Dimension | Anthropic | Anthropic Token Optimizer | claude-automation-recommender |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Audit grade | C · Review first | C · Review first | C · Review first |
Execution risk | High | High | High |
Threat tags | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, identity privilege abuse, data exfiltration | data exfiltration, human approval gap |
Control gaps | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails | missing license, network without allowlist, no human approval |
Permission summary | Permission review, Network, Secrets, Command | Permission review, Network, Secrets, Command | Network, Command |
Evidence confidence | 67% | 69% | 63% |
| Source & provenance | |||
Provenance | openclaw/skills | openclaw/skills | anthropics/claude-plugins-official/tree/main/plugins/claude-code-setup/skills/claude-automation-recommender |
Category | Integrations & Connectors | Knowledge & RAG | Dev & Engineering |
Freshness | |||
| Risk & trust | |||
Trust score | 79 | 85 | 76 |
Audit signals | needs credentials, network access, runs shell, writes files | needs credentials, network access, runs shell, writes files | No explicit signals |
| Install & compatibility | |||
Supported tools | Claude | Claude, OpenClaw | Claude, Codex, Cursor, Universal |
Install method | script-backed | script-backed | registry-install |
Install friction | |||
| Community | |||
Stars | 0 | 0 | 7K |
Repository: openclaw/skills
Author: zwd0313 · Source status: Clear source
Run Claude Code tasks in headless mode with `claude -p` through the local `cc-task-runner.sh` wrapper, including model switching, JSON output capture, structured schema checks, multi-file artifact validation, and glob ma
Score basis：Clear source · High risk signals · Claude
2026-03-08 |
2026-04-02 |
2026-02-04 |
Permission hints |
|---|
verify source provenance before install |
verify source provenance before install |
registry access, remote metadata pull, runtime dependencies may be required |
65 |
65 |
50 |
