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.
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.
Suggested baseline
Repository: Instagram-Hashtag-Scraper
Author: youmeat6678 · Source status: Clear source
A Python project for scraping Instagram posts based on specific hashtags.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
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
Pre-install score, evidence completeness, 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-perf-suite
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
Playwright (Automation + MCP + Scraper)
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing repo, missing license, broad permissions
checkout-agent
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, shell without guardrails, network without allowlist
| Dimension | mcp-perf-suite | Playwright (Automation + MCP + Scraper) | checkout-agent |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 81 · Manual review | 80 · Evidence missing | 85 · Manual review |
Score basis | Clear source, High execution risk, Universal | Source needs review, High execution risk, Claude | Clear source, High execution risk, OpenClaw |
Threat tags | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, identity privilege abuse, data exfiltration |
Control gaps | missing license, broad permissions, shell without guardrails | missing repo, missing license, broad permissions | missing license, shell without guardrails, network without allowlist |
Permission summary | Permission review, Network, Command | Permission review, Network, Secrets, Command | Permission review, Network, Secrets, Command |
Evidence completeness | 67% | 69% | 65% |
| Source & provenance | |||
Provenance | canyonlabz/mcp-perf-suite | Source needs review | openclaw/skills |
Freshness | 2026-04-06 | 2026-03-12 | 2026-04-02 |
| Risk & permission signals | |||
Audit signals | No explicit signals | needs credentials, network access, runs shell, writes files | needs credentials, network access |
Permission hints | repository clone, local runtime dependencies | review skill metadata before install, check required credentials in skill docs, requires local binaries: node, npx | verify source provenance before install |
| Install & compatibility | |||
Supported tools | Universal | Codex, OpenClaw, Claude, Cursor, Universal | OpenClaw |
Install method | script-backed | instruction-only | script-backed |
Install friction | |||
| Community | |||
Stars | 3 | 80 | 0 |
Repository: BotD
Author: fingerprintjs · Source status: Clear source
Free bot detection library that runs in the browser.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Repository: UI-TARS-desktop
Author: bytedance · Source status: Clear source
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra Topics: agent, agent-tars, browser-use, computer-use, cowork, gui-agent, gui-operator, mcp, mcp-server, multimodal, tars, ui-ta
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Repository: agent-browser
Author: vercel-labs · Source status: Clear source
Agent Browser skill from vercel-labs/agent-browser.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 67%
40 |
100 |
55 |
