Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
Selected skills (3/4)
agent-memory-systems
davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/agent-memory-systems · Score 79
openai-realtime-console
openai/openai-realtime-console · Score 92
ui-ux-pro-max
nextlevelbuilder/ui-ux-pro-max-skill/tree/main/.claude/skills/ui-ux-pro-max · Score 82
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: openclaw/skills
Author: cinience · Source status: Clear source
Use when working with OpenSearch vector search edition via the Python SDK (ha3engine) to push documents and run HA/SQL searches.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 69%
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
agent-memory-systems
Execution risk：High
Threat tags：data exfiltration, memory context poisoning, human approval gap
Control gaps：missing license, network without allowlist, no human approval
openai-realtime-console
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
ui-ux-pro-max
Execution risk：High
Threat tags：data exfiltration, human approval gap
Control gaps：missing license, network without allowlist, no human approval
| Dimension | agent-memory-systems | openai-realtime-console | ui-ux-pro-max |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 79 · Manual review | 92 · Manual review | 82 · Manual review |
Score basis | Clear source, High execution risk, Claude | Clear source, High execution risk, Universal | Clear source, High execution risk, Claude |
Execution risk | High | High | High |
Threat tags | data exfiltration, memory context poisoning, human approval gap | unexpected code execution, data exfiltration, human approval gap | data exfiltration, human approval gap |
Control gaps | missing license, network without allowlist, no human approval | missing license, broad permissions, shell without guardrails | missing license, network without allowlist, no human approval |
Permission summary | Network, Command | Permission review, Network, Command | Network, Command |
Evidence completeness | 65% | 65% | 63% |
| Source & provenance | |||
Provenance | davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/agent-memory-systems | openai/openai-realtime-console | nextlevelbuilder/ui-ux-pro-max-skill/tree/main/.claude/skills/ui-ux-pro-max |
Category | Knowledge & RAG | Automation & Workflows | Design & Content |
Freshness | |||
| Risk & permission signals | |||
Audit signals | No explicit signals | metadata-only | No explicit signals |
Permission hints | registry access, remote metadata pull, runtime dependencies may be required | repository clone | registry access, remote metadata pull, runtime dependencies may be required |
| Install & compatibility | |||
Supported tools | Claude, Codex, Cursor, Universal | Universal | Claude, Codex, Cursor, Universal |
Install method | registry-install | script-backed | registry-install |
Install friction | |||
| Community | |||
Stars | 19.9K | 3.6K | 29.8K |
Repository: openai/skills
Author: openai · Source status: Clear source
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 67%
Repository: openclaw/skills
Author: neroagent · Source status: Clear source
Core memory resilience layer: WAL (Write-Ahead Log), Working Buffer, and three-layer memory integration.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 71%
Repository: openclaw/skills
Author: lookupmark · Source status: Clear source
Find and send local files to a chat channel (Telegram, Discord, WhatsApp, Signal, Slack).
Score basis：Clear source · High execution risk · OpenClaw · Evidence completeness 67%
Repository: openclaw/skills
Author: moltbotmolty-del · Source status: Clear source
Your agent forgets everything after compaction?
Score basis：Clear source · High execution risk · OpenClaw · Evidence completeness 67%
2026-02-04 |
2025-08-28 |
2026-02-04 |
50 |
75 |
50 |
