New in AI Agent Skills | Security Audit Articles: Security Audit Skills Worth Trying First (Nov 16, 2026)

Newly added in Security Audit: 10 new entries, ordered by real platform data. (content moderation review)

1. ruview-advanced-sensing

Author: ruvnet | Source: github | Downloads: 104,356

Advanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, persistent field model), cross-viewpoint fusion across multiple nodes, RF tomography (ISTA L1 solver, voxel grids), longitudinal biomechanics drift, pre-movement intention signals

2. cli-mcp

Author: cheaper-inference | Source: github | Downloads: 87,743

Inspect the MCP server status, list registered tools and scopes, run tool invocations, and manage MCP audit logs from the CLI.

3. cli-policy-audit

Author: cheaper-inference | Source: github | Downloads: 87,743

Inspect audit logs, manage access policies, view telemetry data, and review request history from the CLI. Filter by event type, user, or time range for compliance workflows.

4. omni-github-skills

Author: cheaper-inference | Source: github | Downloads: 87,743

Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across many tool and provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets

5. omni-mcp

Author: cheaper-inference | Source: github | Downloads: 87,743

"Connect to the OmniRoute MCP server (3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across its permission scopes.

6. omni-proxies

Author: cheaper-inference | Source: github | Downloads: 87,743

Configure HTTP/HTTPS/SOCKS proxies for upstream provider requests. Set per-provider or global proxy rules, test connectivity, and manage proxy rotation.

7. ponytail

Author: cheaper-inference | Source: github | Downloads: 87,743

"External agent skill (MIT, github.com/DietrichGebert/ponytail). Forces the laziest solution that actually works: question whether the task needs to exist at all (YAGNI), reuse what is already in the codebase, reach for the standard library before custom code, native platform features before

8. code-review

Author: shareAI-lab | Source: github | Downloads: 80,443

Perform thorough code reviews with security, performance, and maintainability analysis.

9. claude-md-improver

Author: anthropics | Source: github | Downloads: 47,457

Audit and improve CLAUDE.md files in repositories.

10. claude-security

Author: anthropics | Source: github | Downloads: 47,457

"Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose).

Direct links


Curated by StackPilot —— the ai agent skills. Browse all categories for the full directory.