Agent Skills Hub

linkedin-sales-navigator-alt

Build targeted prospect lists by analyzing public LinkedIn profiles and business data to identify decision-makers, track career moves, and enrich leads for outreach.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.

docs-applying-content-quality

Standardizes markdown content with active voice, precise heading hierarchies, and WCAG AA accessibility compliance for documentation, web sites, and repository files.

serena-mcp

Semantic code analysis guide for Serena MCP. Automatically prioritizes Serena tools for symbols, references, and code memory to optimize context and efficiency.

semgrep

Run Semgrep static analysis scans on codebases using parallel subagents, multi-language detection, and Pro-enabled cross-file taint tracking.

debug-distributed

Debugging guide for AReaL distributed training issues, including hangs, NCCL errors, OOM, and numerical consistency in FSDP2/TP/CP/EP.

kagent

Expert guide for kagent: the Kubernetes-native framework for building, deploying, and managing AI agents, MCP tools, and A2A protocols.

sherlock-review

Evidence-based code review using Sherlock Holmes-style deductive reasoning to verify implementation claims, investigate bugs, and conduct root cause analysis.

security-assessment

Systematic security assessment using STRIDE threat modeling, OWASP top 10 review, and secure coding practices for code, architecture, and infrastructure.

testability-scoring

AI-driven web testability assessment using 10 core principles. Evaluates observability, controllability, and stability via Playwright and Vibium to identify testing bottlenecks and improve quality readiness.

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.