All Skills

Generate minimal, research-backed CLAUDE.md / AGENTS.md / COPILOT.md context files for coding agent CLIs. Based on "Evaluating AGENTS.md" (ETH Zurich, Feb 2026) which found that auto-generated context files DECREASE performance by ~3% and increase costs by 20-23%, while minimal human-written files improve performance by ~4%. Use when the user says "generate CLAUDE.md", "create AGENTS.md", "generate context file", "agentmd", "create recommended CLAUDE.md", "generate agent instructions", "init context file", or any request to create/improve a coding agent context file for a repository. Replaces the default /init command which generates bloated, counterproductive context files.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Configure TLS certificates and encryption for secure communications. Use when setting up HTTPS, securing service-to-service connections, implementing mutual TLS (mTLS), or debugging certificate issues.

Hugging Face Transformers with PyTorch Lightning - LightningModule integration, distributed training (FSDP/DeepSpeed), PEFT (LoRA/QLoRA), data pipelines with HF Datasets, evaluation metrics, and common NLP tasks

Automate Procfu tasks via Rube MCP (Composio). Always search tools first for current schemas.

Implement production-ready service mesh deployments with Istio, Linkerd, or Cilium. Configure mTLS, authorization policies, traffic routing, and progressive delivery patterns for secure, observable microservices. Use when setting up service-to-service communication, implementing zero-trust security, or enabling canary deployments.

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate in a week", "rapid prototype", "test with users", or "de-risk before building". Covers mapping, sketching, deciding, prototyping, and testing. For ongoing experimentation, see lean-startup. For customer job analysis, see jobs-to-be-done.

Graph database implementation for relationship-heavy data models. Use when building social networks, recommendation engines, knowledge graphs, or fraud detection. Covers Neo4j (primary), ArangoDB, Amazon Neptune, Cypher query patterns, and graph data modeling.

Coordinate UX/UI design work across platforms. Launches the UX System Coordinator to orchestrate design specialists.

Automate Dnsfilter tasks via Rube MCP (Composio). Always search tools first for current schemas.

Worker that checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Validates architectural decisions via MCP Ref: (1) Optimality (2) Compliance (3) Performance. Reports issues with SEC-, PERF-, MNT-, ARCH-, BP-, OPT- prefixes.

Automate Doppler Secretops tasks via Rube MCP (Composio). Always search tools first for current schemas.

This skill should be used when the user asks to "validate a finding", "check if a vulnerability is real", "triage a security finding", "confirm a vulnerability", "determine if a finding is a true positive or false positive", or provides a security finding for review. It validates security vulnerability findings by tracing data flows, verifying exploit conditions, analyzing security controls, and optionally testing attack vectors against a live application.

Automate Demio tasks via Rube MCP (Composio). Always search tools first for current schemas.

Proactive US tax advisor — ask any tax question or request structured analysis

Automated tech debt cleanup worker (L3). Reads codebase audit findings, applies safe auto-fixes for low-risk issues (unused imports, dead code, commented-out code, deprecated aliases). Confidence >=90% only. Creates single commit with summary.

Write readable, maintainable code through disciplined naming, small functions, and clean error handling. Use when the user mentions "code review", "naming conventions", "function too long", "code smells", or "readable code". Covers SRP, comment discipline, formatting, and unit testing. For refactoring techniques, see refactoring-patterns. For architecture, see clean-architecture.

Automate Dromo tasks via Rube MCP (Composio). Always search tools first for current schemas.

Engineer word-of-mouth and virality using the STEPPS framework (Social Currency, Triggers, Emotion, Public, Practical Value, Stories). Use when the user mentions "go viral", "word of mouth", "shareable content", "social currency", or "why people share". Covers environmental triggers and high-arousal emotional content. For sticky messaging, see made-to-stick. For persuasion tactics, see influence-psychology.

Audit websites and landing pages for conversion issues and design evidence-based A/B tests. Use when the user mentions "landing page isn''t converting", "conversion rate", "A/B test", "why visitors leave", or "objection handling". Covers funnel mapping, persuasion assets, and objection/counter-objection frameworks. For overall marketing strategy, see one-page-marketing. For usability issues, see ux-heuristics.

This skill should be used when working with Rust code, reviewing Rust code, managing Rust dependencies, creating Rust projects, or fixing Rust compilation errors. It provides strict coding standards (especially FAIL FAST error handling), workspace architecture guidance, dependency management automation, and common Rust patterns.

Automate Documenso tasks via Rube MCP (Composio). Always search tools first for current schemas.

Personalize COG Second Brain workflow through role pack selection and vault initialization

Researches real-world problems, competitor solutions, and customer complaints before test planning. Posts findings as Linear comment for ln-522 and ln-523.