All Skills

Guide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or orchestrator that requires isolated context and deep specialization. Works with any agent that supports subagent delegation. Triggers on "create subagent", "new agent", "specialized assistant", "create verifier". Do NOT use for Cursor-specific subagents (use cursor-subagent-creator instead).

Use when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team, stress test assumptions, audit evidence quality, or find blind spots before committing. Do NOT use for building plans, making decisions, or generating solutions — this skill only challenges and critiques.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices". Focuses on visual design and interaction patterns. Do NOT use for performance audits (use core-web-vitals), SEO (use seo), or comprehensive site audits (use web-quality-audit).

Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.

Generate comprehensive BIM model validation reports. Check data quality, completeness, and compliance with standards.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

Manage Jira issues via Atlassian MCP — search, create, update, transition status, and handle sprint tasks. Auto-detects workspace configuration. Use when user says "create a Jira ticket", "update my sprint", "check Jira status", "transition this issue", "search Jira", or "move ticket to done". Do NOT use for Confluence pages (use confluence-assistant).

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to Interactive, or optimizing for Lighthouse scores. Triggers on: web performance, bundle size, page speed, slow site, lazy loading. Do NOT use for Core Web Vitals-specific fixes (use core-web-vitals), running Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).

Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or triage PR comments. Fetches comments via GitHub CLI, classifies by severity, applies fixes with user confirmation, commits with proper format, replies to threads.

Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors). Use when completing features, making design decisions, or when user asks to understand code better. Triggers on "learning exercise", "help me understand", "teach me", "why does this work", or after creating new files/modules. Do NOT use for urgent debugging, quick fixes, or when user says "just ship it".

Guide product managers through calculating Total Addressable Market (TAM), Serviceable Available Market (SAM), and Serviceable Obtainable Market (SOM) for a product idea by asking adaptive, contextual

Guide product managers through structured PRD (Product Requirements Document) creation by orchestrating problem framing, user research synthesis, solution definition, and success criteria into a cohes

Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts". Focuses specifically on the three Core Web Vitals metrics. Do NOT use for general web performance (use perf-web-optimization), Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).

This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimization", mentions "state-of-the-art DSPy optimizer", "joint instruction tuning", or needs maximum performance from a DSPy program with substantial training data (200+ examples).

Capture current session state without stopping

Coordinates security scanning (secrets + deps). Delegates to ln-761 + ln-625(mode=vulnerabilities_only). Generates SECURITY.md, pre-commit hooks, CI workflow.

Generate Excalidraw diagrams from natural language descriptions. Outputs .excalidraw JSON files openable in Excalidraw. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", "generate an Excalidraw file", "draw an ER diagram", "create a sequence diagram", or "make a class diagram". Supports flowcharts, relationship diagrams, mind maps, architecture, DFD, swimlane, class, sequence, and ER diagrams. Can use icon libraries (AWS, GCP, etc.) when set up. Do NOT use for code architecture analysis (use the architecture skills), Mermaid diagram rendering (use mermaid-studio), or non-visual documentation (use docs-writer).

Browser debugging, performance profiling, and automation via Chrome DevTools MCP. Use when user says "debug this page", "take a screenshot", "check network requests", "profile performance", "inspect console errors", or "analyze page load". Do NOT use for full E2E test suites (use playwright-skill) or non-browser debugging.

Python resilience patterns including automatic retries, exponential backoff, timeouts, and fault-tolerant decorators. Use when adding retry logic, implementing timeouts, building fault-tolerant services, or handling transient failures.

Fast lookup table for 32+ SaaS finance metrics with formulas, benchmarks, and when to use each. Includes red flags and decision frameworks.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing. Do NOT use for quick page debugging or network inspection (use chrome-devtools instead).