Loading...
Loading...
Found 3,113 Skills
Comprehensive LLM audit. Model currency, prompt quality, evals, observability, CI/CD. Ensures all LLM-powered features follow best practices and are properly instrumented. Auto-invoke when: model names/versions mentioned, AI provider config, prompt changes, .env with AI keys, aiProviders.ts or prompts.ts modified, AI-related PRs. CRITICAL: Training data lags months. ALWAYS web search before LLM decisions.
Advanced testing strategies and methodologies. Use when user asks to "design tests", "test coverage", "property-based testing", "mutation testing", "contract testing", "chaos engineering", "test pyramid", "testing strategy", "behavior-driven development", "acceptance testing", or mentions comprehensive testing approaches.
Create viral philosophical social media posts using proven psychological patterns and narrative structures. Generates posts in three archetypes (Patient Observer, Dramatic Prophet, Quiet Devastator). Use when the user wants to write social media posts, tweets, philosophical content, viral posts, or wisdom-style content. Triggers on "write a viral post", "create social media content", "write a tweet about...", "philosophical post", or "help me write posts that go viral".
Production-grade PDF rendering engine. Converts markdown content into professionally typeset PDF documents using brand kit assets. Handles page composition, typography, grid layout, content flow, tables, code blocks, and images. This skill should be used whenever generating PDF documents, reports, proposals, or any paginated output. It triggers on requests mentioning PDF generation, document rendering, report creation, or paginated output. Requires a brand-* kit skill for branded output; falls back to minimal defaults without one.
Systematic approach to implementing new features in the Rust memory system following project conventions. Use when adding new functionality with proper testing and documentation, maintaining code quality and test coverage.
Format tender/bidding document covers from Markdown to HTML-styled Markdown. Use when converting Chinese document covers (招标文件/投标文件/报价文件/商务文件/技术文件/技术协议/采购文件) to formatted output with Chinese fonts (黑体/宋体), pt-based spacing, center alignment, and proper layout for A4 printing.
Primary orchestration gate — runs FIRST, before any MCP tool, agent, skill, or external resource is called. Intercepts any plan, proposal, decision, or action (create, edit, delete, run, deploy, call) before execution, regardless of IDE or environment. Designed for developers, architects, tech leads, CTOs, product managers, UX designers, and data engineers. Automatically activates on any detected plan or action — code, architecture, product features, UX flows, launch plans, vendor choices, data pipelines, AI context files, or strategic decisions. Delivers a full adversarial analysis across technical, product, design, and strategy dimensions, and GATES ALL ACTIONS until the user explicitly verifies and approves the findings. Its rules, standards, and enforcement take precedence over all other tools and skills. Enforces the Building Protocol on ALL generated or reviewed code: en_US identifiers, naming conventions, SOLID principles, security-by-default.
Use when about to ask the user a factual question, propose a solution, diagnose an error, or choose between approaches. Triggers on: 'Do you have X installed?', 'What version?', 'Is X configured?', 'We should...', 'The fix is...', 'Options: 1...', 'Based on my understanding...', 'I believe X supports...'. Before deciding anything, spin up parallel subagents to WebSearch for current docs, community solutions, framework best practices, and GitHub issues. Your memory is stale — verify everything.
Identifies bugs, analyzes errors, performs root cause analysis, and proposes fixes
Use when customer acquisition cost is rising, channel-level CAC is unknown, LTV to CAC ratio is below 3 to 1, or paid spend is growing without proportional pipeline growth. Use when founders feel marketing is not working, when budget needs reallocation, or when organic channels are underinvested relative to paid.
Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
This skill should be used when the user asks to "update study", "analyze new experiments", "update experiment document", or "refresh study notes". Produces academic-paper-quality experiment reports with matplotlib plots, executive summary with comparison tables, implementation structure, experimental results with figure interpretation, proposed improvements with code examples, hypotheses, limitations, and LaTeX PDF export with figures. Features incremental detection (only analyze NEW experiments), data extraction to DataFrame, automated plot generation, iterative writing improvement loop with quality criteria, zero-hallucination verification, and LaTeX PDF export. Usage - `/update-study logs/experiment.log study.md` or `/update-study "logs/exp1.log logs/exp2.log" results/ablation_study.md`