Loading...
Loading...
Found 2,066 Skills
Autonomous ML experimentation framework by Andrej Karpathy. AI agent autonomously modifies train.py, runs 5-minute GPU experiments, evaluates with val_bpb, and commits only improvements via git ratcheting — so you wake up to 100+ experiments and a better model. Use when setting up autoresearch, writing program.md directives, interpreting results, configuring hardware, or running overnight autonomous ML experiments. Triggers on: autoresearch, autonomous ml experiments, overnight gpu experiments, karpathy autoresearch, train.py experiments, val_bpb, program.md research directives, ai runs experiments.
Use this skill when translating Figma designs to code, interpreting design specs, matching visual fidelity, or bridging designer-developer handoff. Triggers on Figma implementation, design-to-code, pixel-perfect, design handoff, auto layout to flexbox, Figma tokens, component variants to props, and any task requiring faithful implementation of design mockups.
Tealium platform help — enterprise Customer Data Platform (CDP), Real-Time CDP, Composable CDP, iQ Tag Management, EventStream, AudienceStream, 1300+ connectors, identity resolution, consent management, V3 API. Use when setting up Tealium CDP, tags not firing or loading slowly, connectors failing or data not flowing to destinations, visitor profiles not merging across channels, identity resolution producing duplicate profiles, choosing between Tealium and Segment or mParticle, configuring EventStream or AudienceStream, or working with the Tealium V3 API. Do NOT use for general email marketing (use /sales-email-marketing) or CRM data dedup without Tealium (use /sales-data-hygiene).
Helps engineering managers support direct report growth — produces a stage-by-stage model of engineering impact (Circles of Influence), a framework for non-linear career planning (Tarzan Method), diagnostic signals for stalled growth, conversation scripts for career talks, and a promotion readiness vs. timing distinction. Use when the user says "career growth," "promotion," "career path," "this person wants to grow," "career conversation," "what's next for this person," "career ladder," "IC vs manager track," "how do I help my report advance," "help someone grow," or "engineer wants a promotion." Do NOT use for formal written performance reviews or underperformance — use performance-reviews instead.
Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational | learning | operational_health | compliance_or_safety), committed-vs-aspirational interpretation, evidence quality assessment, learning synthesis, and next-cycle recommendations. Refuses to retroactively change targets or shrink committed scope, average away guardrail KRs, treat 0.7 as success for committed or compliance_or_safety KRs, equate effort with impact, or use scores for individual performance. Hands off to iterate-lessons-log, iterate-retrospective, define-hypothesis, measure-dashboard-requirements, measure-instrumentation-spec, and foundation-okr-writer.
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
Generate code from templates and patterns including scaffolding, boilerplate generation, AST-based code generation, and template engines. Use when generating code, scaffolding projects, creating boilerplate, or using templates.
Systematic framework for evaluating scholarly and research work based on the ScholarEval methodology. This skill should be used when assessing research papers, evaluating literature reviews, scoring research methodologies, analyzing scientific writing quality, or applying structured evaluation criteria to academic work. Provides comprehensive assessment across multiple dimensions including problem formulation, literature review, methodology, data collection, analysis, results interpretation, and scholarly writing quality.
This skill provides production-ready AI chat UI components built on shadcn/ui for conversational AI interfaces. Use when building ChatGPT-style chat interfaces with streaming responses, tool/function call displays, reasoning visualization, or source citations. Provides 30+ components including Message, Conversation, Response, CodeBlock, Reasoning, Tool, Actions, Sources optimized for Vercel AI SDK v5. Prevents common setup errors with Next.js App Router, Tailwind v4, shadcn/ui integration, AI SDK v5 migration, component composition patterns, voice input browser compatibility, responsive design issues, and streaming optimization. Keywords: ai-elements, vercel-ai-sdk, shadcn, chatbot, conversational-ai, streaming-ui, chat-interface, ai-chat, message-components, conversation-ui, tool-calling, reasoning-display, source-citations, markdown-streaming, function-calling, ai-responses, prompt-input, code-highlighting, web-preview, branch-navigation, thinking-display, perplexity-style, claude-artifacts
Run MTHDS methods and interpret results. Use when user says "run this pipeline", "execute the workflow", "execute the method", "test this .mthds file", "try it out", "see the output", "dry run", or wants to execute any MTHDS method bundle and see its output.
Pragmatic qualitative analysis for interview data in sociology research. Guides you through systematic coding, interpretation, and synthesis with quality checkpoints. Supports theory-informed (Track A) or data-first (Track B) approaches.
Prevents premature execution on ambiguous requests. Analyzes request clarity using 5W1H decomposition, surfaces hidden assumptions, and generates structured clarifying questions before work begins. Use at the start of any non-trivial task, or when a request could be interpreted multiple ways. Triggers on "뭘 원하는건지", "요구사항 정리", "clarify", "what exactly", "scope", "requirements", "정확히 뭘", "before we start".