Loading...
Loading...
Found 2,082 Skills
Write titles for blog posts, deep dives, and hub articles. 15 proven formulas + 10 Commandments evaluation. Generate 10+ options, select best through systematic criteria.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
Score assistant responses for guidance & actionability on a strict 1-5 scale, then return strict JSON only with dimension, score, rationale, and improvement suggestions. Use when the user asks to evaluate how actionable, helpful, or step-by-step a response is.
Specialized business logic evaluator for the Evaluate-Loop. Use this for evaluating tracks that implement core product logic — pipelines, dependency resolution, state machines, pricing/tier enforcement, packaging. Checks feature correctness against product rules, edge cases, state transitions, data flow, and user journey completeness. Dispatched by loop-execution-evaluator when track type is 'business-logic', 'generator', or 'core-feature'. Triggered by: 'evaluate logic', 'test business rules', 'verify business rules', 'check feature'.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response, single_step, trajectory, RAG), CLI management commands, SDK-based creation, and example management. Uses the langsmith CLI tool.
Evaluate and improve skills through measured testing. Run trigger evaluations to test whether skill descriptions cause correct activation, optimize descriptions via automated train/test loops, benchmark skill output quality with A/B comparisons, and validate skill structure. Use when user says "improve skill", "test skill triggers", "optimize description", "benchmark skill", "eval skill", or "skill quality". Do NOT use for creating new skills (use skill-creator-engineer).
AI creative director with recursive self-assessment. Generates concepts using world-class methodologies (SIT, TRIZ, Lateral Thinking, bisociation), scores against 6 weighted criteria with Cannes/D&AD/HumanKind calibration, and recursively refines until the 9+ threshold is reached. Accepts briefs in any format — text, voice transcript, PDF, or raw notes. Use when the user asks to generate creative concepts, brainstorm campaign ideas, develop a Big Idea or campaign platform, evaluate or critique existing creative work, find consumer insights, or shares a brief for ideation. Do not use for media planning, production budgeting, brand identity/logo design, copywriting final drafts, or market research data collection.
Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when another skill needs a quality gate on its output. Also triggers on: "score this landing page", "expert panel these email variants", "rate this headline", "panel these charts".
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent delegates a code task with 'MODE: MORE_EFFORT', the user selects 'More Effort' code generation mode, or the task explicitly requests iterative refinement for higher code quality. Do NOT use for single-pass code generation (Lite mode), experiment pipeline orchestration (use experiment-pipeline), or diagnosing a specific experiment failure (use experiment-craft).
Use this skill when the user asks to "evaluate MCP tools", "test tool selection", "improve tool descriptions", "check MCP schema quality", "eval my MCP server", or wants to measure whether Claude uses their MCP tools correctly. Tests tool selection accuracy, analyzes schema quality, and iteratively optimizes descriptions. Companion to build-mcp-server.
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.