Loading...
Loading...
Found 437 Skills
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.
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.
Transform song lyrics into vivid visual scene descriptions and image generation prompts — filtering for concrete imagery and rendering each distinct scene as a numbered canvas.
Expert guidance for Anthropic Claude API development including Messages API, tool use, prompt engineering, and building production applications with Claude models.
Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when generating or refining prompts for ComfyUI workflows.
Optimizer that refines and professionalizes AI agent skills through real usage — saves tokens, eliminates redundancy, and tightens instructions so skills cost less to run. Learns from mistakes, reviews quality, and improves over time. Observes skill execution in the current conversation, analyzes up to four sources (conversation friction, file diffs, user feedback, static diagnostic) plus accumulated lessons, and proposes concrete improvements to the target skill's SKILL.md. Works with Claude Code and compatible SKILL.md-based agent frameworks. Use after executing any skill: `/skill-optimizer [name]` or `/skill-optimizer` to auto-detect. `--review` processes accumulated lessons.
Turn a rough idea into a structured prompt or skill scaffold with explicit objective, inputs, workflow, outputs, and a concrete file plan. Use this whenever the user wants to design a new prompt or skill, scaffold a skill-like workflow, mentions "scaffold," "blueprint," "structure," or "plan" for a prompt, or arrives with a vague request that needs to be shaped before implementation — even if they don't explicitly ask to scaffold.
Generate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check (aspect ratio correction), prompt engineering, avatar resolution, and voice selection. Required for any HeyGen video generation. Replaces deprecated endpoints with v3. Use when: (1) generating any HeyGen video (via API or otherwise), (2) sending a personalized video message (outreach, update, announcement, pitch, knowledge), (3) creating a HeyGen presenter-led explainer, tutorial, or product demo with a human face, (4) "make a video of me saying...", "send a video to my leads", "record an update for my team", "create a video pitch", "make a loom-style message", "I want to appear in this video", "generate a HeyGen video", "make a talking head video". Accepts avatar_id from heygen-avatar for identity-first HeyGen videos, or uses a stock presenter. Returns video share URL + HeyGen session URL for iteration. Chain signal: when the user wants to create/design an avatar AND make a video in the same request, run heygen-avatar first, then return here. Conjunctions to watch: "and then", "and immediately", "first...then", "X and make a video", "design [presenter] and record" = always CHAIN. If the user provides a photo AND wants a video, route to heygen-avatar first. NOT for: avatar creation or identity setup (use heygen-avatar first), cinematic footage or b-roll without a presenter, translating videos, TTS-only, or streaming avatars.
Analyze and optimize system prompts using a structured prompting guidelines framework — AI-powered analysis and rewriting. Use when a prompt needs improvement, experiment results show quality gaps, or you want a structured review of an existing system prompt. Do NOT use when production traces show failures (use analyze-trace-failures first to identify patterns). Do NOT use to build evaluators (use build-evaluator).
Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces stunning, professional-quality photography through generative AI tools.
Use when the user wants a full feature-development chain: clarify a rough feature idea into a prompt, review it with the user, then hand it to grill-with-docs, to-prd, to-issues, and tdd.
Convert a local AGENT.md into a Claude Code optimized agent. Audits one agent against Claude Code runtime behavior, creates a per-agent DAG rewrite plan with source-backed guardrails, and optionally rewrites the frontmatter and system-prompt body so the agent is thinner, more role-specific, and better aligned with Claude's agent runtime. Use when the user says "convert this agent to Claude", "normalize this AGENT.md", "thin this agent", or "rewrite this persona for Claude Code".