Loading...
Loading...
Found 1,660 Skills
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.
Create and run orq.ai experiments — compare configurations against datasets using evaluators, analyze results, and generate prioritized action plans. Use when evaluating LLM agents, deployments, conversations, or RAG pipelines end-to-end. Do NOT use without a dataset and evaluators. Do NOT use for cross-framework comparisons with external agents (use compare-agents).
Read production traces, identify what's failing, and build failure taxonomies using open coding and axial coding methodology. Use when debugging agent or pipeline quality, investigating "why are my outputs bad?", or before building any evaluator — error analysis must come first. Do NOT use when you already have identified failure modes and need evaluators (use build-evaluator) or datasets (use generate-synthetic-dataset).
Runs available security scanning tools against the current project and produces a consolidated markdown report. Auto-detects installed tools (gitleaks, semgrep, grype, npm audit, bandit, pip-audit, gosec, govulncheck, cargo audit, bundle-audit) and activates language-specific scanners based on project files. Gracefully skips missing tools and provides installation hints. By default scans the entire target directory. Pass --full to make the intent explicit (useful in workflows that combine full-codebase and diff-only scans). Use when running security scans, checking for vulnerabilities, detecting leaked secrets in git history, or validating security posture before commits or releases. Pairs with security-review for a complete security workflow.
Automates ingestion of documents into the Obsidian wiki (obsidian-wiki) using the wiki-ingest pipeline. Handles deduplication via manifest, frontmatter, and cross-links; triggers on user request within the obsidian-wiki project context.
Plan and orchestrate end-to-end video production pipelines in ComfyUI with validation gates and error recovery. Handles img2vid, txt2vid, vid2vid, and multi-shot video production. Produces pipeline plans with correct step ordering (generate, validate, animate, validate, concat), model selection, retry strategies (seed randomization, parameter adjustment, model fallback), and VRAM-aware resource management. Use when asked to make a video, animate images, create a multi-shot video, set up a video pipeline, or orchestrate video production in ComfyUI. Does NOT cover still image generation, prompt writing, workflow building for non-video tasks, video editing in external tools, model training, installation, or hardware recommendations.
Use this skill whenever reverse-engineering a Sketch file (or Figma export with similar shape) into pixel-perfect React + CSS — covers the iteration mental model, tree reconstruction, layout inference algorithms, geometry math, visual-regression diffing, and the style/typography/path conversions that make "improvement without regression" enforceable. Trigger even if the user doesn't explicitly mention "algorithms" but is converting a design source into web code, building a design-to-code pipeline, or struggling to make incremental fidelity improvements without breaking previously-converted output.
Guides research engineering and science on LLM tokens—hypotheses about context use, tokenization, compression, and inference efficiency; rigorous benchmarks (tokens per task, quality–cost Pareto); ablation design; instrumentation and reproducible logs; and research memos that inform product decisions. Use when designing token-efficiency experiments, measuring context utilization, comparing compression or routing methods, analyzing tokenizer effects, or writing technical reports on token/cost trade-offs—not for phased cost roadmaps and owners (ai-token-improvement-plan-engineer), production context pipeline implementation (ai-context-engineer), single-prompt edits (prompt-engineer), general non-token AI research (ai-researcher), or shipping features (ai-engineer).
Guides product management for human data platforms—annotation and labeling products, workforce workflows, task design, quality systems (gold sets, adjudication, inter-annotator agreement), customer ML-team project delivery, contributor experience, and privacy-safe handling of human-generated training data. Use when prioritizing roadmap for labeling/RLHF/eval data platforms, writing PRDs for annotation or QA features, defining success metrics for throughput and quality, scoping enterprise customer workflows, or balancing cost-quality-speed tradeoffs—not for hands-on model training (data-scientist), warehouse/analytics pipelines (data-warehouse-engineer), generic BRD workshops without product lens (business-analyst), AI solution architecture for copilots (applied-ai-architect-commercial-enterprise), or control implementation for audits (compliance-engineer). UX flows: product-designer. Eval harnesses: prompt-engineer-agent-prompts-evals. Pricing/packaging for platform: product-management-monetization.
Organize design assets, optimize images and fonts, maintain brand asset libraries, implement version control for assets, and enforce naming conventions. Use when optimizing images for web, converting fonts to WOFF2, organizing asset directories, setting up responsive image pipelines, or managing logo variants.
Low-latency streaming text-to-speech via OpenAI TTS API — adaptive sentence chunking, concurrent fetch pipelining, six voices.
Manual test planning, writing, reviewing, executing, and maintaining test cases. Use when: user asks to write test cases, create a test plan, run manual tests, review test coverage, update tests after feature changes, or asks 'how should I test this'. Also trigger after implementing features that change system behavior — per CLAUDE.md, updating the manual test plan is mandatory. Covers API/backend, frontend, pipeline/workflow, AI/LLM, and infrastructure testing patterns.