发现 AI Agent Skills

Table extraction from PDFs and images for RAG. Covers Camelot, Tabula, pdfplumber, TableTransformer (DETR), Amazon Textract Tables, Azure Document Intelligence. Conversion to markdown/CSV/JSON, merged-cell handling. USE WHEN: user mentions "table extraction", "PDF tables", "Camelot", "Tabula", "TableTransformer", "Textract tables", "Azure form recognizer tables", "markdown table for LLM" DO NOT USE FOR: general PDF text - use `pdf-extraction`; full OCR pipelines - use `ocr`

Create, list, and apply Stitch design systems from DESIGN.md using the verified Stitch MCP design-system tools and safe upload fallbacks.

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

Router for all Remotion skills

Three.js 3D building system with spatial indexing, structural physics, and multiplayer networking. Use when creating survival games, sandbox builders, or any game with player-constructed structures. Covers performance optimization (spatial hash grids, octrees, chunk loading), structural validation (arcade/heuristic/realistic physics modes), and multiplayer sync (delta compression, client prediction, conflict resolution).

Structure and review an OpenEvidence clinical consult while preserving clinician accountability and evidence traceability. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence core workflow a", "OpenEvidence clinical-consult", or a matching workflow request.

Workflow recovery protocol for resuming workflows after context loss, session interruption, or errors. Handles state reconstruction, artifact recovery, and seamless workflow continuation.

Discover and track emerging trends across Google Trends, Instagram, Facebook, YouTube, and TikTok to inform content strategy.

Scans all skill directories in the repository to generate a comprehensive global map of agent capabilities, inputs, and outputs. Use when you need to understand the full potential of your agent library or when a master agent needs to decide which sub-agent skill to invoke for a complex task.

Use when the user asks for vfx or a task matching the examples below. Turn a plain video clip into a cinematic AI-VFX shot at 1080p by default (or 4K / 720p on request). Give Claude a video and the change you want; it reads EVERY frame via local contact sheets and understands the audio, writes a Seedance-faithful prompt that locks your face, gestures, and camera move, then re-renders the same shot with the VFX baked in via Seedance reference-to-video.

Systematic bug investigation, resolution, and documentation. Use when fixing bugs that need thorough analysis, test coverage, and a formal bugfix report. Applies systematic debugging methodology, creates regression tests, and generates a standardized report in specs/bugfixes/<bug-name>/. For complex bugs, spawns competing implementation agents (including alternative harnesses like Kiro) and selects the best solution. Triggers on requests like "fix this bug", "debug and document this issue", or when a bug needs both resolution and documentation.

Retrieve curated public Regulations.gov comment details for explicit IDs through the Tiangong CLI. Use after comment discovery when a task needs comment text, docket/document linkage, dates, withdrawal or restriction state, organizational context, duplicate count, or optional attachment metadata; do not use to expose named personal-profile fields, download attachment bytes, submit comments, infer public sentiment, or make legal judgments.

Adversarially review a code change — assume it's broken, try to break it, and only report findings that survive an independent refutation pass. Use when the user wants a deep, skeptical review of a diff, PR, or branch ("adversarial review", "try to break this", "find what's wrong before I ship", "review this like a skeptic", "what will break in production"). Scales from a single inline pass to a multi-agent fan-out (one skeptic per domain → adversarial verify → synthesis). Distinct from a normal code review: it leads with concrete failure scenarios over style, distrusts the tests, and is honest about what it could not verify.

Orchestrate TestFlight distribution, groups, testers, and What to Test notes using asc. Use when rolling out betas.

Use when a working session is ending, the context window is nearly full, work needs to pass to a teammate or a fresh session, or the user says "hand this off", "write this up before we lose it", "I'm starting a new session", or "summarize where we are". Produces a handoff document that lets the next session resume without re-reading the transcript.

Finds YouTube micro-influencers and niche creators using apidojo's YouTube scraper on Apify. Triggers when the user asks to: find YouTube channels under 100k subscribers in a niche, discover emerging YouTube creators for sponsorship deals, find YouTubers covering a specific topic, identify high-engagement YouTube channels with smaller audiences, build a YouTube influencer outreach list, compare YouTube channel growth rates in a category, or find YouTube channels for affiliate or brand partnership programs. Returns channel name, subscriber count, total views, average views per video, and contact info. Ideal for brand sponsors, podcast networks, and affiliate marketing teams.

Image generation and presentations. Use when: - User asks for images: logos, icons, app assets, diagrams, flowcharts, architecture diagrams, patterns, textures, photo edits, restorations - User needs a presentation or slide deck Covers nanobanana CLI for image generation and Slidev for presentations.

Author or revise readable, flat-world Three.js game levels. Use for movement and camera routes, collision and navigation, encounter zones, landmarks, objectives, pickups, motivated lighting, visibility, deterministic level data, or desktop and mobile playthrough verification.