AI & ML

flashinfer-ai-flashinfer-bench Skill

Validate the correctness and completeness of a FlashInfer Trace dataset. Use when checking dataset quality, verifying definitions/workloads/solutions/traces, debugging data issues, or preparing a dataset for release.

flashinfer-ai-flashinfer-bench Skill

Auto-collect workloads from SGLang inference runs using FlashInfer logging API. Dumps tensors, sanitizes them according to kernel definitions, and submits PR to flashinfer-trace workload repo.

flashinfer-ai-flashinfer-bench Skill

Add pytest tests to validate reference implementations in the flashinfer-trace HuggingFace dataset against FlashInfer or SGLang ground truth. Use when validating kernel definitions, adding tests for new op_types, or verifying reference implementations are correct.

flashinfer-ai-flashinfer-bench Skill

Open the per-definition pair of PRs that publishes a model onboarding — PR 2 to the HuggingFace flashinfer-trace dataset (definition + reference test + baseline solution + workloads + blobs + eval traces) and PR 1 to flashinfer-bench (docs/model_coverage.mdx update only). Use as Phase 4 of /onboard-model.

flashinfer-ai-flashinfer-bench Skill

Generate Definition JSON files for the flashinfer-trace HuggingFace dataset by harvesting them from a short SGLang inference pass (FlashInfer's @flashinfer_api(trace=...) dumper) — or, as a fallback, by manually transcribing the schema from SGLang sources when FlashInfer doesn't yet have a trace template. Use when adding a new model, extracting GPU kernels (MLA, MoE, GQA, RMSNorm, GEMM, GDN, RoPE, sampling), or filling gaps in the dataset.

zai-org Bundle

Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to describe, caption, summarize, or interpret the content of images, videos, or files. Supports single/multiple inputs, URLs, local paths, and base64 (images only).

zai-org Bundle

A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image and output relative coordinates normalized to 0-1000 based on image size. Coordinate formats include 2D bounding box (default), 2D points, and 3D bounding box. GLM-V also supports spatiotemporal localization and tracking of multiple prompt-specified targets in videos, outputting 2D bounding boxes per second.

openclawq Skill

Use the `clawmonitor` CLI/TUI to inspect OpenClaw sessions, model health, token usage, and gateway service health.

lksrz Skill

PRIMARY skill for any cnvs.app board work. Collaborate on a cnvs.app whiteboard (canvas / board / drawing surface) in real time — read shared state, add/update/move/delete text, links, sticky notes, strokes, images, and Mermaid diagrams (flowcharts, sequence diagrams, class and ER diagrams, mind maps, gantt charts, concept maps, and more), and render the SVG preview when the board has drawings. Use whenever the user references a cnvs.app board (URL `https://cnvs.app/#<id>`, `cnvs://board/<id>/...`, or `/mcp` endpoint), asks to draw / sketch / diagram / flowchart / annotate / brainstorm / collaborate / edit / watch / create content on a shared whiteboard or canvas, or drops a board ID expecting the agent to act on it — even if they don't name cnvs.app, MCP, or REST. For push-to-model notifications on human edits this skill delegates to the generic `mcp-listen` skill; install both for the full loop.

ddien Bundle

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

ddien Bundle

REQUIREMENT. Use this skill FIRST when starting ANY new feature, bug fix, or refactoring task. It creates a structured status file in `docs/status/` to track the plan and progress.

akrindev Bundle

Generate text content using Google Gemini models via scripts/. Use for text generation, multimodal prompts with images, thinking mode for complex reasoning, JSON-formatted outputs, and Google Search grounding for real-time information. Triggers on "generate with gemini", "use gemini for text", "AI text generation", "multimodal prompt", "gemini thinking mode", "grounded response".

mossaka Bundle

Forensic analysis of GitHub Agentic Workflow runs using gh aw logs and gh aw audit. Use when: (1) Investigating why agentic workflows failed across multiple runs, (2) User says 'forensic analysis' or 'analyze workflow runs', (3) Comparing workflow behavior across time periods or code changes, (4) Diagnosing systematic issues with a specific engine (claude, copilot, codex, gemini), (5) Auditing MCP server connectivity, tool usage, and safe outputs across runs.

datahub-project-datahub-skills Bundle

Use this skill when the user needs to set up a DataHub connection, install the DataHub CLI, configure authentication, verify connectivity, set default scopes, or create agent configuration profiles. Triggers on: "set up DataHub", "connect to DataHub", "install datahub CLI", "configure DataHub", "set default platform", "focus on domain X", "create profile", or any request to establish, configure, or troubleshoot DataHub connectivity.

zai-org Bundle

Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to generate prompts from reference images/videos, create AI art prompts, or get prompt engineering suggestions from visual content.

zai-org Bundle

Screen and evaluate resumes against criteria using ZhiPu GLM-V multimodal model. Reads multiple resume files (PDF/DOCX/TXT), compares against user-defined screening criteria, and outputs a Markdown table with pass/fail analysis. Use when the user wants to filter resumes, compare candidates, or batch-evaluate job applications.

zai-org Bundle

Write a textual content based on given document(s) and requirements, using ZhiPu GLM-V multimodal model. Read and comprehend one or multiple documents (PDF/DOCX), write a content in Markdown format according to the specified requirements. Use when the user wants to draft a paper/article/essay/report/review/post/brief/proposal/plan, etc.

miles990-self-evolving-agent Bundle

自我進化 Agent：給定目標，自主學習並迭代改進直到完成。整合 superpowers 工作流紀律。

datahub-project-datahub-skills Bundle

Plans new DataHub connectors by classifying the source system, researching it using a dedicated agent or inline research, and generating a _PLANNING.md blueprint with entity mapping and architecture decisions. Use when building a new connector, researching a source system for DataHub, or designing connector architecture. Triggers on: "plan a connector", "new connector for X", "research X for DataHub", "design connector for X", "create planning doc", or any request to plan/research/design a DataHub ingestion source.

paleo Skill

Conventions for writing sharp, concise prose and Markdown, for human readers and AI agents. Read before writing or editing documentation, READMEs, instructions, agent skills, or any prose text.

akrindev Bundle

Generate text embeddings using Gemini Embedding API via scripts/. Use for creating vector representations of text, semantic search, similarity matching, clustering, and RAG applications. Triggers on "embeddings", "semantic search", "vector search", "text similarity", "RAG", "retrieval".

ogprotege Bundle

Create, update, and maintain clear, accurate, and well-organized technical documentation for complex codebases. This agent focuses on understanding the current state of the code and existing documentation before proposing or making changes, ensuring documentation remains up to date, discoverable, and trustworthy for developers.

venturo-id Skill

Use when the user wants to verify their Venturo Arsenal install is healthy, asks for /venturo-arsenal-check, says the guard hook or team MCP servers seem broken, or is onboarding a new laptop and wants proof everything landed.

zeulewan Skill

Chrome DevTools MCP for browser automation. Five servers configured for parallel agents. Auto-select available server, cleanup when done.

useorgx Skill

Use when managing work through the OrgX OpenClaw plugin — reporting progress, requesting decisions, registering artifacts, syncing memory, checking quality gates, inspecting agent config policy, or viewing org status. Activates for phrases like "report progress", "request approval", "check orgx", "sync with orgx", or "register artifact".

useorgx Skill

Power-user OrgX skill for OpenClaw. Use when you explicitly need the full mutation surface for entity CRUD, run control, checkpoints, stream reassignment, or agent-config policy changes.

useorgx Skill

OrgX sales execution contract for OpenClaw. Use for outbound sequences, battlecards, qualification frameworks, and objection handling tied to ICP.

useorgx Skill

OrgX product execution contract for OpenClaw. Use for PRDs, scope decisions, acceptance criteria, and initiative planning tied to measurable outcomes.

useorgx Skill

OrgX operations execution contract for OpenClaw. Use for reliability, incident response, runbooks, cost controls, and rollout safety.

useorgx Skill

OrgX engineering execution contract for OpenClaw. Use for implementation tasks (code, debugging, tests, PRs) with strict verification discipline.

useorgx Skill

OrgX orchestration execution contract for OpenClaw. Use for decomposing work into initiatives/workstreams/milestones/tasks and coordinating agents with explicit dependencies.

chrisblattman Skill

Turn a rough, dictated, or ambiguous request into a clear, structured task, then carry it out. Use when a request is conversational, messy, underspecified, or high-stakes enough to deserve careful framing before work begins.

patrickserrano Skill

Build, run, and debug iOS apps on a simulator. Use when asked to run an iOS app, interact with the simulator UI, capture logs, or diagnose runtime behavior.

thinking-machines-lab Skill

Sample, evaluate, and post-train Inkling and Inkling-Small, Thinking Machines Lab's models built for Tinker. Use this skill whenever the user mentions Inkling, `thinkingmachines/Inkling`, tml-renderers, `tml_v0` / `TmlV0Renderer`, or thinking/reasoning effort — and whenever they are choosing a model, building training data, running evals, setting up SFT or RL, handling parse errors, or working with audio or image inputs for an Inkling model. Inkling has requirements that differ from other Tinker models (mandatory effort conditioning, its own renderer and tokenizer, a learning rate you calibrate yourself), so load this skill before writing any Inkling code.

thinking-machines-lab Bundle

Conduct post-training research for LLMs using the Tinker API — replicate paper results, explore new training ideas, run and monitor experiments, and document findings. Use this skill whenever the user wants to do research, replicate experiments from a paper or repo, investigate training hypotheses, run experiment sweeps, explore post-training techniques (SFT, RL, DPO, distillation, etc.), set up training, write training code, choose a model, tune hyperparameters, manage checkpoints, export weights, or analyze training logs — even if they just say "try this idea" or "let's see what happens if...".

clearfunction Bundle

Manages MCP (Model Context Protocol) servers for Claude Code and Claude Desktop. Activates for: finding MCP servers, MCP registries, MCP server setup, MCP configuration, MCP troubleshooting, MCP security, building MCP servers, MCP transport selection, claude mcp commands, mcp.json files, mcpServers configuration, tool poisoning prevention, MCP debugging, Smithery, Glama, GitHub MCP registry, which MCP server should I use. NOT for: general Claude Code settings (use claude-code-mastery), OAuth/authentication unrelated to MCP, generic API integrations without MCP.