agentsclimarketplace

Context & AI engineering

25,729 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Full inventory over sampling prompt

    kjuhwa/skills-hub/skills/workflow/full-inventory-over-sampling-prompt Skill

    0★ repo

    When a reference corpus fits comfortably in the LLM context window, pass the full inventory and let the model filter — don't sample arbitrarily

  • Slash command authoring

    kjuhwa/skills-hub/skills/workflow/slash-command-authoring Skill

    0★ repo

    Author Claude Code slash commands that read cleanly, include safety rules, and compose with OMC skills — frontmatter, argument-hint, step ordering, and dry-run patterns.

  • Split llm codegen into idea plus per item

    kjuhwa/skills-hub/skills/workflow/split-llm-codegen-into-idea-plus-per-item Skill

    0★ repo

    Split large LLM code generation into lightweight idea call + per-item full code calls to maximize output per artifact

  • Stale persistent context detection

    kjuhwa/skills-hub/skills/workflow/stale-persistent-context-detection Skill

    0★ repo

    Detect and remove stale error snapshots that LLM tools inject via persistent-context files (CLAUDE.md, AGENTS.md, system prompts, memory) before chasing a fix. If the current source already compiles, the injected error is a ghost from a previous session, not a real bug.

  • Worktree isolation resolver

    kjuhwa/skills-hub/skills/workflow/worktree-isolation-resolver Skill

    0★ repo

    Resolve which git worktree a workflow should run in using an ordered chain (existing ref → same-workflow reuse → linked-issue share → PR branch adoption → create new), each step guarded by worktree-ownership verification against the canonical repo path.

  • Ref sp agents plugin marketplaces

    swiftpostlabs/agentic-tools/.agents/skills/ref-sp-agents-plugin-marketplaces Skill

    0★ repo

    Shareable skills and tools for AI agents

  • Ref sp agents policy

    swiftpostlabs/agentic-tools/.agents/skills/ref-sp-agents-policy Skill

    0★ repo

    Repository-specific guidance for the agents-policy feature, .agents/config.json policy section, and generated AI restriction outputs in this repo. Use when: working on the agents-policy feature, updating policy docs, or debugging Copilot, Claude Code, or Gemini policy generation here.

  • Tool sp maintain agents instructions

    swiftpostlabs/agentic-tools/.agents/skills/tool-sp-maintain-agents-instructions Skill

    0★ repo

    Review and update repository agent instruction files after code, workflow, or skill changes. Use when: AGENTS.md, GEMINI.md, or .claude/CLAUDE.md may be outdated, the skill catalog changed, or a multi-provider repo needs its instruction bridge refreshed.

  • Portage orchestrator

    geoffsdesk/portage/skills/portage-orchestrator Skill

    0★ repo

    Run an end-to-end EKS to GKE migration program. Coordinates discovery, design, translation, cutover, and post-migration ops by sequencing the other Portage skills. Use when the user asks to "migrate from EKS to GKE", "plan an EKS→GKE migration", "replace our PSO engagement", or any holistic move of a Kubernetes estate from AWS to Google Cloud. Do NOT use for single-skill tasks (e.g., "translate this Helm chart") — call the specific skill directly.

  • Worktree isolation

    0SxD/agent-skills-plugin-v01/skills/worktree-isolation Skill

    0★ repo

    Create and manage git worktrees for parallel coding agent isolation. Invoke when two independent coding tasks need to run simultaneously (max 2).

    The same file is in 2 other repositories

  • Loop engineering

    fxckcode/skills-kit/skills/loop-engineering Skill

    0★ repo

    Design and implement autonomous agent loops for multi-agent software development. Maker-checker split, nested SDD cycles, worktree isolation, verification layers, and iteration budgets. Use when building systems where AI agents collaborate autonomously on software projects.

  • Swarm forge skill

    fxckcode/skills-kit/skills/swarm-forge-skill Skill

    0★ repo

    Sets up or refines repository AI workflow context across multiple CLI targets and four development patterns: TDD, BDD, ATDD, and SDD. Use when the user says things like "set up this repo for Claude Code", "set up this repo for Codex", "prepare the agent workflow", "add a TDD setup", "make this BDD-friendly", "set up ATDD", "set up spec driven development", or "review this project and scaffold the context files". It inspects the repo, chooses or confirms suitable CLI targets, setup patterns, and one of the four supported development patterns, asks only missing setup questions, runs bundled scaffold scripts when needed, and safely merges into existing project context files.

  • Towow bridge

    floccose-burner9185/wow-harness/reference/towow-snapshot/.claude/skills/towow-bridge Skill

    0★ repo

    Towow bridge 专项工程 Skill。用于设计、诊断、实现、重构和修复 bridge 全链问题,包括 `bridge_agent/*`、`backend/product/bridge/*`、`backend/product/routes/bridge.py`、worker_distributed 执行链、Claude CLI 运行时、systemd 部署、事件/产物/complete 状态、线上 bridge 观测与环境一致性。当用户提到 bridge、hosted negotiation 卡死、completed 伪装、Claude CLI `code=1`、lease/heartbeat/events/complete、bridge 部署、bridge 测试、bridge 重构,或任何“本地可以、服务器偶尔不行”的 bridge 问题时使用。

  • Towow dev handoff

    floccose-burner9185/wow-harness/reference/towow-snapshot/.claude/skills/towow-dev-handoff Skill

    0★ repo

    通爻开发接手入口。用于新 AI 接手 Towow 开发、梳理最新上下文、开始生产排障、继续上一轮工作或确认当前主线时使用。

  • Towow eng orchestrator

    floccose-burner9185/wow-harness/reference/towow-snapshot/.claude/skills/towow-eng-orchestrator Skill

    0★ repo

    通爻编排引擎专才。负责异步状态机、事件驱动架构和协商引擎核心逻辑。

  • Towow eng prompt

    floccose-burner9185/wow-harness/reference/towow-snapshot/.claude/skills/towow-eng-prompt Skill

    0★ repo

    通爻 Skill Prompt 工程专才。负责 LLM Prompt 设计和 Skill 实现。

  • Mcp bridge

    Harzva/deepseek-cli/packages/deepseek-cli/skills/mcp-bridge Skill

    0★ repo

    DeepSeek-first API CLI and Agent Skills toolkit with multi-provider fallback

  • Mcp bridge

    Harzva/deepseek-cli/packages/provider-api-cli/skills/mcp-bridge Skill

    0★ repo

    DeepSeek-first API CLI and Agent Skills toolkit with multi-provider fallback

  • Mcp bridge

    Harzva/deepseek-cli/skills/mcp-bridge Skill

    0★ repo

    DeepSeek-first API CLI and Agent Skills toolkit with multi-provider fallback

  • Agent browser

    rbr7/MedClawMini/skills/agent-browser Skill

    0★ repo

    Browse the web for any task research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.

  • Antibody design agent

    rbr7/MedClawMini/skills/antibody-design-agent Skill

    0★ repo

    An advanced agent for de novo antibody design and optimization using state-of-the-art protein language models (MAGE, RFdiffusion).

  • Cellfree rna agent

    rbr7/MedClawMini/skills/cellfree-rna-agent Skill

    0★ repo

    AI-powered cell-free RNA analysis from liquid biopsy for cancer detection, tissue-of-origin identification, and non-invasive transcriptomic profiling.

  • Chemcrow drug discovery

    rbr7/MedClawMini/skills/chemcrow-drug-discovery Skill

    0★ repo

    An LLM chemistry agent with expert-designed tools for organic synthesis, drug discovery, and materials design.

  • Chemistry agent

    rbr7/MedClawMini/skills/chemistry-agent Skill

    0★ repo

    Autonomous chemical synthesis & analysis

  • Cnv caller agent

    rbr7/MedClawMini/skills/cnv-caller-agent Skill

    0★ repo

    AI-enhanced copy number variation calling and analysis from sequencing data for cancer genomics, constitutional CNV detection, and chromosomal aberration characterization.

  • Cryoem ai drug design agent

    rbr7/MedClawMini/skills/cryoem-ai-drug-design-agent Skill

    0★ repo

    AI-powered integration of cryo-EM structural data with generative AI and molecular dynamics for structure-based drug design targeting flexible proteins and membrane complexes.

  • Gene panel design agent

    rbr7/MedClawMini/skills/gene-panel-design-agent Skill

    0★ repo

    AI-powered design of targeted gene panels for clinical and research applications including cancer diagnostics, pharmacogenomics, and rare disease testing.

  • Long read sequencing agent

    rbr7/MedClawMini/skills/long-read-sequencing-agent Skill

    0★ repo

    AI-powered analysis of long-read sequencing data (PacBio, ONT) for structural variant detection, isoform discovery, epigenetic modifications, and de novo assembly.

  • Molecular glue discovery agent

    rbr7/MedClawMini/skills/molecular-glue-discovery-agent Skill

    0★ repo

    AI-powered molecular glue discovery for targeted protein degradation, enabling neo-substrate recruitment and undruggable target degradation through E3 ligase interface modulation.

  • Molecule evolution agent

    rbr7/MedClawMini/skills/molecule-evolution-agent Skill

    0★ repo

    Evolve Molecules

  • Multi ancestry prs agent

    rbr7/MedClawMini/skills/multi-ancestry-prs-agent Skill

    0★ repo

    AI-powered multi-ancestry polygenic risk score calculation and optimization for equitable disease risk prediction across diverse global populations.

  • Pharmacogenomics agent

    rbr7/MedClawMini/skills/pharmacogenomics-agent Skill

    0★ repo

    AI-driven pharmacogenomic analysis for precision dosing and adverse event prediction using multi-omics data.

  • Popeve variant predictor agent

    rbr7/MedClawMini/skills/popeve-variant-predictor-agent Skill

    0★ repo

    AI-powered genetic variant pathogenicity prediction using PopEVE deep learning model for population-aware disease variant identification and rare disease diagnosis.

  • Protac design agent

    rbr7/MedClawMini/skills/protac-design-agent Skill

    0★ repo

    AI-powered PROTAC (Proteolysis Targeting Chimera) design for targeted protein degradation, integrating ternary complex prediction, linker optimization, and ADMET modeling.

  • Prs net deep learning agent

    rbr7/MedClawMini/skills/prs-net-deep-learning-agent Skill

    0★ repo

    Geometric deep learning-based polygenic risk score prediction using PRS-Net for modeling gene interactions, enhanced disease prediction, and cross-ancestry portability.

  • Simulation orchestrator

    rbr7/MedClawMini/skills/simulation-orchestrator Skill

    0★ repo

    Orchestrate multi-simulation campaigns including parameter sweeps, batch jobs, and result aggregation. Use for running parameter studies, managing simulation batches, tracking job status, combining results from multiple runs, or automating simulation workflows.

    The same file is in 3 other repositories

  • Time resolved cryoem agent

    rbr7/MedClawMini/skills/time-resolved-cryoem-agent Skill

    0★ repo

    AI-powered time-resolved cryo-EM analysis for capturing protein dynamics, drug-binding kinetics, and conformational transitions for dynamics-based drug discovery.

  • Tpd ternary complex agent

    rbr7/MedClawMini/skills/tpd-ternary-complex-agent Skill

    0★ repo

    AI-powered ternary complex prediction for targeted protein degradation, modeling POI-degrader-E3 ligase assemblies to optimize PROTAC and molecular glue efficacy.

  • Handoff

    SID-SURANGE/cursor-team-ops/skills/core/handoff Skill

    0★ repo

    Generate a structured session handoff document capturing progress, root causes, failed attempts, open issues, and next steps. Triggered by "generate handoff", "close session", "write handoff doc", "end of day", "EOD", "I'm done for today", "wrapping up", "switching tasks", "summarise what we did", "summarize progress", "session summary", "handoff".

  • Mcp security review

    vibesec-advisory/skills/skills/mcp-security-review Skill

    no license0★ repo

    Use when reviewing an MCP server, MCP tool, connector, local bridge, hosted integration, or agent tool catalog before connecting it to an assistant, granting credentials, or allowing read/write actions.

  • Prompt injection defense

    vibesec-advisory/skills/skills/prompt-injection-defense Skill

    no license0★ repo

    Use when reviewing an AI workflow, agent, RAG system, document pipeline, email workflow, browser task, or tool-using assistant that may consume untrusted content before it acts, summarizes, sends, retrieves, or exposes data.

  • Blender mcp

    fengluisobel/ask-dongfeng-hermes/optional-skills/creative/blender-mcp Skill

    0★ repo

    Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

    The same file is in 1 other repository

  • Kanban video orchestrator

    fengluisobel/ask-dongfeng-hermes/optional-skills/creative/kanban-video-orchestrator Skill

    0★ repo

    Plan, set up, and monitor a multi-agent video production pipeline backed by Hermes Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Hermes profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Hermes rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.

  • Fastmcp

    fengluisobel/ask-dongfeng-hermes/optional-skills/mcp/fastmcp Skill

    0★ repo

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.

    The same file is in 1 other repository

  • Chroma

    fengluisobel/ask-dongfeng-hermes/optional-skills/mlops/chroma Skill

    0★ repo

    Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

    The same file is in 1 other repository

  • Pinecone

    fengluisobel/ask-dongfeng-hermes/optional-skills/mlops/pinecone Skill

    0★ repo

    Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

    The same file is in 1 other repository

  • Qdrant

    fengluisobel/ask-dongfeng-hermes/optional-skills/mlops/qdrant Skill

    0★ repo

    High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

    The same file is in 1 other repository

  • Tensorrt llm

    fengluisobel/ask-dongfeng-hermes/optional-skills/mlops/tensorrt-llm Skill

    0★ repo

    Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

    The same file is in 1 other repository

  • Torchtitan

    fengluisobel/ask-dongfeng-hermes/optional-skills/mlops/torchtitan Skill

    0★ repo

    Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

    The same file is in 1 other repository

  • Page agent

    fengluisobel/ask-dongfeng-hermes/optional-skills/web-development/page-agent Skill

    0★ repo

    Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script> tag or npm package and lets end-users of your site drive the UI with natural language ("click login, fill username as John"). No Python, no headless browser, no extension required. Use this skill when the user is a web developer who wants to add an AI copilot to their SaaS / admin panel / B2B tool, make a legacy web app accessible via natural language, or evaluate page-agent against a local (Ollama) or cloud (Qwen / OpenAI / OpenRouter) LLM. NOT for server-side browser automation — point those users to Hermes' built-in browser tool instead.

    The same file is in 1 other repository

  • Claude code

    fengluisobel/ask-dongfeng-hermes/skills/autonomous-ai-agents/claude-code Skill

    0★ repo

    Delegate coding to Claude Code CLI (features, PRs).

    The same file is in 2 other repositories

  • Hermes agent

    fengluisobel/ask-dongfeng-hermes/skills/autonomous-ai-agents/hermes-agent Skill

    0★ repo

    Configure, extend, or contribute to Hermes Agent.

  • Claude design

    fengluisobel/ask-dongfeng-hermes/skills/creative/claude-design Skill

    0★ repo

    Design one-off HTML artifacts (landing, deck, prototype).

    The same file is in 1 other repository

  • Touchdesigner mcp

    fengluisobel/ask-dongfeng-hermes/skills/creative/touchdesigner-mcp Skill

    0★ repo

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    The same file is in 3 other repositories

  • Kanban orchestrator

    fengluisobel/ask-dongfeng-hermes/skills/devops/kanban-orchestrator Skill

    0★ repo

    Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.

  • Kanban worker

    fengluisobel/ask-dongfeng-hermes/skills/devops/kanban-worker Skill

    0★ repo

    Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.

  • Native mcp

    fengluisobel/ask-dongfeng-hermes/skills/mcp/native-mcp Skill

    0★ repo

    MCP client: connect servers, register tools (stdio/HTTP).

  • Lm evaluation harness

    fengluisobel/ask-dongfeng-hermes/skills/mlops/evaluation/lm-evaluation-harness Skill

    0★ repo

    lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

    The same file is in 3 other repositories

  • Llm wiki

    fengluisobel/ask-dongfeng-hermes/skills/research/llm-wiki Skill

    0★ repo

    Karpathy's LLM Wiki: build/query interlinked markdown KB.

  • Hermes agent skill authoring

    fengluisobel/ask-dongfeng-hermes/skills/software-development/hermes-agent-skill-authoring Skill

    0★ repo

    Author in-repo SKILL.md: frontmatter, validator, structure.