agentsclimarketplace

Context & AI engineering

25,841 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

  • Clawhub skill

    twilareckless401/agent-soul/clawhub-skill Skill

    2★ repo

    Give AI agents persistent identity and shared memory across runtimes, devices, and sessions — Git-native, no database, no vendor lock-in.

  • Company check

    paulieb89/bouch-plugins/plugins/foundations/skills/company-check Skill

    no license2★ repo

    Run a full due diligence check on a UK company or director. Cross-references Companies House, Gazette insolvency, HMRC VAT, and the Disqualified Directors register, then scores against a configurable risk profile (lender, journalist, acquirer, AML, or your own). Produces a CLEAR / WATCH / FLAG verdict with weighted reasons. Use when someone asks "check this company", "due diligence on X", "is this company legit", "who owns X Ltd", "is this director disqualified". Requires the UK Due Diligence MCP server.

  • Context window management

    varunk130/ai-workflow-playbooks/skills/context-window-management Skill

    2★ repo

    Production-grade playbooks for AI coding agents across the full software delivery pipeline. 21 playbooks, 10 agent skills, 4 specialist guardians, and 5 runbooks — from discovery through operations.

  • New python project

    zhengbingquant/frontier-skills/skills/new-python-project Skill

    2★ repo

    Bootstrap a new Python project from a proven scaffold. Use whenever the user asks to start, create, scaffold, or set up a new Python tool, library, CLI, package, service, or experiment repo — or says 'set up a project the usual way'. Do NOT hand-roll a project structure from memory when this skill is available: run its script instead. Produces a src-layout package with pyproject.toml, tests, Makefile, an agent contract (AGENTS.md + CLAUDE.md), operating docs, a review checklist, and a definition of done — a project any agent or human can pick up cold.

  • Skill

    hqzzdsda/belief-state-runtime/belief_state_runtime/skill Skill

    no license2★ repo

    LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCERTAIN). Use when the agent needs to assess whether information is trustworthy, detect contradictions in evidence, or quantify uncertainty.

  • Xreview feature

    tonychen15/xReview/codex/commands/xreview-feature Skill

    2★ repo

    Implement a feature with xReview peer review. Codex is the developer, a peer LLM agent reviews your work. Use when: /feature, implement a feature with review

  • Veriglow agent map

    ChizhongWang/veriglow-agent-map-skill/plugins/veriglow-agent-map/skills/veriglow-agent-map Skill

    2★ repo

    Look up VeriGlow Agent Map for any website URL to discover its data functions, internal APIs, browser automation recipes, and agent reliability reports. Use when you need to extract structured data from a website, call a website's hidden API, or automate browser interactions with a web page.

    The same file is in 3 other repositories

  • Skills curator lite

    captkernel/Skills_Curator/skills/skills-curator-lite Skill

    2★ repo

    The intelligence layer for Claude skills — without Python. Maintains a trust-rated catalog (curated entries + live GitHub topic search via curl), identifies what fits your project (stack, deps, CLAUDE.md), recommends with pros/cons and per-project customization advice, persists every decision, and migrates across 55 supported agent platforms. Same model as the full version, no engine — the agent does the work via Bash, Read, Glob, Grep, Write. Use when the user mentions a skill, asks "should I install X", asks to evaluate / recommend / audit / check a skill, asks "what skills fit this project", asks for a list of supported platforms, or wants to migrate skills to another agent. Choose this over the full version when you don't have Python, want zero dependencies, or prefer transparent agent reasoning.

  • Autonomous loop patterns

    jacob-balslev/skills/skills/agent-ops/autonomous-loop-patterns Skill

    2★ repo

    Use when designing, reviewing, or debugging an autonomous AI agent loop: repeated agent execution, completion signals, checkpoints, supervisor respawn, stall detection, safety caps, and human handoff rules. Covers the core loop patterns from simple bounded runs through sentinel-based continuation, checkpoint-resume, and external supervisor loops. Do NOT use for choosing a specific agent product command (use agent-engineering or the product's docs), writing ordinary task instructions (use prompt-craft), or optimizing individual tool calls (use tool-call-strategy).

  • Skill factory

    srinitude/skills/skills/skill-factory Skill

    2★ repo

    Use when a workflow, recipe, or capability needs to be packaged as an agent skill, or when an existing skill needs scaffolding, validation, linting, or evals. Covers requests to build, create, generate, scaffold, check, or evaluate a skill: a folder holding SKILL.md, scripts, tests, a task graph, CI, and eval cases. Applies even when the request says playbook, runbook, or reusable workflow instead of skill.

  • Claudeemailskill

    Sequenzy/skills/skills/claudeemailskill Skill

    2★ repo

    Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on Claude-oriented email prompts, campaign drafting, critique loops, and human review. Triggers include requests about prompt packs, campaign draft evaluation, review rubrics, rewrite loops, and Claude Code email handoffs.

    The same file is in 2 other repositories

  • Memory engine

    allanbian1017/skills/skills/deprecated/memory-engine Skill

    2★ repo

    A memory management and learning system for Antigravity. Use this skill whenever the user issues a memory command like save, reload, handoff, reflect, todo, learn, or any other memory-related commands. This skill enables the agent to store context across sessions, maintain a reflection diary, track cross-project tasks, and learn from mistakes.

  • Agent swarm

    tommylower/cortex/agent-workflows/agent-swarm Skill

    2★ repo

    Multi-agent parallel workflow — wave execution, review loops, adversarial dual-review

  • Audit agent onboarding

    gustavo-meilus/aiboarding/skills/audit-agent-onboarding Skill

    2★ repo

    Use to lint a repo's agent onboarding files (AGENTS.md, CLAUDE.md, .claude/rules/*.md) for bloat, contradictions, duplication, stale or vague commands, missing sections, leakage, and secrets - or with --stats to view compression receipts. Read-only; reports findings and hands fixes to update-agent-onboarding.

  • Dag fleet

    quickcall-dev/skills/skills/dag-fleet Skill

    2★ repo

    Persistent, budgeted, DAG-ordered runner for parallel `claude -p`, `codex exec`, or `pi -p` workers in tmux. Use ONLY when you need persistence across sessions, per-worker budget caps, dependency ordering, or mixed models/providers per worker. For ad-hoc parallel sub-agents inside a live conversation, use Claude Code's built-in Agent tool instead.

  • Ai discovery agent experience

    nevitonsantana/adaptive-skills/domain-packs/ai-discovery-agent-experience/skills/ai-discovery-agent-experience Skill

    no license2★ repo

    Route broad discovery, SEO, generative visibility, and agent-readiness goals to the smallest sufficient AI Discovery building blocks.

  • Agent image generation

    danielgwilson/luxin/skills/agent-image-generation Skill

    2★ repo

    Image generation an autonomous agent can run with no human setup step: free image generation for agents to start, without an API key, a provider account, or a billing account. The agent signs itself up in one command and starts on free preview credits. The --max-estimated-usd-per-image flag rejects a call whose quote is over budget before it spends. When the credits run out the agent hands its human one dashboard link to fund more.

  • Coding agents

    Vironnimo/vbot/resources/skills/coding-agents Skill

    2★ repo

    Drive external coding-agent CLIs — Claude Code (claude), Codex (codex), OpenCode (opencode) — non-interactively from an agent session, where every shell call is a fresh process with no persistent console and no way to type into a prompt. Use when the user asks an agent to delegate a coding task to claude/codex/opencode, run a headless coding agent, continue or resume a coding-agent session across calls, or pick a model, sub-agent, or thinking/reasoning effort for one. Covers print/exec/run modes, session resume, JSON output, permission and sandbox flags, and model/agent/effort selection. Do not use to operate vBot itself — that is the vbot-cli skill.

  • Codex dev

    shengyy/agent-skills/skills/codex-dev Skill

    2★ repo

    Full loop for delegating development tasks to the OpenAI Codex CLI. Claude plans the approach, writes the task brief, orchestrates, runs mechanical acceptance + review + merge; codex only writes code inside a workspace-write sandbox. Every codex task runs as an omegacode agent (one task = a 1-agent run, several = multi-agent, parallel if independent and ordered if dependent), so every dispatch gets a live dashboard, a completion notification, and disk-persisted reconnect. Use when the user says "delegate"/"hand it to codex"/"have codex implement|build <task>"/"fan out several codex tasks", or runs /codex-dev. For review/consultation only (no code-writing) use gstack-codex instead, not this skill.

  • Agentic income

    frankxai/agentic-income-skills/skills/agentic-income Skill

    2★ repo

    Build and operate principal-owned AI income systems that perform accepted paid work. Use when discovering an agent service opportunity, validating demand, creating an Outcome Pack, implementing a vertical AI system, defining agent authority, evaluating delivery, exposing a Skill/MCP/A2A service, or proving net economics. Active services belong here; affiliate and owned income assets belong to Agentic Passive Income; capital, crypto, lending, staking, trading, and yield experiments belong to DPI.

  • Loop eval

    VioletScar-Hui/Build_Great_Loop/loop-eval Skill

    2★ repo

    Design success criteria and a small eval set for an agentic loop — so the loop knows when it's done, and so YOU can measure whether the loop is any good. Use this whenever the user asks how to know if their agent/loop is working, how to define or sharpen success criteria, how to write evals/tests/graders for an agent, how to measure agent reliability, or wants pass/fail checks for a long-running task. Also use as the verification step when building a loop with loop-engineering. Covers verifiable criteria, code-based vs model-based graders, reliability metrics (pass@k vs pass^k), and balanced positive/negative cases. For a new unscoped loop, loop-spec owns success-definition intake first. Mining failures from specified run artifacts is led by loop-retro. Whole-harness audits are led by loop-review. This skill owns a standalone eval artifact once scope is settled. Routing tests for this suite are owned by loop-review.

  • Bifrost gateway

    SiteVisorCloud/bifrost-gateway-integration-skill/skills/bifrost-gateway Skill

    2★ repo

    Routes EVERY LLM / AI-provider request through a Bifrost (OpenAI-compatible) gateway so that all calls are logged and tracked in one place. Use this skill WHENEVER you write, configure, or debug any code that calls a large language model or AI provider — OpenAI/GPT, Anthropic/Claude, Google Gemini, DeepSeek, xAI/Grok, Perplexity, or any other — in ANY language (Python, PHP, JavaScript/TypeScript, Go, curl) or framework (Laravel AI SDK, LangChain, LlamaIndex, Vercel AI SDK). This covers new integrations, editing existing client setup, base_url / api_key configuration, chat completions, the Responses API, embeddings, and streaming. Trigger even when the user only says "call gpt-4o", "add Claude to this script", "sk-bf-...", "generate text with an LLM", or names a provider SDK without mentioning the gateway. NEVER call provider APIs directly — the whole point of the gateway is that no request goes around it.

  • Find pi capabilities

    varadfromeast/Vskills/find-pi-capabilities Skill

    2★ repo

    Scout the smallest verified Pi capability set before execution. Use when the user asks what Agent Skill, Pi package, MCP/tool integration, or subagent can handle a task.

  • Claude cli agent

    ImL1s/agent-cli-skills/skills/claude-cli-agent Skill

    2★ repo

    Run Anthropic Claude Code headlessly via claude-exec.sh (claude -p). Use when the user asks for Claude Code, claude CLI, ultracode, Claude workflows, agent teams, or Claude subagents. -r is plan mode (clears skip-permissions); -T/--ultracode enables effort ultracode + multi-agent preamble; -P sets permission-mode. Orchestrator owns git (--no-git).

  • Brand book paper

    ordinarynerds/brand-book/brand-book-paper Skill

    2★ repo

    Build a full brand guidelines document ("brand book") on the Paper design canvas (an editable, exportable file), and ship it with a matching agent-usable brand skill. Requires the Paper desktop app + its MCP. The brand can be your own or a client's. Use when the user wants a brand book / brand guidelines / identity system ON PAPER specifically, or wants an editable design-canvas version they can keep tweaking. If they just want a portable document (open anywhere, print to PDF, publish as an Artifact), use `brand-book-html` instead — that's the better default for most people. Two deliverables every time: (1) the Paper book (→ PDF), (2) a `<brand>-brand` skill that keeps that brand's product on-brand during agentic coding.

  • Skm extract agent skill pack

    weiox/skm/skills/skm-extract-agent-skill-pack Skill

    no license2★ repo

    Use when a set of local skills should be split out from an existing source tree into a standalone skill-pack repository skeleton, while keeping the original skills in place until the new repository is reviewed and reconnected through `vendor`.

  • Agent expertise protocol

    kinhluan/skills/.agent-skills/agent-expertise-protocol/agent-expertise-protocol Skill

    2★ repo

    Define the Expertise Protocol for all agents in the kinhluan skills ecosystem. Use when setting up agent behavior, defining agent roles, or clarifying the boundary between agent recommendation and user decision. Ensures agents act as domain experts while respecting user sovereignty.

  • Rulespec

    pallaoro/rulespec/skills/rulespec Skill

    no license2★ repo

    Define, manage, and compile business rules as structured YAML data into LLM-ready prompts and agent-loadable SKILL.md files. Use when the user wants to create business rules, define policies, set guardrails, enforce constraints, add compliance rules, manage refund policies, escalation rules, approval thresholds, SLA requirements, content moderation rules, or any operational policy an AI agent should follow. Also use when the user says "add a rule", "create a policy", "set a constraint", "define guardrails", or asks about rulespec, rulespec.yaml, or business rule management.

  • Agent fundamentals

    agent-blueprint/agent-blueprint-skills/plugins/agent-blueprint-skills/skills/agent-fundamentals Skill

    no license2★ repo

    Agentic AI fundamentals for enterprise: what is an agent, agent vs workflow, should I use agents, and how do agents work. Covers when to use agents vs. workflows or chatbots, agent anatomy, architecture patterns, decision frameworks, and common failure modes. Use when someone is new to agents, evaluating whether agents fit their use case, or needs conceptual grounding before deploying. Triggers: what is an agent, agent vs workflow, should I use agents, how do agents work, new to agents, agent fundamentals, when to use agents, agent design patterns, explain agentic, agent architecture, learn about agents, agentic AI concepts.

  • Adding mcp oauth

    scalekit-inc/skills/skills/adding-mcp-oauth Skill

    no license2★ repo

    Guides users through adding OAuth 2.1 authorization to Model Context Protocol (MCP) servers using Scalekit. Use when setting up MCP servers, implementing authentication for AI hosts like Claude Desktop, Cursor, or VS Code, or when users mention MCP security, OAuth, or Scalekit integration.

    The same file is in 1 other repository

  • Hermes skill

    doteyeso-ops/vibes-coded-agent-connector/src/hermes-skill Skill

    2★ repo

    Vibes-Coded connector: register agents, list skills, browse Solana escrow jobs, prepaid /start + Operator Interrupt, Reclaim SOL (/reclaim-sol), hosted uploads, checkout, affiliates. Hermes + Solana agent economy.

  • Ai prompt writing

    The-AI-Directory-Company/agents-and-skills/skills/ai-prompt-writing Skill

    2★ repo

    Write effective prompts for AI coding tools — structure task context, specify constraints, provide examples, and iterate based on output quality. Targets developers using Claude Code, Copilot, Cursor, and similar tools.

  • Mcp builder

    pinkpixel-dev/agentskills-mcp/.codex/skills/mcp-builder Skill

    2★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 18 other repositories

  • Death

    sidtheone/tarot-skills/death Skill

    no license2★ repo

    Death XIII — The Chaos Agent. Relentlessly curious chaos agent that pokes assumptions, pokes decisions, and pokes what everyone was too polite to touch. Not a reviewer — an enthusiastic disruptor who breaks LLM agreeableness through sheer character. Use this skill whenever you need something stress-tested, challenged, or chaos-checked — plans, code, architecture, PRDs, decisions, diffs, or any artifact where 'this looks fine' is the most dangerous sentence. Trigger on: 'chaos check', 'death this', 'what are we missing', 'challenge this', 'poke this', 'stress test', or when things feel too comfortable.

  • Orchestrator

    coreline-ai/antigravity_gemini_skills/.agent/skills/orchestrator Skill

    2★ repo

    Gemini/Antigravity 기반 에이전틱 DevOps·SDLC 오케스트레이션 스킬 시스템 | Gemini/Antigravity skill system for agentic DevOps and SDLC orchestration

  • Ai agents architect

    bcastelino/agent-skills-kit/skills/ai-agents-architect Skill

    2★ repo

    Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ...

  • Agent skills setup

    Luckycat133/skills-repo/skills/agent-skills-setup Skill

    2★ repo

    Reusable AI agent skills with multi-IDE sync, export, and publishing workflow

  • Exa company research

    CodeAlive-AI/exa-skills/exa-company-research Skill

    no license2★ repo

    Research companies with Exa semantic search — find competitors, funding, headcount, news, and build company lists. Use for competitor analysis, market mapping, sourcing companies by category/stage/geo, or 'find companies like X'. Runs a local script against the Exa API; no MCP server required.

  • Pm tasks asana

    llodev/skills/skills/pm-tasks-asana Skill

    2★ repo

    Asana adapter for the @llodev/pm-tasks-* family. Use when the user mentions Asana, asks to "create Asana task", "publish to Asana", "post to Asana", "publish", "add comment in Asana", or uses --publish-asana; OR for CRUD on existing tasks (check subtask, close task, change due-date, assign person, comment); OR when invoked autonomously by another agent with [autonomous] / --auto sentinel. Asana hierarchy: workspace > project > section > parent task > subtasks (one level), with custom fields and multi-assignee support. Modes: paste-ready (no MCP needed), MCP publish (via claude.ai Asana MCP), autonomous (write-through with allowlist). Implements 7 CRUD verbs (task.create, task.move, checklist.check, task.close, task.due-date.set, task.assignee.add, task.comment.add) from skills/pm-tasks-core/references/contract.md. Requires @llodev/pm-tasks-core installed.

  • Zh

    ZHOUCOOKIE/prompt-engineering-skill/skill/zh Skill

    no license2★ repo

    Writes, rewrites, reviews, and audits prompts and system prompts using Anthropic's current official guidance, and selects the right model and effort level for the task before drafting. Use when the user asks to write a prompt, improve or fix a prompt, design a system prompt, or check a prompt before running a task — including phrasings like "帮我写 prompt"、"改一下这个 prompt"、"设计 system prompt"、"处理任务之前先检查我的 prompt"、"帮我把需求整理成 prompt"、"help me prompt this better". Applies whether the resulting prompt will be pasted into Claude Code for a coding task or run in a desktop chat or Cowork session for a non-coding task. Also use when the user pastes a prompt and asks why it is not working, when they are authoring an agent system prompt or CLAUDE.md, or when they ask which model or effort level to use. Several widely repeated prompt techniques are now obsolete or rejected by the API, so consult this skill even when prompting from memory feels sufficient.

  • Logic analyzer agent

    felixfinal/agent-dsviewer-logic-analyzer/skills/logic-analyzer-agent Skill

    no license2★ repo

    Top-level agent for USB logic analyzer work using the verified dslogic-cli/libsigrok4DSL native backend. Use for DSLogic/DSView environment setup, device connection, capture (stream+buffer), protocol decode (UART/SPI/I2C), and data interpretation. Use the dsview-logic MCP for hardware operations.

  • Agentic income

    frankxai/affiliate-agent-skills/skills/agentic-income Skill

    2★ repo

    The operating brain for building income systems with AI agents. Use when planning, building, or scaling an affiliate/content/product income network — deciding what to build next, where money actually comes from, how to make it compound, and how the system improves itself. Composes affiliate-audit. Trigger phrases: build an income system, make money with agents, scale my content network, what should I build next, passive income with AI, monetize this site, agentic income.

  • Ko

    Imtylerrrrrr/TK/ko Skill

    2★ repo

    Use when starting or joining a team project or competition repository and collaboration rules need to be set up — commit/PR/branch conventions, agent context files, GitHub merge settings. Triggers — new hackathon/공모전/대회 repo, "협업 규칙", "커밋 규칙 세팅", "PR 규칙", "팀 레포 준비", team develops with coding agents (Claude Code, Codex, Cursor, Gemini CLI).

  • Delegation coordinator

    rumotion/ai-agent-project-template/.agents/skills/delegation-coordinator Skill

    2★ repo

    Coordinates task delegation across Gemini, Codex, Claude, and subagents using the portable subagent contract.

  • Aigd handoff

    ProdaZhang/aigd/aigd-handoff Skill

    2★ repo

    AIGD Phase 4 · finalize and generate the handoff package. Use this when, after a system is finalized in playtesting, you want to generate the interface contract, acceptance cases, (as needed) art/client/server docs, and the designer-facing acceptance checklist. Produces platform-agnostic handoff artifacts that "another AI can develop directly from". Part of the aigd package; methodology in ../aigd/references/.

  • Memory prune

    shandar/memory-map/skills/memory-prune Skill

    2★ repo

    Clean stale, outdated, or redundant entries from Claude's stored memory. Use this skill when the user says things like "clean up memory", "prune memory", "memory is getting cluttered", "remove old entries", "consolidate memory", or "trim the memory map". Also trigger proactively when memory approaches its limits — 30 entries on claude.ai, 200 lines on Claude Code — or when entries reference past events that have completed (an event date that has passed, a deliverable marked "upcoming" that is now shipped). Always propose changes for user confirmation before applying — never delete memory autonomously. Pairs with memory-map and memory-recall to form the complete memory loop.

  • Agent wallet

    hec-ovi/blockchain-skill/plugins/agent-wallet-codex/skills/agent-wallet Skill

    2★ repo

    Operate a non-custodial blockchain wallet on-chain (EVM and Bitcoin), no exchange or MetaMask. Create or import a wallet, balances, send native/ERC-20/BTC, swap tokens, compile/deploy/call Solidity. Trigger on wallet, crypto, ETH, BTC, ERC-20, token, send, transfer, swap, trade, Solidity, contract, on-chain, testnet, mainnet, sepolia.

  • Skill diet

    brenbuilds1/cutweight/skills/skill-diet Skill

    2★ repo

    Audit the always-on context cost of an agent setup: installed skills, memory files (CLAUDE.md, AGENTS.md), and MCP tool schemas. Use when asked to audit, trim, shrink, or cut skills or context, when an agent picks the wrong skill or feels dumber after the setup grew, when MCP servers eat the context window, or when the token bill grows without more work getting done. Produces a keep/trim/cut table with measured numbers. Does not delete anything.

  • Agent orchestration

    vignesh2027/AI-AGENT-SKILLS/skills/agent-orchestration Skill

    2★ repo

    Design multi-agent systems with robust tool interfaces, state management, and failure handling

  • M4nual

    maxkle1nz/deviance-skills/claude/m4nual Skill

    2★ repo

    Establish and maintain THE MANUAL of a system — the canonical operations book (≠ PATHOS which is living state; ≠ AGENTS.md which is agent rules): how the system works, where infra lives (servers, DB, DNS, email, attached services), drawn mermaid maps, real development rules, runbooks. One source, two projections: docs/MANUAL.md for agents (greppable, typed anchors, mermaid) + generated interactive HTML for humans (calm design, navigation, search). Trigger when the user asks for /m4nual, "manual do sistema", "livro de operação", to establish/sync/update a system manual, or when an agent needs the canonical answer to "how do I operate/control this system?". NOT for session state (use pathos) and NOT for agent work rules (AGENTS.md).

  • Skill

    yvzhou1111/skillforge/skill Skill

    2★ repo

    Discover, security-audit, and install Agent Skills for the current project. Use this when the user asks "find a skill for X", "what skills do I need", wants to extend the agent's capabilities, or asks to set up skills for a project/tech stack. SkillForge scans the project, plans a skill combination, audits each skill for security risks, and installs them into the target agent (Claude Code, Cursor, Codex, Gemini, Hermes, OpenClaw). Works two ways: as MCP tools (skillforge_*) or by calling the `skillforge` CLI directly.

  • Agent memory

    kimtth/agent-skill-100-lines-or-less/skills/agent-memory Skill

    no license2★ repo

    Use when: persist and recall context across coding sessions so the agent stops re-learning the same stack, bugs, and decisions.

  • Orchestrate cursor delegation

    matdev83/hermes-cursor-dispatcher/skills/orchestrate-cursor-delegation Skill

    2★ repo

    Use when executing an approved software implementation plan by orchestrating one or more Cursor CLI workers through the cursor-delegate skill. Decompose work into self-contained tasks, provide complete fresh-context prompts, enforce TDD, inspect every retained worktree and diff, run independent validation, and issue bounded repair delegations until the approved plan is complete or a hard failure is reached.

  • Agent observability desk

    MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/agent-observability-desk Skill

    2★ repo

    design observability for AI agents and workflows including traces, prompts, model calls, tool calls, retrieval events, approvals, errors, eval probes, cost, latency, and safety signals.

  • Forge ai

    is-bo/fullstack-forge-skill/.agents/skills/forge-ai Skill

    2★ repo

    Audit model boundaries, prompt injection, tool authority, data handling, output validation, evaluation, fallback, and cost. Activate automatically for llm, embedding, classifier, agent, retrieval, or generative-media features when that concern is relevant to a software-engineering request.

  • DaedalMap Disaster and Geospatial Data

    xyver/daedal-map/com.daedalmap/county-map MCP server

    2★ repo

    Geospatial MCP server for earthquake, tsunami, volcano, disaster, and FX data queries.

  • Quantrisk

    78degrees/mcp-server/io.github.78degrees/quantrisk MCP server

    2★ repo

    Portfolio risk analytics MCP server — VaR, Monte Carlo, stress testing, and more.

  • Molecular mcp

    andylbrummer/math-mcp/io.github.andylbrummer/molecular-mcp MCP server

    2★ repo

    GPU-accelerated MCP server for molecular dynamics, N-body simulations, and particle systems

  • Mysql

    marcelo-ochoa/servers/io.github.marcelo-ochoa/mysql MCP server

    no license2★ repo

    An MCP server for MySQL databases.

  • MCP Sentinel

    oaslananka/mcp-suite/io.github.oaslananka/sentinel MCP server

    2★ repo

    Zero-trust MCP security proxy with policy enforcement, PII scrubbing, approvals, and audit trails.