agentsclimarketplace

Context & AI engineering

25,610 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

  • Visual prompt

    NovateStudioGit/novate-studio-skills/creative-production/visual-prompt Skill

    0★ repo

    Expand a short visual brief into a Shlabu-density, paste-ready prompt for any modern image or video generation tool — Kling, Veo, Sora, Seedance, Higgsfield, Flux, GPT Image, Nano Banana, or Midjourney. Trigger this skill in TWO modes. (1) Explicit — the user types `/visual-prompt` or natural-language like "expand this prompt", "make this prompt detailed", "give me the long version", "Shlabu this", "write the detailed prompt for [scene]". (2) Auto-detect — the user's last message LOOKS like a raw visual brief: a short declarative scene description (1–4 sentences), photographic/cinematic vocabulary like "shot of", "POV", "angle", "frame", "lit by", "hero shot", a subject + setting + intent shape, and no other clear request type (not a question, not a feedback note, not a code request, not a meta-conversation). When triggered in auto-detect mode, do NOT compose the prompt yet — first respond with a one-line gate asking Will to confirm by typing `/visual-prompt`, then wait. Only compose after explicit confirmation. Output is a single comma-spliced prose paragraph at Shlabu density (250–350 words) for prose tools, or a comma-separated keyword + parameter line for Midjourney.

  • Browser testing with devtools

    jae-labs/skills/skills/browser-testing-with-devtools Skill

    0★ repo

    Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

  • Context engineering

    jae-labs/skills/skills/context-engineering Skill

    0★ repo

    Optimizes agent context setup. Use when starting a new session, when switching from design/spec work into implementation, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

  • Handoff

    jae-labs/skills/skills/handoff Skill

    0★ repo

    Compact the current conversation into a handoff document for another agent to pick up.

    The same file is in 13 other repositories

  • Md docs

    jae-labs/skills/skills/md-docs Skill

    0★ repo

    Use ONLY to update or initialize README.md, CLAUDE.md, or AGENTS.md. Do not trigger for other Markdown files.

  • Skill creator

    jae-labs/skills/skills/skill-creator Skill

    0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Enhance prompt

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/enhance-prompt Skill

    0★ repo

    Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

    The same file is in 6 other repositories

  • Karpathy guidelines

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/karpathy-guidelines Skill

    0★ repo

    Coding discipline guardrails for writing, reviewing, debugging, or refactoring code with fewer LLM-agent mistakes. Use when a task touches source files, tests, architecture, bug fixes, feature implementation, refactors, cleanup, or code review and needs explicit assumptions, simple solutions, surgical diffs, existing-style consistency, and verifiable success criteria.

  • Mcp builder

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/mcp-builder Skill

    0★ repo

    MCP server design, implementation, and review workflow for Model Context Protocol integrations. Use when building or auditing MCP servers, tools, resources, prompts, connectors, external API integrations, tool schemas, authentication boundaries, error handling, pagination, or agent-facing workflow tools in Python, TypeScript, or another runtime.

  • Phere 9 agent manager

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/phere-9-agent-manager Skill

    0★ repo

    Use when managing the Phere/Shaadikhata app through the named Phere 9-Agent Manager developer workflow, including enterprise-style engineering agents, planner, product, frontend, backend, Supabase/database, tester, production, security, architecture, performance, observability, documentation, data/AI, truthfulness checks, and optional post-code business agents such as marketing and sales. Trigger when the user asks for agents, an agent manager, deep agent training, planner/tester/production agents, evidence-based app maintenance, release coordination, or a multi-agent development team.

  • Qa agent

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/qa-agent Skill

    0★ repo

    Use when the user asks to test a website, CRM flow, login flow, dashboard, form, report, responsiveness, console/network health, UI/UX bugs, or to generate a QA report with screenshots using the local QaAgent repo.

  • Supabase

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/supabase Skill

    0★ repo

    Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

    The same file is in 1 other repository

  • Website qa agent

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/website-qa-agent Skill

    0★ repo

    Run safe, evidence-based website and CRM QA with the QaAgent framework, including login flows, module checks, test-data handling, screenshots, browser-state inspection, bug reporting, and the repository quality gate.

  • Enhance prompt

    BAKUGOS1/SkilledAgents-Toolkit/skills/codex/enhance-prompt Skill

    0★ repo

    Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

    The same file is in 6 other repositories

  • Karpathy guidelines

    BAKUGOS1/SkilledAgents-Toolkit/skills/codex/karpathy-guidelines Skill

    0★ repo

    Coding discipline guardrails for writing, reviewing, debugging, or refactoring code with fewer LLM-agent mistakes. Use when a task touches source files, tests, architecture, bug fixes, feature implementation, refactors, cleanup, or code review and needs explicit assumptions, simple solutions, surgical diffs, existing-style consistency, and verifiable success criteria.

  • Mcp builder

    BAKUGOS1/SkilledAgents-Toolkit/skills/codex/mcp-builder Skill

    0★ repo

    MCP server design, implementation, and review workflow for Model Context Protocol integrations. Use when building or auditing MCP servers, tools, resources, prompts, connectors, external API integrations, tool schemas, authentication boundaries, error handling, pagination, or agent-facing workflow tools in Python, TypeScript, or another runtime.

  • Qa agent

    BAKUGOS1/SkilledAgents-Toolkit/skills/projects/qaagent/qa-agent Skill

    0★ repo

    Use when the user asks to test a website, CRM flow, login flow, dashboard, form, report, responsiveness, console/network health, UI/UX bugs, or to generate a QA report with screenshots using the local QaAgent repo.

  • Website qa agent

    BAKUGOS1/SkilledAgents-Toolkit/skills/projects/qaagent/website-qa-agent Skill

    0★ repo

    Run safe, evidence-based website and CRM QA with the QaAgent framework, including login flows, module checks, test-data handling, screenshots, browser-state inspection, bug reporting, and the repository quality gate.

  • Phere 9 agent manager

    BAKUGOS1/SkilledAgents-Toolkit/skills/projects/shaadikhata/phere-9-agent-manager Skill

    0★ repo

    Use when managing the Phere/Shaadikhata app through the named Phere 9-Agent Manager developer workflow, including enterprise-style engineering agents, planner, product, frontend, backend, Supabase/database, tester, production, security, architecture, performance, observability, documentation, data/AI, truthfulness checks, and optional post-code business agents such as marketing and sales. Trigger when the user asks for agents, an agent manager, deep agent training, planner/tester/production agents, evidence-based app maintenance, release coordination, or a multi-agent development team.

  • Supabase

    BAKUGOS1/SkilledAgents-Toolkit/skills/projects/shaadikhata/supabase Skill

    0★ repo

    Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

    The same file is in 1 other repository

  • Orchestrator operating pattern

    w3rdist-creator/agent-intelligence-economy/skills/orchestrator-operating-pattern Skill

    0★ repo

    Coordinate agents, scripts, ledgers, and durable files without turning every task into a swarm.

  • Normalize agent instructions

    Andiedie/skills/skills/normalize-agent-instructions Skill

    no license0★ repo

    Normalize AGENTS.md/CLAUDE.md project instruction files. Use when the user asks to standardize AGENTS.md and CLAUDE.md or migrate Claude guidance to AGENTS.md.

  • Subagent protocols

    clankercode/agent-file-chat/skills/subagent-protocols Skill

    no license0★ repo

    Use when setting up parent<->subagent communication or dispatching subagents and wanting a clean inbox handshake. This is the general pattern: the coordinator decides per subagent whether to monitor, append on demand, or stay one-way. The simple-agent-comms and simple-agent-room sibling skills are specialized variants that add a persistent Monitor.

  • Agent drives ui

    selamy-labs/agent-skills/skills/agent-drives-ui Skill

    0★ repo

    Use when an agent operates a UI on the user's behalf through conversation, navigating, filling forms, updating live views, with real-time bi-directional state sync. Activates on conversational app control, agent drives the front end, agentic UX, or choosing an agent-to-app protocol.

  • Agent otel trajectory

    selamy-labs/agent-skills/skills/agent-otel-trajectory Skill

    0★ repo

    Emit OpenTelemetry trajectory spans (tool-call, latency, token usage) as an agent works — vendor-neutral, via otel-cli wrapping shell tool-calls, exported to any OTLP backend.

  • Agentic coding loop

    selamy-labs/agent-skills/skills/agentic-coding-loop Skill

    0★ repo

    Use when implementing code from a spec through a bounded build-test-fix loop with explicit acceptance criteria, automated checks, live verification when needed, and clear stop conditions.

  • Authoring skills vs mcp

    selamy-labs/agent-skills/skills/authoring-skills-vs-mcp Skill

    0★ repo

    Use when deciding whether a capability should be a SKILL or an MCP SERVER, and how to author either well. The axis is knowledge-vs-capability: would the agent READ this to know how, or CALL this to do it?

  • Codegraph worktree startup

    selamy-labs/agent-skills/skills/codegraph-worktree-startup Skill

    0★ repo

    Use when starting or resuming code work in a repository worktree. Initialize or sync CodeGraph, keep its cache uncommitted, and prefer CodeGraph for code navigation before grep or broad file reads.

  • Command creator

    selamy-labs/agent-skills/skills/command-creator Skill

    0★ repo

    Use when turning a repeated workflow into a Claude Code slash command. Structure the command markdown, choose argument handling and allowed tools, and write agent-executable steps so the workflow runs consistently instead of being re-explained every time.

  • Credential proxy

    selamy-labs/agent-skills/skills/credential-proxy Skill

    0★ repo

    Use when a workload (agent, sandbox, container, CI job) must call an authenticated upstream (LLM/provider/cloud API) but should not hold the credential itself. Keep the secret in a proxy that injects it, so a compromised workload cannot exfiltrate the key.

  • Plugin authoring

    selamy-labs/agent-skills/skills/plugin-authoring Skill

    0★ repo

    Use when packaging skills, commands, agents, or hooks into a Claude Code plugin and publishing to a marketplace. Get the directory structure, plugin.json and marketplace.json manifests, version bump, and local-test loop right so the plugin installs cleanly and is version-pinnable.

  • Self improving agent loops

    selamy-labs/agent-skills/skills/self-improving-agent-loops Skill

    0★ repo

    Use when designing a system that should autonomously generate, evaluate, and refine its own candidate solutions (agents, prompts, configurations, experiments) in a loop — rather than hand-managing each iteration. The system does the search; the human owns the architecture and the final decision.

  • Sim zero mode

    selamy-labs/agent-skills/skills/sim-zero-mode Skill

    0★ repo

    Use when building/testing an app or agent that depends on paid APIs or LLM calls and you must exercise plumbing/UI/harness without spend or real intelligence, for CI, demos, local dev. Activates on test without burning API budget, demo without live calls, or fakes/offline mode.

  • Structure improves agent predictability

    selamy-labs/agent-skills/skills/structure-improves-agent-predictability Skill

    0★ repo

    Use when writing code an AI agent will later read and edit. Structure it so the next edit is obvious — typed boundaries, exhaustive matches, named dispatch, small surfaces — because well-structured code makes an agent predictable and ad-hoc code makes it guess.

  • Setup indexing

    Myra-Agents/skills/skills/setup-indexing Skill

    0★ repo

    Install a greppable code index so agents locate files/symbols without rescanning the project every session — generates an index.sh (dirs/files/symbols with file:line, per repo or workspace member), wires .gitignore + CLAUDE.md, offers a SessionStart refresh hook, then runs a validation pipeline (syntax, edge-case sandbox, measured recall check, staleness detection, optional A/B benchmark). Use whenever the user wants to set up code indexing, complains that the agent re-scans/re-explores the whole project to find things, asks to make agent search faster/cheaper, or mentions a project index, code map, symbol index, or ctags-like setup for agents.

  • Aegis operator

    HaloForgeAI/aegis-agent-plugins/plugins/aegis/skills/aegis-operator Skill

    0★ repo

    Use Aegis from Codex as an AI assistant. Trigger when the user asks to inspect, capture, triage, assign, dispatch, report, clean up, or diagnose Aegis work through the configured aegis MCP server. Do not trigger for simple one-off chat unless Aegis state should be read or changed.

  • Agent os

    percymcn/agent-cookbook/skills/autonomous-ai-agents/agent-os Skill

    0★ repo

    Agent Operating System — Hermes is the command hub on Telegram. You talk to Hermes, Hermes orchestrates subagents (Felix/Claude Code), and results auto-save to memory. Built-in voice intent detection and cron job memory feedback.

  • Delegate to claude code

    percymcn/agent-cookbook/skills/autonomous-ai-agents/delegate-to-claude-code Skill

    0★ repo

    Delegate complex coding/reasoning tasks to Claude Code CLI via the call_claude_code Python wrapper.

  • External coding agents

    percymcn/agent-cookbook/skills/autonomous-ai-agents/external-coding-agents Skill

    0★ repo

    Umbrella for delegating software work to external coding-agent CLIs: Claude Code, OpenAI Codex, and OpenCode. Use for autonomous implementation, refactoring, code review, PR work, parallel worktrees, long-running agent sessions, PTY/tmux orchestration, and CLI-specific pitfalls.

  • Hermes agent

    percymcn/agent-cookbook/skills/autonomous-ai-agents/hermes-agent Skill

    0★ repo

    Configure, extend, or contribute to Hermes Agent.

  • Gumroad operations

    percymcn/agent-cookbook/skills/business-automation/gumroad-operations Skill

    0★ repo

    Manage Purse's Gumroad store through the local Gumroad CLI and MCP server: products, sales, offer codes, subscribers, licenses, webhooks, reports, and guarded mutations.

  • Context engineering collection

    percymcn/agent-cookbook/skills/context-engineering/context-engineering-collection Skill

    0★ repo

    A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.

  • Latent briefing

    percymcn/agent-cookbook/skills/context-engineering/latent-briefing Skill

    0★ repo

    This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.

  • Memory systems

    percymcn/agent-cookbook/skills/context-engineering/memory-systems Skill

    0★ repo

    This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization.

    The same file is in 1 other repository

  • Multi agent patterns

    percymcn/agent-cookbook/skills/context-engineering/multi-agent-patterns Skill

    0★ repo

    This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.

    The same file is in 1 other repository

  • Project development

    percymcn/agent-cookbook/skills/context-engineering/project-development Skill

    0★ repo

    This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.

  • Touchdesigner mcp

    percymcn/agent-cookbook/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

    percymcn/agent-cookbook/skills/devops/kanban-orchestrator Skill

    0★ repo

    Decomposition playbook + 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

    percymcn/agent-cookbook/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

    percymcn/agent-cookbook/skills/mcp/native-mcp Skill

    0★ repo

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

  • Evaluation lm evaluation harness

    percymcn/agent-cookbook/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

  • Hermes agent skill authoring

    percymcn/agent-cookbook/skills/software-development/hermes-agent-skill-authoring Skill

    0★ repo

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

  • Subagent driven development

    percymcn/agent-cookbook/skills/software-development/subagent-driven-development Skill

    0★ repo

    Execute plans via delegate_task subagents (2-stage review).

    The same file is in 1 other repository

  • Agent browser clawdbot

    percymcn/agent-cookbook/skills/uncategorized/agent-browser-clawdbot Skill

    0★ repo

    Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

  • Agent browser

    percymcn/agent-cookbook/skills/uncategorized/agent-browser Skill

    0★ repo

    Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

  • Agent os learned

    percymcn/agent-cookbook/skills/uncategorized/agent-os-learned Skill

    0★ repo

    Use when reviewing or referencing past agent-OS architecture analysis sessions. Contains notes from evaluating local JARVIS-style AI assistants (e.g. Mark-XL) covering Whisper STT, Ollama LLM integration, tool ecosystems, and persistent memory patterns.

  • Agentic workflow automation

    percymcn/agent-cookbook/skills/uncategorized/agentic-workflow-automation Skill

    0★ repo

    Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow definitions, and automation handoff artifacts.

  • Claude code mastery

    andersonoliveiraventurini/esquadrao-classe-a/.agents/skills/claude-code-mastery Skill

    no license0★ repo

    Acione para maestria no PRÓPRIO Claude Code — escrever CLAUDE.md, desenhar hooks de enforcement, integrar servidores MCP, criar skills e slash commands, e endurecer segredos/permissões. Use quando o assunto for configurar, automatizar ou orquestrar o Claude Code em si, não construir features de uma app comum. Keywords: claude-code, hooks, mcp, skills, slash-commands, enforcement

  • Claude code mastery

    andersonoliveiraventurini/esquadrao-classe-a/claude-code-mastery/skills/claude-code-mastery Skill

    no license0★ repo

    Acione para maestria no PRÓPRIO Claude Code — escrever CLAUDE.md, desenhar hooks de enforcement, integrar servidores MCP, criar skills e slash commands, e endurecer segredos/permissões. Use quando o assunto for configurar, automatizar ou orquestrar o Claude Code em si, não construir features de uma app comum. Keywords: claude-code, hooks, mcp, skills, slash-commands, enforcement

  • Claude code mastery

    andersonoliveiraventurini/esquadrao-classe-a/esquadrao-completo/skills/claude-code-mastery Skill

    no license0★ repo

    Acione para maestria no PRÓPRIO Claude Code — escrever CLAUDE.md, desenhar hooks de enforcement, integrar servidores MCP, criar skills e slash commands, e endurecer segredos/permissões. Use quando o assunto for configurar, automatizar ou orquestrar o Claude Code em si, não construir features de uma app comum. Keywords: claude-code, hooks, mcp, skills, slash-commands, enforcement