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

  • Mission control handoff audit burst

    MN755/Codex-Mission_Control/.codex/skills/mission-control-handoff-audit-burst Skill

    1★ repo

    Use when Mission Control should recommend a read-only handoff audit burst for run instructions, validation evidence, limitations, docs quality, and security caveats.

  • Mission control handoff

    MN755/Codex-Mission_Control/.codex/skills/mission-control-handoff Skill

    1★ repo

    Retrieve and present the final Mission Control handoff. Use when the user asks for the finished result, final summary, what changed, how to run it, evidence, limitations, or next tasks.

  • Mission control knowledge base map

    MN755/Codex-Mission_Control/.codex/skills/mission-control-knowledge-base-map Skill

    1★ repo

    Build or inspect a graph-style map of docs, wiki pages, claims, entities, and relationships through Mission Control.

  • Mission control mcp builder

    MN755/Codex-Mission_Control/.codex/skills/mission-control-mcp-builder Skill

    1★ repo

    Design, build, or audit MCP servers and tool/resource/prompt contracts through Mission Control. Use for MCP schemas, stdio startup, auth boundaries, plugin packaging, and smoke tests.

  • Mission control memory state policy

    MN755/Codex-Mission_Control/.codex/skills/mission-control-memory-state-policy Skill

    1★ repo

    Define memory, state, checkpoints, resumability, and retention policy for Mission Control workflows and agents.

  • Mission control rag retrieval design

    MN755/Codex-Mission_Control/.codex/skills/mission-control-rag-retrieval-design Skill

    1★ repo

    Design retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.

  • Mission control subagent burst

    MN755/Codex-Mission_Control/.codex/skills/mission-control-subagent-burst Skill

    1★ repo

    Recommend or review Mission Control Codex subagent bursts for bounded read-heavy work. Use when the user wants parallel exploration, review, planning, handoff audit, or failure diagnosis without replacing the normal worker system.

  • Mission control swarm

    MN755/Codex-Mission_Control/.codex/skills/mission-control-swarm Skill

    1★ repo

    Inspect or adjust Mission Control swarm behavior. Use when the user wants to show the swarm plan, explain agent roles, scale up or down, change strategy, pause dynamic spawning, resume dynamic spawning, or inspect active agents.

  • Mission control agent contracts

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-agent-contracts Skill

    1★ repo

    Show or request Mission Control agent contracts. Use when the user wants to inspect a worker mission, allowed paths, forbidden paths, tools, validation obligations, stop conditions, or escalation rules.

  • Mission control agent graph workflows

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-agent-graph-workflows Skill

    1★ repo

    Design graph-style agent workflows with nodes, edges, gates, retries, checkpoints, and human approvals through Mission Control.

  • Mission control agent stuck

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-agent-stuck Skill

    1★ repo

    Diagnose a stuck Mission Control agent. Use when an agent shows no output, repeats errors, times out, asks for the same approval repeatedly, or stops making progress events.

  • Mission control agents md

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-agents-md Skill

    1★ repo

    Generate or review AGENTS.md from Mission Control understanding. Use when the user wants AGENTS.md proposed from the codebase map, existing instructions reviewed, or a safe draft prepared before writing.

  • Mission control approve

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-approve Skill

    1★ repo

    Relay Mission Control approvals and questions to the user. Use when there are pending command approvals, tool approvals, write permissions, Manager questions, swarm approvals, recovery decisions, or handoff review gates.

  • Mission control benchmark comparison

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-benchmark-comparison Skill

    1★ repo

    Compare before-and-after performance evidence through Mission Control without turning benchmark claims into theater.

  • Mission control claude cli mode

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-claude-cli-mode Skill

    1★ repo

    Use or prefer Claude CLI runner mode through Mission Control. Use when the user explicitly wants Claude CLI if configured and Codex should verify availability and fallback rather than assuming setup exists.

  • Mission control continue handoff

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-continue-handoff Skill

    1★ repo

    Continue work after a Mission Control handoff without losing continuity. Use when the user wants another iteration, wants limitations preserved, or needs the next change request to build on the previous handoff and evidence.

  • Mission control evals observability

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-evals-observability Skill

    1★ repo

    Design or run evaluation, tracing, callback, telemetry, and regression-observability workflows for Mission Control agents.

  • Mission control handoff audit burst

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-handoff-audit-burst Skill

    1★ repo

    Use when Mission Control should recommend a read-only handoff audit burst for run instructions, validation evidence, limitations, docs quality, and security caveats.

  • Mission control handoff

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-handoff Skill

    1★ repo

    Retrieve and present the final Mission Control handoff. Use when the user asks for the finished result, final summary, what changed, how to run it, evidence, limitations, or next tasks.

  • Mission control knowledge base map

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-knowledge-base-map Skill

    1★ repo

    Build or inspect a graph-style map of docs, wiki pages, claims, entities, and relationships through Mission Control.

  • Mission control mcp builder

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-mcp-builder Skill

    1★ repo

    Design, build, or audit MCP servers and tool/resource/prompt contracts through Mission Control. Use for MCP schemas, stdio startup, auth boundaries, plugin packaging, and smoke tests.

  • Mission control memory state policy

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-memory-state-policy Skill

    1★ repo

    Define memory, state, checkpoints, resumability, and retention policy for Mission Control workflows and agents.

  • Mission control rag retrieval design

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-rag-retrieval-design Skill

    1★ repo

    Design retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.

  • Mission control review handoff

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-review-handoff Skill

    1★ repo

    Use when Codex should retrieve Mission Control status, evidence, and final handoff notes for review with the user.

  • Mission control subagent burst

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-subagent-burst Skill

    1★ repo

    Recommend or review Mission Control Codex subagent bursts for bounded read-heavy work. Use when the user wants parallel exploration, review, planning, handoff audit, or failure diagnosis without replacing the normal worker system.

  • Mission control swarm

    MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-swarm Skill

    1★ repo

    Inspect or adjust Mission Control swarm behavior. Use when the user wants to show the swarm plan, explain agent roles, scale up or down, change strategy, pause dynamic spawning, resume dynamic spawning, or inspect active agents.

  • Mission control agent contracts

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-agent-contracts Skill

    1★ repo

    Show or request Mission Control agent contracts. Use when the user wants to inspect a worker mission, allowed paths, forbidden paths, tools, validation obligations, stop conditions, or escalation rules.

  • Mission control agent graph workflows

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-agent-graph-workflows Skill

    1★ repo

    Design graph-style agent workflows with nodes, edges, gates, retries, checkpoints, and human approvals through Mission Control.

  • Mission control agent stuck

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-agent-stuck Skill

    1★ repo

    Diagnose a stuck Mission Control agent. Use when an agent shows no output, repeats errors, times out, asks for the same approval repeatedly, or stops making progress events.

  • Mission control agents md

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-agents-md Skill

    1★ repo

    Generate or review AGENTS.md from Mission Control understanding. Use when the user wants AGENTS.md proposed from the codebase map, existing instructions reviewed, or a safe draft prepared before writing.

  • Mission control approve

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-approve Skill

    1★ repo

    Relay Mission Control approvals and questions to the user. Use when there are pending command approvals, tool approvals, write permissions, Manager questions, swarm approvals, recovery decisions, or handoff review gates.

  • Mission control benchmark comparison

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-benchmark-comparison Skill

    1★ repo

    Compare before-and-after performance evidence through Mission Control without turning benchmark claims into theater.

  • Mission control claude cli mode

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-claude-cli-mode Skill

    1★ repo

    Use or prefer Claude CLI runner mode through Mission Control. Use when the user explicitly wants Claude CLI if configured and Codex should verify availability and fallback rather than assuming setup exists.

  • Mission control continue handoff

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-continue-handoff Skill

    1★ repo

    Continue work after a Mission Control handoff without losing continuity. Use when the user wants another iteration, wants limitations preserved, or needs the next change request to build on the previous handoff and evidence.

  • Mission control evals observability

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-evals-observability Skill

    1★ repo

    Design or run evaluation, tracing, callback, telemetry, and regression-observability workflows for Mission Control agents.

  • Mission control handoff audit burst

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-handoff-audit-burst Skill

    1★ repo

    Use when Mission Control should recommend a read-only handoff audit burst for run instructions, validation evidence, limitations, docs quality, and security caveats.

  • Mission control handoff

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-handoff Skill

    1★ repo

    Retrieve and present the final Mission Control handoff. Use when the user asks for the finished result, final summary, what changed, how to run it, evidence, limitations, or next tasks.

  • Mission control knowledge base map

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-knowledge-base-map Skill

    1★ repo

    Build or inspect a graph-style map of docs, wiki pages, claims, entities, and relationships through Mission Control.

  • Mission control mcp builder

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-mcp-builder Skill

    1★ repo

    Design, build, or audit MCP servers and tool/resource/prompt contracts through Mission Control. Use for MCP schemas, stdio startup, auth boundaries, plugin packaging, and smoke tests.

  • Mission control memory state policy

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-memory-state-policy Skill

    1★ repo

    Define memory, state, checkpoints, resumability, and retention policy for Mission Control workflows and agents.

  • Mission control rag retrieval design

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-rag-retrieval-design Skill

    1★ repo

    Design retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.

  • Mission control subagent burst

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-subagent-burst Skill

    1★ repo

    Recommend or review Mission Control Codex subagent bursts for bounded read-heavy work. Use when the user wants parallel exploration, review, planning, handoff audit, or failure diagnosis without replacing the normal worker system.

  • Mission control swarm

    MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-swarm Skill

    1★ repo

    Inspect or adjust Mission Control swarm behavior. Use when the user wants to show the swarm plan, explain agent roles, scale up or down, change strategy, pause dynamic spawning, resume dynamic spawning, or inspect active agents.

  • Remember

    gzb1128/skill-forge/plugins/agent-docs/skills/remember Skill

    1★ repo

    Skill Forge: Claude Code plugin marketplace for agent harness docs, code quality workflows, and OpenCode customization.

  • Skill creator

    gzb1128/skill-forge/plugins/skill-creator/skills/skill-creator Skill

    1★ repo

    Skill Forge: Claude Code plugin marketplace for agent harness docs, code quality workflows, and OpenCode customization.

  • Chrome devtools mcp

    mauriciovieira/skills/skills/engineering/chrome-devtools-mcp Skill

    1★ repo

    Scaffolds a dedicated Chrome instance with an isolated, persistent profile plus a chrome-devtools-mcp (CDP) server registration, so Claude can inspect authenticated network traffic in a web app - list open tabs, navigate, and read real requests (method, URL, sensitive headers, body, response shape) to reverse-engineer an API. Use when the user wants to inspect authenticated traffic in a browser, capture real headers/cookies for an integration, reverse-engineer a web app's undocumented API, or asks to set up chrome-devtools-mcp / CDP debugging.

  • Setup mauricio vieira skills

    mauriciovieira/skills/skills/engineering/setup-mauricio-vieira-skills Skill

    1★ repo

    Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` recording this repo's issue tracker, triage label vocabulary, and domain doc layout - the issue tracker and triage labels are optional bookkeeping (not read by any shipped skill; mainly documentation or groundwork interop), but domain docs are what `diagnose`, `tdd`, and `zoom-out` actually read. Run before first use of those three, or if they appear to be missing domain-doc context.

  • Setup worktree

    mauriciovieira/skills/skills/engineering/setup-worktree Skill

    1★ repo

    Use when the user is in a linked git worktree and needs to bootstrap it from the main repo - symlinks language-agnostic dependency directories (node_modules, .venv, vendor, target, deps) and copies env files. Trigger phrases include "setup worktree", "/setup-worktree", "bootstrap worktree", or when the user just created a worktree and wants to install/run dev.

  • Git guardrails claude code

    mauriciovieira/skills/skills/misc/git-guardrails-claude-code Skill

    1★ repo

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

    The same file is in 18 other repositories

  • Sync dotfiles

    mauriciovieira/skills/skills/misc/sync-dotfiles Skill

    1★ repo

    Sync your local agent/editor config (e.g. ~/.claude/, ~/.cursor/) into a dotfiles git repo, show the diff, and prompt for a commit. Use when the user asks to "sync dotfiles", "push my claude/cursor config", "save my editor settings to dotfiles", or after editing global config that should propagate to other machines.

  • Handoff

    mauriciovieira/skills/skills/productivity/handoff Skill

    1★ repo

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

    The same file is in 13 other repositories

  • Write a skill

    mauriciovieira/skills/skills/productivity/write-a-skill Skill

    1★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories

  • Skill creator

    yzp100911/skillgate-agent/cclaw/data/codex-home/skills/.system/skill-creator Skill

    1★ repo

    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 Codex's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 3 other repositories

  • Proactive agent

    yzp100911/skillgate-agent/cclaw/data/workspace-main/skills/proactive-agent Skill

    1★ repo

    Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

    The same file is in 1 other repository

  • Skill creator

    yzp100911/skillgate-agent/xCrab/cclaw/data/codex-home/skills/.system/skill-creator Skill

    1★ repo

    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 Codex's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 3 other repositories

  • Proactive agent

    yzp100911/skillgate-agent/xCrab/cclaw/data/workspace-main/skills/proactive-agent Skill

    1★ repo

    Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

    The same file is in 1 other repository

  • Browser use guide

    yzp100911/skillgate-agent/xCrab/skills/browser-use-guide Skill

    1★ repo

    让AI代理控制浏览器自动化网页操作。支持 Claude/GPT/Gemini/Ollama,可执行填表、购物、搜索等任务。

    The same file is in 1 other repository

  • Openclaw agent browser

    yzp100911/skillgate-agent/xCrab/skills/openclaw-agent-browser Skill

    1★ repo

    Headless browser automation CLI for AI agents. Use when interacting with websites — navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, scraping, testing web apps, downloading files, or automating any browser task. Triggers on requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data", "test this web app", "login to a site", "monitor a page", or any task requiring programmatic web interaction.

    The same file is in 2 other repositories

  • Self improving proactive agent

    yzp100911/skillgate-agent/xCrab/skills/self-improving-proactive-agent Skill

    1★ repo

    A unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work moving with clear boundaries.

    The same file is in 1 other repository

  • Ts tsconfig modern strict starter

    kongyo2/agent-primary-ts-starters/ts-tsconfig-modern-strict-starter Skill

    1★ repo

    Set up a TypeScript 7 tsconfig.json with maximally strict, machine-verifiable settings tuned so the LLM agent doing the editing gets the largest possible share of its mistakes reported as compiler errors, in output it can consume. Use whenever a tsconfig.json is being created, edited, reviewed, troubleshot, or even just discussed — apply the standing policy even when the user only asks about a single option. Default to this skill instead of free-recall whenever the answer involves a tsconfig field.