task-decomposition
Break complex tasks into GIVEN/UNKNOWN/PLAN before taking action. Use when tasks have multiple steps, require planning, or involve multi-step reasoning.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
agent-deadline-setup
Installs, configures or removes the agent-deadline hooks (soft wall-clock budget for subagents). Triggers: agent-deadline, subagent timeout, agent time limit,…
agent-return-setup
Installs, configures or removes the agent-return hooks (size budget on every subagent's final return message). Triggers: agent-return, subagent return budget,…
agent-router-setup
Installs, configures or removes the agent-router hook (routes a generic Agent spawn to the real project/plugin expert). Triggers: agent-router, wrong agent,…
agents
Creates, improves, syncs Claude Code subagents. Triggers: create agent, improve agent, sync agents, memory sync.
manager-setup
Manager mode: project hard delegation wall — status, install, upgrade, enable, disable, uninstall, purge, level, edit — and prompt codewords ++m, ++a, ++rr,…
memory-sync-setup
Generates a project-tailored memory-sync skill: memory surface batches, checkable-fact catalogue, non-growth sync, independent verify, self-sync, agent…
semble-setup
Installs, audits, repairs, updates, enables, reindexes or removes the semble_code semantic code-search MCP for a project. Triggers: semble, semantic code…
skills
Lists, improves, creates, syncs Claude Code skills. Triggers: create skill, improve skill, sync skills, memory sync.
task-board-init
Generator: deploys a file-based Kanban into ANY repo via multi-agent analysis, with an optional gated CLAUDE.md-optimization pass. Triggers: init task board,…
teams-setup
Creates and manages dynamic teams of domain agents. Triggers: create team, agent team, team status, cleanup team.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
claude-code
Drive Anthropic's Claude Code CLI (`claude -p`) as a non-interactive coding sub-agent from inside Codex. Use when you want to delegate a…
subagentmaxxing
Spawn and control non-Claude coding-agent subagents (OpenAI Codex CLI and Cursor CLI — grok-4.5, composer-2.5, gpt-5.5) as one-prompt-in/one-answer-out…
reservoir-production
Guide AI agents through reservoir management and production optimization.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude…
storage-analyzer
macOS / Windows read-only storage analysis assistant (auto-detects the system). Scans whole-machine disk usage, finds the big space consumers, sorts each item into three levels: 🟢 can be cleaned automatically / 🟡 requires manual judgment / 🔴 clean with caution, and gives an executable remediation plan, generating a beautifully formatted, collapsible, interactive HTML report with one-click copyable commands, and can…
work-tickets
Continuously execute an approved ticket set from its tracker frontier until complete or human judgement is required.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any…
mcp-server-builder
Build Model Context Protocol (MCP) servers that expose tools, resources, and prompts to LLM clients. Covers the official Python SDK (FastMCP) and the…
skill-builder
Create, validate, and package Agent Skills from scratch. Explains the SKILL.md format and frontmatter, how to write a high-signal description that triggers…
agent-desktop-macos
macOS platform guide for the agent-desktop CLI. Use for desktop automation on macOS: granting Accessibility and Screen Recording permission (TCC), what headed…
looker
Semantic search over EasyPost's Looker BI instance via MCP tools (mcp__looker__*). Use when: (1) finding what data exists in Looker ('what dashboard shows…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…