cdcx-autonomy-levels
Progressive agent autonomy — from read-only to fully autonomous. Pick the lowest level that gets the job done.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
Agents & models
25,975 results
cdcx-check-balance
Verify credentials and inspect account balance — the first action an agent takes before trading.
handoff
Save task state in a structured Markdown handoff for a fresh-context agent. Use when asked to hand off, save state, or prepare a session for continuation.
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…
call-agent
Delegate a bounded task to a user-named peer CLI, or to fill a capability the host lacks. Supports Codex, Claude, Antigravity, Kiro, NotebookLM, and ChatGPT…
refine-skill-terse
Tighten a SKILL.md so agents (not humans) read it fast - cut prose, keep the procedure, move rationale out. Use when the user says "make the skill succinct",…
skill-cleanup
Archive unused or stale Claude/Codex skills based on skill usage stats without deleting content. Use for clean up skills, archive unused skills, or skill cleanup.
skill-lab
Build and iteratively improve agent skills with evaluations, benchmarks, and trigger optimization. Use when a user wants to test or refine a new skill, modify…
streamdeck-agent-cockpit
Use when a user wants a standalone Stream Deck cockpit for Claude Code, Codex, Pi, JCode, or other terminal agents: personalize buttons,…
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output…
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…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any…
install-plugins
Use when a user asks how to install plugins from this marketplace, needs onboarding to the Claude Code plugin system, or encounters plugin installation errors…
skill-creator
Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with…
context-diet
Cut Claude Code system-prompt bloat by disabling unused tools/skills in settings.json. Use when reducing token usage.
handoff
Handoff: saves state to pause, resume, or transfer work. Use when: "handoff", "pause here and continue later", "hand this over to QA or another agent".
sol
Orchestrate application work through GPT-6.1 Sol subagents (high reasoning, fast tier). Use for /sol, "use sol", or handing build, fix, backend, browser or QA…
legal-meta-skill
Used to create, transform, audit, or evaluate reusable mainland China legal Skills: use a general legal capability model to establish applicability records for jurisdiction and point in time, subject roles, legal relationships and claim elements, legal source interpretation, evidence/burden of proof/standard of proof, procedural deadlines, remedies and enforcement, and human review, and complete modeling, packaging, and dual-track evaluation. Suitable for contract review, case analysis, litigation analysis, PDF evidence processing, and legal meta-Skills...
agentpostage
Send PDFs as physical US mail with AgentPostage and check prices, letter status, balance, tracking or return receipts. Use for mailing bank disputes, gym…
orchestration
Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task…
fipa-00023-agent-management
FIPA standard for agent platform management including lifecycle, directory, and communication services
agentic-calendar-coordination
AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim,…
alphago-deep-rl
Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo…