llk-test-runner-skill
Delegates LLK test runs to the llk-test-runner agent using @.cursor/agents/llk-test-runner.md. Use when the user asks to run tests or mentions LLK tests. Ensure test commands run to completion before reading terminal output (no polling).
codex-implementation-loop
Delegate implementation work to Codex (via the codex-companion runtime), then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex to write code, mentions handing off / delegating implementation to Codex, asks to work through a plan or spec unit-by-unit with Codex doing the coding, or wants a review-and-merge loop wrapped around Codex output â and also when resuming such a loop ("keep going", "next unit", "继ç»ä¸ä¸ä¸ª"). It encodes constraints that are expensive to rediscover: Codex runs in the real environment with effectively read-only git, must not be pointed at a full test suite by default, accepts only specific --effort values, and its self-report is a claim rather than evidence.
agpair
Use agpair to delegate coding work to supported executors (currently Antigravity, Codex, and Gemini), check doctor/status/watch, and drive retry flows.
deliberation
When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
Io.Github.Ferm Ai/Agentwork Mcp
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
analyze-with-file
Interactive collaborative analysis with documented discussions, inline exploration, and evolving understanding. Serial execution with no agent delegation.
create-beads-orchestration
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.
haiku-pilot
Haiku-first execution playbook: through deliberate prompt structure, sub-agent delegation, and quantitative escalation gates, get Haiku 4.5 to produce near-Opus quality on most tasks. Escalate to Sonnet/Opus only when gates trigger. Triggers: "haiku", "Haiku", "Haiku mode", "haiku-pilot". Do NOT use for: cost-only token optimization, file-count cognitive heuristic, agent dispatch table, CLAUDE.md / rules audit, harness health check. This SKILL is a runtime router + escalation gate, not a decision tree or directory.
gemini-delegate
Use when the task is dominated by large-context reading, synthesis, long-form drafting, bilingual or CJK writing, or second-opinion review rather than bulk code generation. Typical triggers include English or Chinese summaries of large source material, cross-file synthesis, terminology alignment, release-note drafting, and reviewer-style passes over documentation or generated output.
propr
Delegate software changes through ProPR's GitHub-integrated issue-to-PR orchestration. Use when asked to diagnose, implement, monitor, review, test, merge, deploy, or publish repository work through ProPR.
ccs-delegation
Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Triggers on "use ccs [task]" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.
NeedHuman
Human-as-a-Service for AI agents. Delegate tasks that need a real human, get results via API.
ClawTeam Skill
ClawTeam enables **collaboration between AI agents**. You can discover other agents, delegate tasks, send messages, and execute work â all through the Gateway API using curl commands.
Agent Passport System — Cryptographic Identity for AI Agents
Cryptographic identity, delegation, governance, and commerce for AI agents. 61 tools.
agentic-data-science-competition
AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing submission failures, setting up automated pipelines, or replicating top notebook solutions.
b0
Delegate tasks to AI agents via Box0. Use when the user asks to review code, check security, run tests, compare tools, get multiple perspectives, research a topic, analyze data, write docs, or any task that could benefit from specialized or parallel execution. Also use when the user mentions agent names or says "ask", "delegate", "get opinions from", or "have someone".
Coding CLI Delegation
When the Manager assigns you a task with a "## Coding CLI Mode" section in `spec.md`, you do **not** write the code yourself. Instead, you:
AgentAuth
Identity and auth for AI agents: credentials, tokens, delegations, and permission checks.
openclaw-management
This skill should be used when the user wants to interact with OpenClaw, delegate tasks to their AI assistant, or check gateway status. Activates for AI assistant delegation and orchestration.
Io.Github.Junct Bot/Eigenlayer Mcp
Eigenlayer - 8 tools for staking, delegation, and rewards data
collaborating-with-codex
Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.
PKM Session End â Knowledge Capture and Graph Maintenance
Workflow for session wrap-up. When running as a subagent, the delegation prompt provides the project path and devlog boundary context. The agent's system prompt handles transcript discovery (Step 0) before this workflow begins.
Io.Github.IndigoProtocol/Cardano Mcp
Cardano MCP — transactions, addresses, UTxOs, balances, ADAHandles & stake delegation
build-agent
Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a new agent, when the user describes a specialised role they want delegated to, or when discussing team composition.
Agents - Custom Agent Composition System
**Auto-routes when user mentions custom agents, agent creation, or specialized personalities.** **Does NOT handle agent teams/swarms â that's Delegation skill â TeamCreate.**
agent-bus
Coordinate work across Claude/Codex/Cursor sessions on the same machine via a local message bus. Use to delegate to helpers, get a second opinion, ask specialists by capability, or track shared tasks.
context-pack
Creates structured handoff briefings between agents. Packages task context, constraints, and progress into a compact packet that subagents can consume without re-reading the full conversation. Prevents the 'lost context' problem in multi-agent delegation.
agent-smith
Use when a complex task needs parallel decomposition into independent subtasks, when multiple agents must work simultaneously without conflicts, or when recursive task delegation is required
Claude Code Skill (`/ask-json`)
`claude-wire` ships with a companion [Claude Code](https://claude.ai/download) skill, [`ask-json`](https://github.com/pivanov/ai-skills/tree/main/skills/ask-json), that teaches the main Claude agent to delegate "give me typed JSON" work to the CLI as a cheap sub-agent.
continual-learning
Orchestrate continual learning by delegating transcript mining to agents-memory-updater and writing durable memory to local JSON (never root AGENTS.md Learned sections). USE WHEN continual learning, mine prior chats, maintain agent memory, or the stop hook triggers this skill.
Io.Github.Hungnguyenhtbvn Max/Autron Core
Open Identity Standard for AI Agents — DID, Agent Cards, delegation, reputation, payment & escrow
codex-delegate
Delegate a heavy or mechanical coding task to the configured Codex CLI model via a low-effort Sonnet wrapper, so Codex's large transcript stays OUT of the main orchestrator context. Trigger when the user says "delegate to codex", "hand this to codex", "let codex do X", or when a well-specified implementation/refactor/migration/bulk task is large enough that doing it inline would flood context with tool round-trips. Do NOT use for small tasks you can one-shot.
Automated Implementation Review (Code Review) / using a supervisor agent
You are a technical lead supervising a software engineer (subagent). You do not write code or use development tools yourself â you delegate all implementation work to the engineer.
sips-delegation-router
Route a task through SIPS commands, agents, scripts, MCP tools, or bounded delegation. Use when asked to route, split, fan out, escalate, or choose the right SIPS path.
SWE-Manager â Autonomous Engineering Manager
You are the SWE-Manager, an always-on autonomous engineering manager for the SWE-Squad system. You operate as a persistent pi-agent session with 16 custom tools. You do NOT write code yourself â you delegate all investigation, development, review, testing, and merging to configured engines via the
attend
Route upstream epistemic deficits and evaluate execution-time risks during AI operations. Scans for unresolved upstream protocol needs, materializes intent into tasks, classifies each for risk signals, delegates low-risk tasks to executor, and surfaces elevated-risk findings for user judgment. Type: (ExecutionBlind, User, EVALUATE, ExecutionContext) â SituatedExecution. Alias: Prosoche(ÏÏοÏοÏή).
Io.Github.Junct Bot/Lido Mcp
Lido - 6 tools for staking, delegation, and rewards data
workflow-orchestration
Disciplined task execution with planning, verification, and self-improvement loops. Use when starting non-trivial tasks (3+ steps), fixing bugs, building features, refactoring code, or when rigorous execution with quality gates is needed. Includes subagent delegation, lessons tracking, and staff-engineer-level verification.
Browser Work
Recon-first browser automation: explore â document â delegate.
agent-cli-dev
Spawns AI coding agents in isolated git worktrees. Use when the user asks to spawn or launch an agent, delegate a task to a separate agent, or parallelize development across features. Only create a worktree without starting an agent if the user explicitly wants setup only.
sc-all
Turn a plain-language web-app goal into a working live app. Designed for non-technical users: choose architecture and hosting automatically, connect accounts safely, create/publish code, data, domain and verification end-to-end, delegate user-facing frontend quality to sc-fe, and expose technical details only when needed or requested.
backlog-technical-project-manager
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization; manage dependencies and overlapping code areas; review and approve sub-agent plans before implementation.
Control Agent (Baudbot)
You are **Baudbot**, a control-plane agent. Your identity: - **Email**: configured via `BAUDBOT_EMAIL` env var (create/verify inbox on startup) - **Role**: Monitor inbox, triage requests, delegate to worker agents
render-topologies
Render all .mmd files to PNG, pixel-diff against main, and open only changed renders as BEFORE/AFTER pairs in Preview. Use after layout or rendering changes to check for visual regressions. Works in worktree mode (fix branch vs main) or standalone mode (current working tree vs main). Companion to the fix-issue skill, which delegates full regression checks here.
agent-fanout
Use this skill when the user asks to "fan out agents", "spawn agents", "use an agent team", "parallel agents", "delegate to subagents", "act as team lead", "orchestrate implementation", "fan out teammates", or when a task decomposes into 2+ independent work items (parallel exploration, one implementer per issue, a multi-lens PR review panel). Covers the basic mechanics of spawning, briefing, supervising, and synthesizing subagents and teammates, plus the hard cap on fleet size.
Architect Research
You are the research orchestrator. Researchers gather; **you** design the decomposition, verify, and write â judgment never delegates. The source-class tactics library (search mechanics + verified endpoints per source class) is in `tactics.md` next to this file; read it when you design researcher
fusion-setup
Use when a user wants to set up, configure, install, or reconfigure the opencode Fusion agent team - a strong main/build agent that plans and reviews but cannot edit files, delegating all edits to a cheaper sidekick subagent, plus an explore search agent and optional research/design/reviewer/vision specialists. Triggers include "set up fusion", "configure fusion", "install fusion", "fusion setup", "undo fusion" / "remove fusion", changing which models the main, sidekick, or explore agents use, or naming a subscription to start from a ready-made profile - e.g. "set up fusion with my OpenCode Go subscription" (also OpenCode Zen, ChatGPT Plus/Pro, GitHub Copilot). Writes the global opencode config under ~/.config/opencode/.
agentify
Bootstraps a dispatchable Claude sub-agent skill for every coding agent CLI installed on this machine (codex, aider, cursor, etc.). Use when the user wants to delegate tasks to locally-installed agent CLIs or expand the plugin's agent fleet.
Sub Agents Mcp
MCP server for delegating tasks to specialized AI assistants in Cursor, Claude, and Gemini
campaign-conductor
Run a project as an orchestrated campaign: Claude as conductor (Fable 5.1, or Opus 5 when Fable is unavailable) dispatching a mixed fleet of workers, Claude Opus 5 agents for UI/UX and design judgment, Claude Sonnet 5 agents for surveys and search, OpenAI Codex CLI workers for implementation and everything else. Use whenever the user says "start a campaign", "campaign mode", "orchestrate this", "use the fleet", "mix of agents", "send out workers", "codex workers", or asks Claude to run a multi-task project by delegating to parallel agents rather than implementing directly. Also use when resuming work in a repo whose CLAUDE.md points at a campaign-hq folder.