Results for “sub-agent”

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.

Agent profile for review pricing, invoices, subscriptions, entitlements, revenue logic, tax-sensitive flows, and billing UX. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply when a task needs application launching, accessibility snapshots, stable element refs, window focusing, semantic clicks/typing, or visual confirmation outside the browser sandbox.

Runs a structured code review using four parallel subagents covering style, correctness, security, and performance, then synthesizes findings by severity and gives an approve/needs-changes recommendation.

Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.

Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.

Unified Agent Teams orchestrator for Diverga v12.0.0. Manages Agent Teams creation, VS Arena debate, and subagent dispatch. Single entry point for all parallel/debate workflows. Replaces research-orchestrator and vs-arena skills. Triggers: orchestrator, agent team, create team, parallel agents, debate, competing, collaborate, VS Arena

Spawns GLM-5 powered teammates with thinking mode for coding, review, testing, planning, and research tasks.

Use acpx as a headless ACP CLI for agent-to-agent communication, always inside an isolated SubAgent. Use when running coding agents through acpx, managing persistent ACP sessions, queueing prompts, consuming structured agent output from scripts, comparing the same prompt across multiple agents, or composing multi-agent workflows with defineFlow/decision/decisionEdge. Never invoke the claude adapter (nested-instance blacklist).

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the agent's design tree decision-by-decision — entity fit, domain focus and vocabulary, role identity, anti-patterns, description, model tier, tools, and self-containment — then reviews the finished agent against the plugin-building guidance and applies every fix it finds. Use when creating, authoring, scaffolding, designing, or drafting a new agent or subagent. Does not build a skill or slash command — use skill-builder. Does not serve, vendor, or refresh the authoring guidance itself — use guidance.

Analyze codebase structure, generate domain-specific sub-skills (UI, Backend, Database, etc.), and create agent-guidance files to help AI agents navigate and develop consistently within a project. Use when onboarding to a new codebase, creating project documentation, or setting up agent guidance systems.

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

Prove a feature works by delegating verification to an independent sub-agent that drives the real app, then open a pull request with the proof.

Inspect and adjust the agent's runtime state, including model, context window, iteration limits, token usage, workspace configuration, subagent status, and request routing metadata.

Adds extra research diligence to coding agents: plan sub-questions, retrieve and cross-check sources, and synthesize before implementing.

Investigates bugs, regressions, and crashes by dispatching four parallel read-only sub-agents, then ranks hypotheses and recommends the fastest proof or fix path.

Guides AI agents through the complete GDPR Data Subject Access Request (DSAR) workflow under Article 15, including identity verification, 30-day deadline calculation with extensions, response formatting, exemptions, and fee provisions. Activate when handling DSAR, access request, subject access, Art. 15, or SAR queries.

Migrate Claude Code configuration, skills, agents, and MCP servers to Codex project and global files.

Tracks multi-step work across sessions using the hzl CLI, coordinating sub-agents with checkpoints and leases.

Spawns GLM-5 powered teammates with native thinking mode for coding, review, testing, planning, and research tasks.

Orchestrating multi-session parallel execution via Claude Code Agent Teams API and Codex CLI Subagents — launch, manage, coordinate concurrent tasks. Use when parallel work is needed.

This skill should be used when executing Bankr requests, submitting prompts to Bankr API, polling for job status, checking job progress, using Bankr MCP tools, or understanding the submit-poll-complete workflow pattern. Provides the core asynchronous job pattern for all Bankr API operations.

Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. Covers supervisor, swarm, and hierarchical multi-agent patterns; subgraph composition; state management (checkpointers/stores); persistence; evals; and production debugging. Reach for this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns.

Decide which work is safe to delegate to worker agents. Use before delegating tasks that may require user interaction, approval, authentication, external writes, or shared-state mutation.

Integrate services or agent harnesses with the 33GOD Bloodbank event bus. Covers schemas in Bloodbank schemas/ and docs/event-naming.md, producing events (NATS preferred; Dapr, HTTP /publish, hookd_bridge alternatives), consuming events (NATS, Dapr, FastStream, event-toaster), and agent hook wiring through the canonical services/agent-hooks publisher. Use for event publish/consume, authoring schemas, integrating harnesses (Claude Code, Copilot CLI, OpenCode, Cursor, Aider, Codex CLI, Hermes), or debugging missing envelopes. Triggers: bloodbank, event bus, publish, subscribe, NATS subject, holyfields legacy, CloudEvents, event-toaster, ntfy.delo.sh/bloodbank, bloodbank.v1.agent.session.started, bloodbank.v1.agent.tool.completed, bloodbank.cmd.v1.agent.invocation.start. Skip for generic brokers, n8n, hindsight memory, or non-event-bus 33GOD.

Runs a structured self-review checklist before committing substantial code changes, covering edge cases, error paths, test coverage, documentation, and code quality.

Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM messages/reactions/chat changes, Approval status changes, Task updates, VC meeting started/joined/ended, Minutes generated, Whiteboard updated, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marker contract — designed for AI agents running as subprocesses.

Builds, tests, and deploys Microsoft 365 apps and agents for Teams and Copilot using the ATK CLI, with sub-skills for project creation, local testing, cloud deployment, troubleshooting, and Slack-to-Teams migration.

Post, claim, and settle agent tasks on the AZZLE protocol (Base mainnet, USDC escrow). Requires Bankr for swaps, approvals, and on-chain execution.

Spawns a researcher agent to investigate how to implement a project phase, gathering context on architecture patterns, standard libraries, and common pitfalls.

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Use when creating test scenarios for a skill, setting up a tests/ directory for a plugin or package, running skill tests against a subagent, or verifying whether a SKILL.md changes agent behavior

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.