القائمة
Build and maintain product-grade agent infrastructure: onboarding diagnostics, runtime home, packaging, skill lifecycle, tool manifests, and agent scaffolds.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Intelligent routing between Bravo and Codex — decides when to delegate tasks to Codex vs handle internally
Secrets and authentication management. Ensures API keys, tokens, and credentials are NEVER exposed in plain text. Use when handling any credential, API key, or sensitive configuration.
Use when CC asks to create a new agent, scaffold a new agent repo, or clone Bravo's architecture for a new domain (client agent, sibling agent, specialized agent). Generates a new AI-agent repo from templates, wires it into C_SUITE_ARCHITECTURE.md and brain/APP_REGISTRY.md, preserves the V5.6 outbound chokepoint, and gives the new agent a doctor command on day one.
Claims-based access control for multi-agent coordination. Defines what each agent can read, write, execute, and spawn. Enforces least-privilege: agents only access what they need. Use when: spawning agents, multi-agent tasks, security-sensitive operations. Skip when: single-agent inline work, trivial tasks.
Spawn and coordinate Claude Code Agent Teams (experimental) — parallel subagents for complex multi-domain tasks
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
| name | agent-runtime-packaging |
| description | Build and maintain product-grade agent infrastructure: onboarding diagnostics, runtime home, packaging, skill lifecycle, tool manifests, and agent scaffolds. |
| triggers | ["agent runtime packaging","use agent runtime packaging","run agent runtime packaging"] |
| tier | specialized |
Use this skill when turning Bravo, Atlas, Maven, Aura, Hermes, or a client agent from a repo into an installable, diagnosable, repeatable product.
The goal is Hermes-grade infrastructure under Bravo-grade business intelligence.
Business intelligence sits on top of infrastructure. The infrastructure should make the agent easy to install, inspect, operate, repair, extend, and package for another business.
Every productized agent should have:
AGENTS.md, CLAUDE.md, GEMINI.md, ANTIGRAVITY.md.brain/, memory/, state, active tasks, session log.~/.bravo, ~/.atlas, ~/.maven, ~/.aura, or client-specific equivalent.scripts/onboarding_diagnostics.pyscripts/browser/browser_harness_doctor.pyruntime/README.mdinstall/README.mdconfig/bravo-config.example.tomlskills/browser-harness/SKILL.mdbrowser/domain-skills/When packaging a new agent:
Skills should move through these states:
draft: local only, not trusted yet.registered: discoverable in docs and registry.validated: used successfully and passes structural checks.promoted: included in the default agent pack.deprecated: replaced or unsafe, retained only for history.Every skill needs:
name and description.Doctor commands must be read-only and should print:
Doctor commands should not:
.env.agentsNever let packaging work bypass Bravo's business safety:
scripts/integrations/send_gateway.py.