build-agent

Solid

Lab composer command scaffold for `/build-agent <name>`. In Agent Builder A1 this only creates a lab-scoped draft agent record and opens that lab's agent detail route for editing. It does not build, run, evaluate, observe, or deploy agents yet.

AI & Automation 20 stars 0 forks Updated 1 weeks ago Apache-2.0

Install

View on GitHub

Quality Score: 77/100

Stars 20%
44
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
67
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# build-agent - lab-scoped draft agent bootstrap Use this skill when the user enters `/build-agent <name>` in a lab chat composer and intends to start defining a new agent inside the current lab. ## A1 behavior The A1 command is intentionally small: 1. Read the agent name from the command text. 2. Create a draft agent record scoped to the current lab. 3. Open the lab-scoped agent detail route: ```text /labs/<lab_id>/agents/<agent_id> ``` The created record is a placeholder for future builder steps. Treat its config as an editable draft, not as a runnable or published agent. ## Required scope - The command must run from an active lab context. - The created agent must carry the current lab id. - Lists and detail views must stay under that lab. - A user without access to the lab must not be able to see or create records for that lab. ## Non-goals in A1 - No actual agent build pipeline. - No run, evaluation, gauntlet, battleground, or publish workflow. - No observability integration. - No deployment orchestration. - No global agents surface; agent records are reached from the owning lab. ## Operator response After the draft is created, keep the response minimal: name the draft and open the lab detail route. Do not imply the agent has been built, tested, deployed, or connected to runtime infrastructure.

Details

Author
Rockielab
Repository
Rockielab/rockie-claude
Created
3 months ago
Last Updated
1 weeks ago
Language
Python
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

agent-builder

Build any goal-declared agent end to end. Turns one declared goal into a portable, self-hardening, publishable agent repo on the Claude-Code harness. Declare goal, pick runtime/tools and write policies/hooks/safeguards, scaffold a portable repo (config-over-code split), build, run a fresh no-memory adversarial gauntlet, iterate with the clean-pass counter resetting on any failed round, publish ONLY after passing twice with zero CRITICALs, then export a .af agent-file. Biased to emit agents that contain their own internal adversarial critic loop. Triggers on "build an agent", "make me an agent that", "agent builder", "scaffold an agent", "publish this agent", "export to .af", "/agent-builder".

20 Updated 1 weeks ago
Rockielab
AI & Automation Listed

agent-builder

Generate role-specific agent system prompts, tool permissions, and self-review checklists from organizational design artifacts — saved to $HOME/.ai-first-kit/ with optional framework-specific configuration for Claude Code, OpenAI Agents SDK, Anthropic Agent SDK, CrewAI, or custom frameworks. Reads the organizational genome, governance, gates, and role definitions to produce agent configurations that embody a specific role in the organization. Use when the user says 'create agent instructions', 'build an agent', 'agent system prompt', 'configure an agent', 'agent for this role', 'OpenAI agent', 'CrewAI agent', 'create agent config', 'deploy an agent', or 'what tools should this agent have'. Also use when the user has completed role-value-mapper and wants to actually deploy agents that follow the organizational genome, or when they ask 'how do I make an agent follow our rules' or 'how do I create an OpenClaw agent for our org' — even if they don't use the word 'builder'. This skill MUST be consulted because it

6 Updated today
synaptiai
AI & Automation Listed

build-agent

Stage, launch, grade, and schedule a Claude Managed Agent (CMA) from a build-sheet. Triggered by 'build the agent', 'launch this agent', 'deploy a managed agent', or as /imagine-agent's handoff.

20 Updated yesterday
tomcounsell