Menu
Use when asked to create or revise a LazyAI agent source definition while keeping generated tool-native agent files derived, not hand-edited.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when debugging a failing test, broken build, runtime error, or unexpected system behavior. Drives hypothesis-based investigation, root-cause fixes, verification, and reusable learning capture.
Use when a claim, plan, spec, doc, or design must be attacked against source evidence before implementation or approval. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when fixing broken behavior and the priority is reproduce, root cause, regression proof, and the smallest safe repair. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when reviewing code changes with explicit stage, target, and focus so own-code checks and others’ PR reviews stay distinct but share one contract. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when the deliverable is docs or reference material and every claim must stay tied to observed behavior or cited source evidence. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when adding or changing product behavior that must ship with explicit purpose, scenarios, and verification. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
| name | create-agent |
| description | Use when asked to create or revise a LazyAI agent source definition while keeping generated tool-native agent files derived, not hand-edited. |
Use this skill when the user asks to:
Do not use when the user is only discussing an idea. Do not use when a skill or plain rule is enough.
A shipped LazyAI agent has one source of truth. In this repository that source is packages/cli/library/canonical/agents/<name>.md. In a consuming setup, edit the canonical source your project compiles from and never hand-edit generated .opencode/, .claude/, or .github/ agent files.
lazyai-cli compile plus lazyai-cli doctor in a consuming project, or go test ./packages/cli/... plus go build ./packages/cli/... when changing LazyAI's embedded library or adapters.name and filename match.