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 merely discussing an agent idea. Do not use when the behavior is better expressed as a skill.
A canonical agent is one markdown file under packages/cli/library/canonical/agents/<name>.md. Host-specific model/provider settings do not belong in canonical agent frontmatter.
Use packages/cli/library/canonical/agents/ existing agent files as the shape reference.
packages/cli/library/canonical/agents/<name>.md with name, description, and markdown system prompt sections.lazyai-cli compile to regenerate tool-native agent files.lazyai-cli doctor to verify output consistency.model, provider, color, or host-only settings to canonical frontmatter.lazyai-cli doctor verifies it.packages/cli/library/canonical/agents/<name>.md.name and filename match.description is one sentence and trigger-specific.lazyai-cli compile.