Menu
a description
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
Structure Claude prompts for clarity and better results using roles, explicit instructions, context, positive framing, and strategic organization. Use when crafting prompts for complex tasks, long documents, tool workflows, or code generation.
Pause agent execution to have the human validate decisions, choose between options, answer freetext, or comment on a document — via the `hl` CLI. Every interaction is a kickoff that returns a job handle immediately; collect the human's answer later with `hl job result`. Use for material design decisions, approval gates, picks between meaningful alternatives, and markdown doc review. Not for trivial yes/no confirmations the agent should decide itself.
Validate technical designs against requirements for coverage, feasibility, and architectural soundness. Use after creating a design.
Validate implementation plans against requirements and design. Use after creating a plan to ensure full coverage and no ambiguities.
Validate requirements documents for EARS compliance, completeness, and consistency. Use after creating requirements.
Design CLIs for humans and LLM agents — subcommand shape, output streams, exit codes, JSON modes, TTY-aware color, structured errors, mutation safety. Use when building or refactoring a CLI, adding machine-readable output, writing --help, deciding stdout vs stderr, or making a tool agent-friendly.
| name | a name |
| description | a description |
| context | fork |
| model | some-model |
| agent | some-agent-name |
This is an example skill, showcasing forked contexts. With forked context, the agent will execute in a fresh context, using the system prompt of the agent. It will pass the skill as context, along with arguments at the end, or replacing $ARGUMENTS with the arguments passed when the skill is called.
Use skills like this to make it so that subagents are prompted "perfectly"—there's the prompt from the agent, the system prompt from the agent, and then the pre-made prompt from the skill.
Skills are kinda like one-off agents that don't have to be used frequently. Subagents have fresh context by default anyway, though they can also be used in a way so that they DON"T have fresh context.
