From advisor-skills
Before beginning any implementation, investigation, review, or other task expected to take more than a trivial amount of work
How this skill is triggered — by the user, by Claude, or both
Slash command
/advisor-skills:intentional-delegationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use subagents deliberately to reduce cognitive load, improve parallelism, or obtain independent judgment. Delegate because it improves the outcome—not because delegation is the default.
Use subagents deliberately to reduce cognitive load, improve parallelism, or obtain independent judgment. Delegate because it improves the outcome—not because delegation is the default.
The controller (you) owns planning, decomposition, integration, and final decisions. Subagents own bounded missions.
Ask these questions:
If most answers are yes, delegate. Otherwise, keep the work in the controller.
Keep work in the controller when it requires:
Use for work that is already defined.
Examples:
Execution agents should not invent solutions when requirements are unclear. If they encounter meaningful ambiguity, they should stop and report it.
Use when independent judgment is valuable.
Examples:
Consulting agents provide recommendations, not final decisions.
Prefer tasks that are naturally isolated.
Good:
Avoid splitting work with heavy back-and-forth dependencies.
Give each subagent only the information it needs.
Include:
Avoid copying unnecessary conversation history.
Never assume a subagent is correct.
Review:
The controller owns the final result.
npx claudepluginhub qduc/claude-skills --plugin advisor-skillsGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Enforces test-driven development: write failing test first, then minimal code to pass. Use when implementing features or bugfixes.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.