delegation
SolidBefore spawning a subagent or dispatching a build, review or research, and before trusting its report: the brief, the delegate, parallel runs, the handoff.
Install
Quality Score: 91/100
Skill Content
Details
- Author
- phuryn
- Repository
- phuryn/product-engineering
- Created
- 2 weeks ago
- Last Updated
- today
- Language
- Python
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
delegate
This skill should be used before delegating work to an agent (one spawn or a whole wave) and when the user says "spawn an agent", "delegate this", "parallelize this", "use a subagent", "send this to Codex", or "use Codex Astra". It covers the spawn decision (inline vs spawn, model tier, batching), required prompt contents, WHAT-not-HOW development briefs with the one-agent plan/TDD/implement/self-review loop for changes up to 1000 LOC, durable tracking of multi-step work, and external Codex dispatch, job monitoring, and broker recovery.
delegation-detail
Use before writing any Agent brief or deciding whether to delegate, split or fan out work - brief shape (files to read first, what you left alone), when delegating pays, unit cap, parallel launch, liveness of a running delegate, impl loop and review/browser gates before a commit.
delegation-discipline
Decide whether subagents, parallel agents, or agent teams are justified and, if so, delegate safely: one agent unless work is bounded, independent, and clearly owned; explicit outcome, ownership, constraints, and return format per worker; the integrating agent owns final correctness, security review, and verification. Use whenever delegation or parallel execution is being considered.