Trigger: broad exploration, multi-file reads, tests/builds, fresh review, or multi-step debug. Orchestrate complex work via delegate_task to protect context.
SkillScore89Maintained
Automatic
◆Coding pack
Last verified 10/7/2026
What it changes
Passed 17 of 19 test cases with the skill, and 12 of 19 without it.
Without skill63%
With skill89%
Checks it passed that the model alone missed
Clarifies that worker tasks are ephemeral
Constrains the exact goal to one sentence
Specifies exactly one red test per requested rule
and 3 more in the full report
5 fixed12 passed either way2 still failing0 broke4 errored
Pass-rate lift
+26 pp
Tokens
+12%
Agent turns
0%
Response time
-49%
Model gemini-3.6-flashMeasured 10/7/2026v317 of 23 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
When writing a worker mission for updating `services/payment.ts`, what constraint applies to how the exact goal must be phrased?
What was checked, without and with the skill
Checked
Without skill
With skill
Constrains the exact goal to one sentence
Missed
Passed
case-21 · gemini-3.6-flash · 10/7/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md63 lines2 files
Activation Contract
Load this skill when you are acting as the parent orchestrator and the work ahead has a named reason to delegate:
A map you need to decide or route that exceeds the inline evidence budget (codebase mapping, approach comparison); never to read files you will read anyway before writing inline
A writer reason: 2+ independent units launched together, or the context backstop; a large task alone is tracked, not delegated
A high-risk change that needs an independent verifier, or a large task's long suites and builds
Fresh adversarial review (diffs, PR readiness, incident audit); never restart it automatically for a candidate whose terminal approved authority was already burned and that is unchanged since, unless a new independent review is deliberately requested
Multi-step debugging that would flood the parent context
Do NOT load this skill if you are already inside a delegated child task — you are the executor, not the orchestrator.
Hard Rules
Use delegate_task only for a named reason listed above. Without one, work inline following your logbook; file count, size, or a large task alone is never a reason.
Workers are EPHEMERAL: each delegate_task call creates a fresh context. Do NOT request persistent agent files or profiles.
Pass a self-contained mission. Workers have no memory of the parent conversation.
Treat worker output as self-report: verify file writes, test pass/fail, URLs, and IDs before reporting success to the user.
Batch parallel calls only for INDEPENDENT workstreams. Sequential dependencies must run sequentially.
Decision Gates
Situation
Action
Need a map to decide or route beyond the inline evidence budget
Delegate a narrow exploration worker
A large (tracked) task
Track it; delegate a writer only for a reason (parallel units or context) with the full mission
A small task's focused test and suite
Run inline, once each
A high-risk change or a large task's long suites
Delegate an executor
Need an adversarial review of a diff
Delegate a fresh-context reviewer
Multi-step debug that grows the context
Delegate a debug worker; feed results back inline
An understood change, even across files, with no named reason
Do it inline; no delegation needed
Quick git/state check
Do it inline; no delegation needed
Execution Steps
Identify which gate applies. If none applies, skip delegation.
Draft a self-contained mission for the worker — include:
Exact goal (one sentence)
File paths or targets to act on
Relevant prior context the worker needs (decisions, conventions, prior findings)