القائمة
Design skill steps with explicit execution topology, asking which parts run directly, in subagents, in teammate swarms, or in parallel.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Collapse multiple change sources into one caller-facing boolean so headless bootstraps know whether a downstream refresh is necessary.
After awaiting persistence work, update the shared budget state for each `tool_use_id` exactly once so no concurrent reader ever sees a half-committed decision.
Issue continuation nudges while the turn stays under budget, then halt once diminishing returns or the budget cap justify stopping.
Lazily extract referenced files for bundled skills so large prompts stay offline until needed.
Persist a cache-safe stop-hook context snapshot only for main session queries so later helpers can resume from stable state without fork pollution.
Sweep stale extension caches before activation, then fall back to a sticky manual-refresh flag if the live refresh fails.
| name | parallelism-aware-skill-step-design |
| description | Design skill steps with explicit execution topology, asking which parts run directly, in subagents, in teammate swarms, or in parallel. |
| metadata | {"author":"ychampion"} |
Domain: multi-agent
Trigger: Use when converting a workflow into a skill and some steps may run in parallel, through task agents, through teammate swarms, or require human checkpoints.
Source Pattern: Distilled from reviewed multi-agent coordination and child-runtime patterns.
Model each major step not just by what it does, but by how it executes. During the interview, ask whether steps are independent, whether they should run directly or via agents, and whether any human confirmation is required before advancing. Then encode those answers into the saved skill so later agents know where concurrency is safe, where isolation is useful, and where execution must pause for a person.
If a launch skill needs one branch to post release notes and another to monitor CI, mark those steps as parallel and note the artifacts they return. If the next step merges a release branch, add a human checkpoint before that merge even though earlier monitoring ran through subagents.
