Menu
Use when researching N independent topics, companies, or candidates - dispatches one subagent per topic and aggregates results
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
Use when the meta-builder routes to kind=discipline. Generates a discipline spell with the rule, excuses table, warning signs, and hard gates.
Use when the user wants to capture a repeatable task as a reusable spell, or asks "how do I build a workflow / skill / framework for X"
Use when the meta-builder routes to kind=subagent. Generates a spell that dispatches one or more subagents to do work in parallel or in isolation.
Use when the meta-builder routes to kind=workflow. Generates a workflow spell with explicit stages, checkpoints, and loop-back conditions.
Use when composing multiple spells into a chain that runs end-to-end (e.g. brainstorm -> plan -> execute -> verify).
Use when browsing what spells are available - bundled seeds, your personal library, or both. Filter by kind, audience, or update status.
| name | researching-five-things-in-parallel |
| description | Use when researching N independent topics, companies, or candidates - dispatches one subagent per topic and aggregates results |
| kind | subagent |
| audience | anyone |
| ai-tools | any |
| complexity | long-running |
| time | 10-30 min wall-clock for 5 topics |
| version | 1.0.0 |
| source | bundled |
When you need to research N independent topics (5 companies before a sales call, 5 candidates before interviews, 5 papers for a literature scan), this skill dispatches one research subagent per topic in parallel, aggregates results, and returns a unified brief.
A unified document where each item appears in the same format, plus a "compare" section that surfaces deltas across items.
This is a subagent dispatch. For each item in the input list, one research-helper subagent is dispatched in parallel; the parent aggregates after all return.
All N subagents (max 8 recommended) run concurrently. Wall-clock time is bounded by the slowest single subagent plus aggregation, not the sum.
Each subagent receives EXACTLY:
Each subagent does NOT receive: the other items, their results, or your overall purpose.
A single artifact in the agreed format. Plus a confidence rating (high/med/low) and a list of unanswered sub-questions.
The parent (you) waits for all subagents, then:
If a subagent fails (timeout, no sources found, ambiguous item), the result for that item is marked [NEEDS RE-RUN: <reason>]. The aggregation continues for the rest. Re-runs are dispatched serially with refined inputs. The chain does NOT block on one failed subagent.
Input:
Process: 5 research-helper subagents dispatched in parallel, each given exactly one company and the same prompt. ~8 min wall-clock.
Output:
[NEEDS RE-RUN: company name is ambiguous, found 3 entities]