Skill · Workflow

competitor-research-brief

A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources. Use when asked to run the "Competitor research brief" workflow.

The skill itself. Agents read the name and description first and load the rest only when a task matches.

competitor-research-brief/SKILL.md
---
name: competitor-research-brief
description: A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources. Use when asked to run the "Competitor research brief" workflow.
---

# Competitor research brief

A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources.

## Inputs

Ask for any of these that the user hasn't given:

- `company` (e.g. "Prompts-GPT.com")
- `competitors` (e.g. "PromptBase, FlowGPT, PromptHero")

## Steps

Run the steps in order. Refer to saved results by name. Don't skip a step that says STOP.

1. **Manual start** — Start: Start with {{company}} and {{competitors}}.
2. **Plan the research** — List the 5 questions that matter for {{company}}: pricing, audience, top content, traffic sources, gaps. Save the result as `plan`.
3. **One subagent per competitor** — Launch these as parallel subagents in one message, then wait for all of them. For each name in {{competitors}}, answer {{plan}} with a source URL for every claim. Save the result as `notes`.
   - **Competitor 1**: Answer the plan for the first competitor.
   - **Competitor 2**: Answer the plan for the second competitor.
   - **Competitor 3**: Answer the plan for the third competitor.
4. **Write the brief** — Turn {{notes}} into a one-page brief: a comparison table, 3 openings for {{company}}, and sources. Save the result as `brief`.
5. **Save the brief** — Finish: Save {{brief}} to research/competitors.md.

## Done when

Every step has run, each approval was given, and you've reported what was produced and where it was saved.