In short:
ak-research-promptwrites a research brief clear enough to hand to a person or another AI with no follow-up questions: context, one main question, which sources to trust, how to present results. Once the brief is done, you hand it toak-researchor another researcher or research tool. It does not do the research itself.
Disclosure: I maintain AgentKit and have an affiliate relationship with it: the AgentKit link in this post is an affiliate link; buying through it gets you 30% off.
Summary
Use it when you need someone, a person or a research-focused AI, to look into a problem so you can make a decision. Do not use it when you want the research results right away: the skill only writes the brief.
flowchart LR
A["Topic or decision to make"] --> B["ak-research-prompt"]
B --> C["Research brief, stops here"]
C --> D["ak-research"]
C --> E["Another researcher or research tool"]Every brief always covers 4 points:
| Point | Question | Example |
|---|---|---|
| A self-contained brief | Can someone who knows nothing about your project start right away? | Opens with context: booking app for small clinics, Node, Postgres, about 200 clinics |
| One question, one decision | What decision will the results feed? | Should the SMS queue move to a managed service this quarter? |
| Source hierarchy | Which evidence counts, and which is only a hint? | Official docs, repos, changelogs first; forums are only a weak signal |
| How to return results | What must the researcher hand back? | One Markdown file, each finding with a source link, a claim and its bearing on the decision |
The brief also makes the researcher separate what is confirmed, what is inferred and what is unresolved when sources disagree, then recheck any claim backed by only one source. If the decision is simple or you ask for it, the brief is one paragraph; otherwise it uses short sections.
Sample prompt for choosing between options:
/ak-research-prompt Decision: should we move the SMS sending queue of <app name>
to a managed queue service this quarter.
Who reads the results: tech lead and accountant. Deadline: next Friday.
Known: we run our own worker on one VM, about 50 thousand messages a day.
Constraints: cost must not rise more than 20%, must retry when the carrier fails.This skill has no flags. The only input is the topic or decision to make, typed right after the skill name; you can put the reader, deadline, what you already know and the constraints in the prompt.
Below is the detailed version: the run flow, 4 situations with prompts, the change history by ak version and common pitfalls. The detailed version and the visual page are for subscribers. Your agent can also find them through the portal's MCP.
Opens when your account has subscriber access
This guide is for subscribers
Once your account has access, the full piece, the interactive visual and the agent call all open.
- Sign in or create a modernEngineer accountReading access belongs to your account email.
- Choose a plan on the pricing page1, 3 or 12 months, paid by VietQR bank transfer. Access opens about a minute after the money arrives.
- Or redeem a Facebook subscriber codePeople supporting the page on Facebook get an activation code by message each month.
Already a subscriber? Sign in to read.
Use this piece in your agent
Get an API keyCopy the text below and paste it into Claude Code, Codex or whichever agent you use. The agent reads the piece and checks it against the repo you have open.
Read "ak-research-prompt: write a research brief clear enough to hand off" on modernEngineer and apply it to this repo.
1. Call the content_get tool of the modernengineer MCP server with locale "en", slug "ak-research-prompt". If the modernengineer MCP server is not connected, stop and walk me through connecting it from https://modernengineer.dev/en/mcp.
2. Summarize the main steps of the piece and point out which apply to this repo.
3. Propose concrete changes and ask me before editing any file.Connect MCP in Claude Code (once)
claude mcp add --transport http modernengineer \
https://api.modernengineer.dev/mcp \
--header "Authorization: Bearer <API key>"Reading the full piece over MCP needs an API key from a subscriber account or one that bought this guide. Without access, the agent only gets the opening.
- Version
- v1.0.0
- Updated
- 22/10/2026
- Licence
- All rights reserved
- Slug
- ak-research-prompt
