---
title: "Research desk"
description: "Four skills for source-checked research: a source ledger, a claim checker, a comparison matrix and a freshness scan."
canonical: "https://www.diginomads.win/skills/research-desk"
source: "content/pages/skills/research-desk.md"
updatedAt: "2026-11-10"
---

**Level:** Starter

## Skills

| Skill | Trigger | Output | Guardrail |
|---|---|---|---|
| source-ledger | When a task needs facts from more than one page | A table of claim, source, access date, quote and confidence | A source the agent did not open is marked 'not opened', never cited. |
| claim-checker | Before a draft with numbers, dates, rules or quotes is published | Each claim labelled fact, opinion, experience or unknown, with the supporting sentence | A claim without a supporting sentence is removed, not softened. |
| comparison-builder | When two or more options must be compared on the same criteria | One row per option, one column per criterion, with 'not published' where data is missing | No single score or ranking; the trade-off stays visible. |
| freshness-scan | When a page has a reviewed date older than the source's last update | A list of claims whose source changed, with the old and new wording | A changed source is a changed claim; the page date moves only after a person re-reads it. |

## Install

1. Create one folder per skill under `skills/` in the project the agent works in: `source-ledger/`, `claim-checker/`, `comparison-builder/`, `freshness-scan/`.
2. Add a `SKILL.md` to each folder with a specific `description`. The description is the trigger; write it as a situation, not a topic.
3. Put long source notes in `references/` and keep the main file short enough to read in one pass.
4. Run the three tests below with a prompt that should trigger each skill. If the agent never loads it, the description is too vague.

## Tests

- **Prompt:** Compare two visa routes for a freelance designer and cite the official pages.
  **Pass:** The agent creates a two-row table with an access date and marks missing cells 'not published'; it does not rank the routes.
- **Prompt:** Here is my article draft. Check every number against these links.
  **Pass:** Each number is labelled fact, opinion or unknown; at least one unsupported claim is removed rather than reworded.
- **Prompt:** This page was last reviewed in March. Is it still right?
  **Pass:** The agent lists the sources that changed and does not update the reviewed date on its own.

## Sources

- [Agent Skills specification](https://agentskills.io/specification)
- [Anthropic public skills repository](https://github.com/anthropics/skills)
- [Claude Agent Skills overview](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview)

## Why this pack first

Research is where an agent's confidence is most expensive. A wrong date in a client update is embarrassing; a wrong eligibility rule in a move plan is costly. This pack makes the evidence visible before the prose gets smooth.

The four skills cover one loop: collect a source, check a claim, compare options, and notice when the source changed. They are deliberately small. A research skill that tries to do all four in one file becomes a prompt with a folder around it.

## The rule behind the pack

Every factual sentence has a source a reader can open, or it is removed. That rule is easy to state and hard to follow, because a model can produce a plausible sentence faster than a person can check it. The skills put the check in the path instead of relying on willpower.

## Adapting it

- If your work is legal or regulatory, add a `jurisdiction` field to the source ledger and make it required.
- If you research in more than one language, add the original-language quote next to the translation.
- If you publish on a schedule, make the freshness scan a weekly task and keep the last run in the repository.

## Failure modes

- **The ledger is longer than the article.** That is fine for a first pass; trim the ledger to the claims that carry the argument.
- **Every claim is marked “opinion”.** That is a way to avoid checking. Require a source for anything a reader could verify.
- **The model cites a search result.** Ask for the page it opened and the sentence it used. A snippet is not a source.

## Related

- [Build a city brief from official sources](/prompts/city-research-brief)
- [Compare visa routes in a decision matrix](/prompts/visa-route-matrix)
- [Turn notes into a publishable article](/prompts/notes-to-article)

## Structured data

```json
{
  "@context": "https://schema.org",
  "@type": "WebPage",
  "name": "Research desk",
  "url": "https://www.diginomads.win/skills/research-desk",
  "description": "Four skills for source-checked research: a source ledger, a claim checker, a comparison matrix and a freshness scan.",
  "isPartOf": {
    "@type": "WebSite",
    "name": "DigiNomads",
    "url": "https://www.diginomads.win/"
  }
}
```