agentleFS
Sign inStart free
gbadedatagbadedata/mcp-research-agent/skills/research-digest/SKILL.md

research-digest

Skill0 starsChanged 4 months agoMITView on GitHub

Collect information from a set of web sources, store the notable items (deduplicated), and produce a short digest. Use when asked to monitor sources, gather links on a topic, or turn a list of pages into a brief.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. 0xUrsanomics/utopia-os★ 2same name
    2. trycomp-io/comp-skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the digest as short bullet points: title, source, one line each.

    line 33
  2. Distinctive:

    Prefer a few high-signal items over many low-signal ones.

    line 37
  3. Distinctive:

    Keep summaries to a single sentence.

    line 38
  4. Distinctive:

    If a fetch fails, note it and continue with the other sources rather than stopping.

    line 39
  5. Very specific:

    If the task does not actually need a model (for example, just re-render what is already stored), the deterministic digest command in this …

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research Digest

A skill for turning web sources into a stored, deduplicated digest. It follows the SKILL.md convention shared by OpenClaw and Claude Code (metadata and instructions in the front matter, guidance below), and the tools it declares are served by the mcp-research-agent MCP server in this repository.

When to use

  • "Monitor these pages and tell me what is new."
  • "Gather the key links on <topic> and summarise them."
  • "Turn this list of URLs into a short brief."

How to run it

  1. For each source URL, call fetch_url to get the title, cleaned text, and outbound links.
  2. Decide which items are worth keeping. For each, call save_item with a one-sentence summary. Duplicates (same URL) are ignored automatically, so re-running is safe.
  3. Optionally call list_items or search_items to review what has been collected.
  4. Write the digest as short bullet points: title, source, one line each.

Guidance

  • Prefer a few high-signal items over many low-signal ones.
  • Keep summaries to a single sentence.
  • If a fetch fails, note it and continue with the other sources rather than stopping.
  • If the task does not actually need a model (for example, just re-render what is already stored), the deterministic digest command in this repo does that with no LLM call.

Wiring

Register the server with an MCP-capable client (Claude Desktop, Claude Code, or another agent runtime). See the repository README for the exact configuration.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free