How do I install the Research Digest skill?

Run npx skillmds@latest add aaronjmars/research-digest-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Research Digest skill do?

> **${var}** — Optional. Pass a different topic to override the default. If empty, digests [REPLACE: TOPIC]. It is listed under Research & Search on SkillMD.

Is Research Digest safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Research Digest?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Research Digest free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Research Digest?

aaronjmars (@aaronjmars) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Research Digest by aaronjmars — Agent Skill

Name: Research Digest
Author: aaronjmars

File contents

${var} — Optional. Pass a different topic to override the default. If empty, digests [REPLACE: TOPIC].

Today is ${today}. Build a digest of the [REPLACE: MAX_ITEMS] most interesting new posts on [REPLACE: TOPIC].

Steps

Read sources — pull the last 24h of entries from each feed:
```
[REPLACE: FEED_URLS]
```
(Comma- or newline-separated list of RSS/Atom URLs.)

Use WebFetch to retrieve each feed and parse the entries. If a feed 404s or returns malformed XML, log a single warning line and skip that feed for this run.
Augment with web search — run a WebSearch for [REPLACE: TOPIC] latest and pick up to 5 fresh links published in the last 24h that aren't already in the feed results.
Score and rank — for each candidate, score on:
- Recency — within the last 24h gets full marks.
- Source weight — feeds in the configured list outrank generic search results.
- Specificity — items mentioning concrete numbers, code, or named systems beat opinion pieces.
Drop anything obviously off-topic (the ${var} or [REPLACE: TOPIC] keyword should appear somewhere in title or summary).
Pick the top [REPLACE: MAX_ITEMS] — write output/articles/[REPLACE: SKILL_NAME]-${today}.md with one entry each:
```
### [Title](url)
*[Source · published date]*
2-3 sentences distilling the takeaway. No filler.
```

Notify via ./notify with:

*[REPLACE: TOPIC] digest — ${today}*

[N] picks. Top item: [shortened title].

Full digest: https://github.com/${GITHUB_REPOSITORY}/blob/main/output/articles/[REPLACE: SKILL_NAME]-${today}.md

Log — append to memory/logs/${today}.md:

## [REPLACE: SKILL_NAME]
- **Sources scanned**: N feeds + 1 web search
- **Items picked**: N (of M candidates)
- **Top source**: domain
- **Status**: DIGEST_OK | DIGEST_QUIET (no items) | DIGEST_DEGRADED (some feeds failed)

Network note

WebFetch and WebSearch are built-in Claude tools. There is no network sandbox — curl works too; use WebFetch as the fallback for a flaky public GET. For this research skill the reads are unauthenticated, so WebSearch + WebFetch are the simplest path.

Constraints

Never repeat. Track which item URLs went out via memory/topics/[REPLACE: SKILL_NAME]-seen.txt (append-only). Skip anything that's already in there.
No filler. If fewer than [REPLACE: MAX_ITEMS] items meet the bar, send fewer items — never pad with low-signal content.
Quote, don't paraphrase the news. Say "Anthropic released X" not "AI labs are releasing things." Specificity beats hand-waving.

---name: research-digest-2description: > **${var}** — Optional. Pass a different topic to override the default. If empty, digests [REPLACE: TOPIC].---> **${var}** — Optional. Pass a different topic to override the default. If empty, digests [REPLACE: TOPIC].Today is ${today}. Build a digest of the [REPLACE: MAX_ITEMS] most interesting new posts on **[REPLACE: TOPIC]**.## Steps1. **Read sources** — pull the last 24h of entries from each feed: ```text [REPLACE: FEED_URLS] ``` (Comma- or newline-separated list of RSS/Atom URLs.) Use **WebFetch** to retrieve each feed and parse the entries. If a feed 404s or returns malformed XML, log a single warning line and skip that feed for this run.2. **Augment with web search** — run a `WebSearch` for `[REPLACE: TOPIC] latest` and pick up to 5 fresh links published in the last 24h that aren't already in the feed results.3. **Score and rank** — for each candidate, score on: - **Recency** — within the last 24h gets full marks. - **Source weight** — feeds in the configured list outrank generic search results. - **Specificity** — items mentioning concrete numbers, code, or named systems beat opinion pieces. Drop anything obviously off-topic (the `${var}` or `[REPLACE: TOPIC]` keyword should appear somewhere in title or summary).4. **Pick the top [REPLACE: MAX_ITEMS]** — write `output/articles/[REPLACE: SKILL_NAME]-${today}.md` with one entry each: ```markdown ### [Title](url) *[Source · published date]* 2-3 sentences distilling the takeaway. No filler. ```5. **Notify** via `./notify` with: ``` *[REPLACE: TOPIC] digest — ${today}* [N] picks. Top item: [shortened title]. Full digest: https://github.com/${GITHUB_REPOSITORY}/blob/main/output/articles/[REPLACE: SKILL_NAME]-${today}.md ```6. **Log** — append to `memory/logs/${today}.md`: ``` ## [REPLACE: SKILL_NAME] - **Sources scanned**: N feeds + 1 web search - **Items picked**: N (of M candidates) - **Top source**: domain - **Status**: DIGEST_OK | DIGEST_QUIET (no items) | DIGEST_DEGRADED (some feeds failed) ```## Network note`WebFetch` and `WebSearch` are built-in Claude tools. There is no network sandbox — `curl` works too; use `WebFetch` as the fallback for a flaky public GET. For this research skill the reads are unauthenticated, so `WebSearch` + `WebFetch` are the simplest path.## Constraints- **Never repeat**. Track which item URLs went out via `memory/topics/[REPLACE: SKILL_NAME]-seen.txt` (append-only). Skip anything that's already in there.- **No filler**. If fewer than `[REPLACE: MAX_ITEMS]` items meet the bar, send fewer items — never pad with low-signal content.- **Quote, don't paraphrase the news**. Say "Anthropic released X" not "AI labs are releasing things." Specificity beats hand-waving.

Frequently asked questions

Research Digest