research-brief
Skill167 starsChanged 16 days agoMITView on GitHub
Create an automation that writes a recurring research brief. Uses Tavily MCP for web research and Notion MCP to publish the final brief with executive summary, implications, and source citations.
- Reads credentials
- Sends data out
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Ask the user for:
- Distinctive: line 51
If any fail, tell the user which integration needs to be installed first.
- Distinctive: line 60
Ask for timezone preference.
- Distinctive: line 78
Use the prompt preset endpoint:
“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Research Brief Writer Automation
Set up a recurring automation that researches a topic and publishes a brief to Notion.
Prerequisites
Required integrations
Both MCP integrations must be installed in Settings → MCP:
- Tavily MCP — for web research and source gathering
- Notion MCP — to publish the research brief
Information to collect
Ask the user for:
- Topic — what should be researched (e.g. "AI code review tools", "competitor pricing changes")
- Keywords and competitors — specific terms, companies, or products to track
- Source quality rules — any preferences on source types (e.g. prefer academic papers, exclude social media)
- Cadence — how often should the brief run? (daily, weekly, bi-weekly)
- Notion destination — which Notion database or page should receive the brief
- Citation style — inline links, footnotes, or a references section
- Brief structure — default: Executive Summary, Key Findings, Implications, Recommended Actions, Sources
Setup Workflow
Step 1 — Verify MCP access
Test each integration:
Use the Tavily MCP to search for a sample topic.
Use the Notion MCP to search for the destination database.If any fail, tell the user which integration needs to be installed first.
Step 2 — Configure the schedule
Based on the user's cadence preference, build a cron schedule:
- Daily:
0 8 * * 1-5(weekday mornings) - Weekly:
0 9 * * 1(Monday morning) - Bi-weekly:
0 9 1,15 * *(1st and 15th)
Ask for timezone preference.
Step 3 — Build the research prompt
Construct a prompt that includes:
- Research topic and keywords
- Competitor/entity tracking list
- Source quality preferences
- Brief structure template
- Notion destination details
- Citation format
Step 4 — Create the automation
Set OPENHANDS_HOST and AUTH_HEADER for the request below:
- OpenHands Cloud or Enterprise - a
<HOST>value is in your system prompt: use it asOPENHANDS_HOST, withAUTH_HEADER="Authorization: Bearer $OPENHANDS_API_KEY" - Local Agent Canvas - an Automation backend is listed in
<RUNTIME_SERVICES>: use itsurl_from_agentasOPENHANDS_HOST, withAUTH_HEADER="X-Session-API-Key: $OPENHANDS_AUTOMATION_API_KEY"
Use the prompt preset endpoint:
curl -s -X POST "${OPENHANDS_HOST}/api/automation/v1/preset/prompt" \
-H "$AUTH_HEADER" \
-H "Content-Type: application/json" \
-d '{
"name": "Research Brief Writer",
"prompt": "<constructed research prompt>",
"trigger": {"type": "cron", "schedule": "<schedule>", "timezone": "<tz>"}
}'PowerShell note: use curl.exe for this exact flag syntax, and replace ${OPENHANDS_HOST} / $AUTH_HEADER with $env:OPENHANDS_HOST / $env:AUTH_HEADER if running it natively.
Step 5 — Confirm
Tell the user:
✅ Research Brief Writer is running!
- Automation ID:
{id}- Topic:
{topic}- Schedule:
{cron description}- Notion destination:
{destination}- Citation style:
{style}
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- duncan-buildroom/freeskills★ 65same name
- charlie947/life-automation-skills★ 25same name
- Mikefluff/skills★ 19same name
- Heuresis/YouTube-Agency★ 15same name
- TheCraigHewitt/cowork-starter-pack★ 5same name
- robertbradley-oss/skills★ 2same name
- alectivism/maven-template★ 1same name
- molly-diversifiedfun/claude-skills★ 1same name
- Nomanriaz786/claude-consulting-team★ 1same name
- Baba01hacker666/dummyskills★ 0same name
9 more not listed
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.
Used alongsideProjects with it also use weekly-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
QuixiAISkillweekly-review
Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week
Also in 3 projects that use this
In this repository68 other files it gives its agents.
- AGENTS.mdAGENTS.md
- add-javadocSkill
- add-skillSkill
- agent-canvas-environmentSkill
- agent-creatorSkill
- agent-memorySkill
- agent-sdk-builderSkill
- azure-devopsSkill
- bitbucket-cloudSkill
- bitbucket-data-centerSkill
- bitbucketSkill
- canvas-extension-apiSkill
- code-reviewSkill
- code-simplifierSkill
- datadogSkill
- denoSkill
- discordSkill
- dockerSkill
- evidence-based-citationsSkill
- flarglebargleSkill
- frontend-designSkill
- github-actionsSkill
- github-agents-md-maintainerSkill
- github-delivery-watchdogSkill
- github-issue-to-prSkill
- github-issue-triageSkill
- github-pr-reviewerSkill
- github-pr-reviewSkill
- github-repo-monitorSkill
- githubSkill
- github-stale-ci-pr-closerSkill
- gitlab-issue-to-mrSkill
- gitlabSkill
- incident-retrospectiveSkill
- iterateSkill
- jira-issue-to-prSkill
- jupyterSkill
- kubernetesSkill
- learn-from-code-reviewSkill
- linearSkill
- linear-triageSkill
- news-digestSkill
- notionSkill
- npmSkill
- openhands-apiSkill
- openhands-automationSkill
- openhands-enterprise-troubleshootingSkill
- openhands-sdkSkill
- pdflatexSkill
- plain-english-contentSkill
- prdSkill
- qa-changesSkill
- release-notesSkill
- securitySkill
- simplified-technical-englishSkill
- skill-creatorSkill
- slack-channel-monitorSkill
- slack-standup-digestSkill
- spark-version-upgradeSkill
- sshSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

