research-brief
Skill0 starsChanged 6 days agoMITView on GitHub
Research a question and write a short, sourced brief. Use when the user says "research", "look into", "find out", "what does the evidence say", "is it true that", or needs a fact base before a decision.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- Suryanandx/qvac-uitheir own version, first seen Nov 1, 2026
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- Evan-Daruwalla/claude-skill-suitetheir own version, first seen Oct 20, 2026
- dss-time/repo-doctor-skillstheir own version, first seen Oct 15, 2026
- Baba01hacker666/dummyskillstheir own version, first seen Oct 13, 2026
- LeonardSEO/ambitious-math-researchtheir own version, first seen Oct 13, 2026
Used with
Projects 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
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- OpenHands/extensions★ 167same name
- duncan-buildroom/freeskills★ 65same name
- Mikefluff/skills★ 26same name
- charlie947/life-automation-skills★ 25same name
- Heuresis/YouTube-Agency★ 15same name
- TheCraigHewitt/cowork-starter-pack★ 5same name
- robertbradley-oss/skills★ 2same name
- alectivism/maven-template★ 1same name
- dss-time/repo-doctor-skills★ 1same name
- molly-diversifiedfun/claude-skills★ 1same name
10 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.
In this repository24 other files it gives its agents.
- api-docsSkill
- changelogSkill
- ci-failure-fixSkill
- code-reviewSkill
- commit-messageSkill
- competitor-analysisSkill
- data-analystSkill
- debug-detectiveSkill
- dependency-upgradeSkill
- dockerizeSkill
- email-replierSkill
- eval-promptSkill
- incident-postmortemSkill
- meeting-notesSkill
- migration-safetySkill
- pr-descriptionSkill
- product-specSkill
- readme-writerSkill
- refactor-safelySkill
- security-checkSkill
- seo-articleSkill
- sql-helperSkill
- support-replySkill
- write-testsSkill
The file
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 19 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 13
No web or document access: say so at the top, answer from knowledge, and label the whole brief "unverified, from model knowledge (cutoff …
- Distinctive: line 21
Do not keep searching to make the brief longer.
- Distinctive: line 39
Never invent a source, URL, author, quote or number.
- Distinctive: line 41
Keep it under one page unless the user asks for depth.
“Common” is measured: kept by at least 6 in 10 of the 19 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
1. Frame
- Restate the question in one sentence, including scope: geography, time period, population, units. Ambiguous scope that changes the answer: ask once, or pick one and say so.
- Break it into 3-5 sub-questions whose answers together answer the question.
2. Search
- No web or document access: say so at the top, answer from knowledge, and label the whole brief "unverified, from model knowledge (cutoff
<date>)". Do not fake citations. - Source priority: primary data and official sources (statistics offices, filings, regulators, standards, docs, peer-reviewed papers) > reputable reporting that cites them > everything else. Trace secondary claims back to the primary source when you can.
- Note each source's publication date. For fast-moving topics (prices, laws, software, AI) prefer the last 12 months and flag older sources.
- Open every source you cite. A search snippet is not a source. Paywalled: cite only what is visible and say so.
3. Stop when
- each sub-question has two independent sources that agree, or
- you have done about 3 searches per sub-question without new information: record it as unknown. Do not keep searching to make the brief longer.
4. Check numbers
For each figure: same unit, year, geography and definition as the question? "Unemployment 4%" from a different country or year does not answer it. Quote figures exactly as published with their date.
5. Write the brief
Answer: 2-4 sentences, bottom line first, with the confidence level.
Key findings: bullets. Each: the claim, the number if any, source name + link + date.
Where sources disagree: who says what, and the likely reason (definitions, methods, dates, interests).
Unknown / not found: what you looked for and could not establish.
Confidence: high (multiple primary sources agree), medium (one primary or several secondary), low (indirect or old evidence). One line on what would change it.
Rules
- Never invent a source, URL, author, quote or number. A missing answer is a valid result.
- Separate your inference from the sources: "Sources show X; this suggests Y (my inference)."
- Keep it under one page unless the user asks for depth.
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
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.