grounded-research
Skill9 starsChanged 38 days agoMITView on GitHub
Answer research questions with inspected sources, dated evidence, honest uncertainty and links that support each claim.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- berkeley-humanoids/skillstheir own version, first seen Oct 9, 2026
- berkeley-humanoids/Skillstheir own version, first seen Oct 9, 2026
- Kaagemusha/agent-skillstheir own version, first seen Sep 27, 2026
- masbrokemanaaja/reethinktheir own version, first seen Sep 20, 2026
- moonpiesheldon1337/grounded-researchtheir own version, first seen May 25, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- berkeley-humanoids/skills★ 4same name
- berkeley-humanoids/Skills★ 4same name
- masbrokemanaaja/reethink★ 3same name
- Kaagemusha/agent-skills★ 0same name
- moonpiesheldon1337/grounded-research★ 0same 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.
In this repository13 other files it gives its agents.
- site/llms-full.txtllms.txt
- site/llms.txtllms.txt
- checked-spreadsheet-analysisSkill
- document-to-action-itemsSkill
- gmail-browser-draftSkill
- google-calendar-browser-tasksSkill
- google-drive-browser-tasksSkill
- meeting-action-itemsSkill
- private-team-reviewSkill
- systematic-debuggingSkill
- todoist-browser-tasksSkill
- weekly-review-planningSkill
- use-mac-appsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
3
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 9
Keep a compact evidence ledger: source title, URL or workspace path, publication/update date if stated, section or source block, and claim …
- Distinctive: line 13
Before delivery, check that each citation supports its sentence and that any saved report exists.
- Distinctive: line 15
Avoid a long list of links with unsupported conclusions.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Source-grounded research
- Turn the question into a small set of claims to verify. Use primary sources where possible and inspect current material for time-sensitive claims. Use available browser or connected tools; never invent a missing search tool.
- Keep a compact evidence ledger: source title, URL or workspace path, publication/update date if stated, section or source block, and claim it supports. Search snippets identify leads; they are not evidence that the full page was read.
- Match each important claim to actual inspected content. Separate direct evidence, your inference and unknowns. If sources disagree, explain the disagreement rather than silently choosing the convenient answer.
- Quote only text you can locate in the source; keep quotes short and follow applicable reuse limits. Prefer faithful paraphrase. Sidemates receipts confirm retrieval, not that your interpretation or quote is correct. This adaptation does not run Hermes's Python quote validator.
- Attach useful inline source links to the relevant statements. Link to the inspected page, not a search results page. Date comparisons and avoid precision unsupported by the source.
- Before delivery, check that each citation supports its sentence and that any saved report exists. State missing coverage, blocked sources and whether conclusions are provisional.
Avoid a long list of links with unsupported conclusions. Return the useful answer first and clearly label inference.
Provenance
Reviewed Sidemates adaptation of grounded-research. Instructions are bundled with Sidemates and do not grant tool or account permissions. See LICENSE for reuse terms.
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.

