grounded-research
Skill4 starsChanged 34 days agoCC0-1.0View on GitHub
Evidence-first mode that searches credible sources (papers, official docs, source code, issue trackers) before stating non-trivial claims, and cites them. Use for research-backed answers, technical comparisons, design decisions, root-cause explanations, or claim checks.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- PrisacariuRobert/sidematestheir own version, first seen Nov 8, 2026
- berkeley-humanoids/skillsword for word, 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 · 1
- berkeley-humanoids/skills★ 4100% same
Edited · 0
None found.
Wrote their own version · 4
- PrisacariuRobert/sidemates★ 9same 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 repository8 other files it gives its agents.
- clean-codingSkill
- github-workflowSkill
- paper-figuresSkill
- pixi-workspaceSkill
- research-code-validationSkill
- robotics-conventionsSkill
- ros2-conventionsSkill
- ste-writingSkill
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 4 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 14
Think critically: Treat all sources as potentially incomplete or wrong.
- Distinctive: line 15
Validate uncertainty cheaply: When evidence is inconclusive, propose the smallest practical experiment, ablation, benchmark, logging …
- Distinctive: line 17
Do not present intuition as established fact.
“Common” is measured: kept by at least 6 in 10 of the 4 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
Grounded Research
Operate in evidence-first mode.
- Search before concluding. For any non-trivial factual claim, technical explanation, comparison, or design choice, search for external evidence first rather than relying on intuition alone.
- Prefer credible sources. Prioritize papers, official documentation, technical reports, source code, issue trackers, and engineering blogs from relevant authors or practitioners.
- Triangulate. For important claims, seek multiple independent sources when practical. Surface disagreements instead of silently choosing one.
- Separate evidence from inference. Clearly distinguish what a source directly shows, what its authors claim, and what you infer from it. Cite claims next to their supporting sources.
- Think critically. Treat all sources as potentially incomplete or wrong. Check assumptions, experimental setup, hardware, datasets, metrics, and applicability to the current problem.
- Validate uncertainty cheaply. When evidence is inconclusive, propose the smallest practical experiment, ablation, benchmark, logging change, or simulation that could support or falsify the claim using the existing setup.
Do not present intuition as established fact. If evidence is weak, say so explicitly.
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.