research-refine
Skill4 starsChanged 41 days agoMITView on GitHub
Refine an accepted, evidence-backed idea into a minimal method, mechanism hypothesis, failure modes, and claim-driven validation plan.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- Yulivu/debuffer-skillstheir own version, first seen Oct 13, 2026
- yvesory/academic-research-suitetheir own version, first seen Oct 9, 2026
- talhaMah56/claude_skillstheir own version, first seen Sep 12, 2026
- wanshuiyin/Auto-claude-code-research-in-sleeptheir own version, first seen Jul 15, 2026
- zjunlp/Mechanisttheir own version, first seen Jul 11, 2026
- catalsqlb-cmd/Prism-Htheir own version, first seen May 29, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19ksame name
- zjunlp/Mechanist★ 75same name
- Chanw-research/claude-code-paper-writing★ 42same name
- catalsqlb-cmd/Prism-H★ 16same name
- Yulivu/debuffer-skills★ 9same name
- yvesory/academic-research-suite★ 9same name
- raja21068/AutoResearch★ 2same name
- talhaMah56/claude_skills★ 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 repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- academic-humanizerSkill
- citation-verificationSkill
- claim-numerics-auditSkill
- cover-letterSkill
- experiment-planSkill
- experiment-runnerSkill
- journal-scoutSkill
- paper-auditSkill
- paper-illustrationSkill
- paper-planSkill
- paper-writeSkill
- research-data-auditSkill
- research-ideationSkill
- research-publicationSkill
- research-quality-gateSkill
- result-to-claimSkill
- scientific-figure-makingSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read AGENTS.md, docs/03_idea_report.md, data analysis, verified literature/evidence records, and any approved constraints.
- Very specific: line 22
Run a focused review: Use the project's local review procedure or $research-quality-gate to test problem fidelity, mechanism specificity, …
- Distinctive: line 26
Do not turn an unverified observation into a mechanism, law, novelty claim, or physical contribution.
- Distinctive: line 27
Do not solve a different, easier problem merely because it makes a cleaner model demo.
- Distinctive: line 28
Prefer a small mechanism that can be disproved over a broad system with many loosely connected innovations.
- Distinctive: line 29
Do not promise expensive training, external review, upload, or publication without the required authorization.
“Common” is measured: kept by at least 6 in 10 of the 8 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 Refine
Refine an approved research direction without allowing it to drift from the problem it is meant to solve. The output is a falsifiable method-and-validation plan, not a feature list.
Inputs and output
Read AGENTS.md, docs/03_idea_report.md, data analysis, verified literature/evidence records, and any approved constraints. Update docs/04_methodology.md; record material decisions in docs/03_idea_report.md or the project decision log.
Workflow
- Freeze the problem anchor. State the real problem, affected setting, measurable consequence, existing-solution bottleneck, and the exact research question. Mark assumptions and evidence gaps.
- State the mechanism hypothesis. Identify observable signals, nuisance factors, representation or inference failure, and a falsifiable prediction. For engineering work, distinguish a physical/measurement contribution from a useful empirical hypothesis; call it physical only when its mechanism and test are concrete.
- Derive one candidate contribution. Express a transferable design principle or knowledge claim before naming the method. Explain how it differs from closest work using verified evidence.
- Design the smallest sufficient method. Define inputs, outputs, modules, interfaces, training/inference path, and why each part tests or enables the hypothesis. Remove any module with no diagnostic, claim, or control purpose.
- Specify failure modes. List expected non-identifiability, distribution shift, weak-signal, label, data-coverage, and resource failure modes, including how each would be detected.
- Build the validation chain. Map every Claim ID to the required data, baseline/control, metric, ablation or intervention, uncertainty treatment, and stopping condition. Engineering work must separately test operational value, mechanism/design-principle evidence, and any transfer claim.
- Run a focused review. Use the project's local review procedure or
$research-quality-gateto test problem fidelity, mechanism specificity, parsimony, evidence sufficiency, feasibility, and drift. Record findings in the active Stage artifact; do not assume an unavailable sub-agent or external model.
Non-negotiable constraints
- Do not turn an unverified observation into a mechanism, law, novelty claim, or physical contribution.
- Do not solve a different, easier problem merely because it makes a cleaner model demo.
- Prefer a small mechanism that can be disproved over a broad system with many loosely connected innovations.
- Do not promise expensive training, external review, upload, or publication without the required authorization.
Report the frozen problem anchor, method chain, rejected additions, claim-to-validation table, residual risks, and the next Stage 1E action.
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.

