research-methodology
Skill0 starsChanged 4 months agoMITView on GitHub
Use when the user asks to research, investigate, or "look into" a topic that requires gathering information from multiple sources and synthesizing it into a defensible answer — not a single fact lookup. Triggers on requests like "research X", "find out whether Y", or "what's the current state of Z".
16 other projects use a version of this.
Adopted by
Most recently taken up by
- komluk/scaffoldingtheir own version, first seen Nov 7, 2026
- SWEStash/swe-workflow-skillstheir own version, first seen Nov 1, 2026
- irahardianto/awesome-agvtheir own version, first seen Oct 14, 2026
- poemswe/co-researchertheir own version, first seen Oct 13, 2026
- The-Focus-AI/standardstheir own version, first seen Oct 12, 2026
- HughYau/pengsida-learning-research-skillstheir own version, first seen Oct 8, 2026
Used with
Projects with it also use literature-review, context-engineering and 2 more.
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.
JDerekLomasSkillliterature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
Also in 3 projects that use this
mrgoonieSkillcontext-engineering
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
Also in 3 projects that use this
CloudflareSkillsecurity-audit
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.
Also in 3 projects that use this
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 3 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- VAMFI/claude-user-memory★ 206same name
- magnus919/agent-skills★ 172same name
- irahardianto/awesome-agv★ 157same name
- poemswe/co-researcher★ 135same name
- HughYau/pengsida-learning-research-skills★ 27same name
- komluk/scaffolding★ 16same name
- stupidZZ/skills★ 9same name
- KhaledSaeed18/dotclaude★ 5same name
- ntaffzii/Skill-Agents★ 4same name
- nic095layson/claude★ 1same name
6 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 repository9 other files it gives its agents.
- agent-architecture-advisorSkill
- business-intelligenceSkill
- compliance-reviewSkill
- data-correlationSkill
- document-analysisSkill
- extractionSkill
- financial-analysisSkill
- legal-contract-reviewSkill
- trace-analysisSkill
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 14 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 14
Record findings as you go: Don't hold everything in working memory — write intermediate findings down (a notes tool, a scratch file, a todo …
- Distinctive: line 15
Triangulate before concluding: Before synthesizing, explicitly check: do my sources agree?
- Distinctive: line 16
Cite per claim, not per document: Every specific claim in the final answer should trace to the tool result or source that supports it.
- Distinctive: line 25
Every factual claim in the output is attributable to a specific source or tool result.
“Common” is measured: kept by at least 6 in 10 of the 14 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 methodology
A systematic workflow for turning a research question into a synthesized, cited answer — the discipline the playbook's research-agent example follows, extracted into a reusable skill so any agent can apply it.
Workflow
- Decompose the question. Split it into independent sub-questions or data sources (e.g. "external trend" vs. "internal data"). Independent threads should be pursued in parallel if your tools support it.
- Gather from at least two source types per claim. A single source is an anecdote; two independent sources that agree is evidence. Prefer primary sources (official docs, direct data) over summaries of summaries.
- Record findings as you go. Don't hold everything in working memory — write intermediate findings down (a notes tool, a scratch file, a todo list) so nothing is lost if the investigation runs long.
- Triangulate before concluding. Before synthesizing, explicitly check: do my sources agree? If they disagree, say so rather than picking the more convenient one.
- Cite per claim, not per document. Every specific claim in the final answer should trace to the tool result or source that supports it. "Several sources suggest X" is weaker than "X (per source A); source B reports a similar figure."
- Flag what you couldn't verify. State assumptions and gaps explicitly rather than smoothing over them.
Composition
This skill pairs naturally with data-correlation when the research involves comparing an external trend against internal data, and with business-intelligence when the output needs to inform a decision rather than just inform.
Quality bar
- Every factual claim in the output is attributable to a specific source or tool result.
- At least one alternative explanation or counter-source was considered for the central claim, even if ultimately rejected.
- Gaps and unverified assumptions are stated, not hidden.
- The answer distinguishes "the sources agree" from "I found one source and stopped."
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.