source-grounded-research
Skill1 starsChanged 56 days agoMITView on GitHub
Cited research briefs
3 other projects use a version of this.
Adopted by
Most recently taken up by
- xuedai-mayi/humanities-report-writing-suitetheir own version, first seen Nov 1, 2026
- xuedai-mayi/folio-desktheir own version, first seen Nov 1, 2026
- Dokuganrryu/ai-agent-skills-and-subagentstheir own version, first seen May 26, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- xuedai-mayi/folio-desk★ 9same name
- xuedai-mayi/humanities-report-writing-suite★ 9same name
- Dokuganrryu/ai-agent-skills-and-subagents★ 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 repository33 other files it gives its agents.
- apollousaSkill
- chrome-clean-installSkill
- ci-hardeningSkill
- codebase-litter-auditSkill
- coderabbit-resolverSkill
- code-step-tourSkill
- code-traceSkill
- colorful-typeSkill
- component-hierarchySkill
- cookieSkill
- deep-traceSkill
- disk-mapSkill
- dndSkill
- electron-releaseSkill
- explain-diff-htmlSkill
- explainSkill
- generating-codebase-wikiSkill
- github-actions-pnpm-ciSkill
- laststance-publish-skillSkill
- learn-htmlSkill
- loadSkill
- locate-ui-from-codeSkill
- mac-security-sweepSkill
- oss-repo-setupSkill
- product-inspirationSkill
- prop-drillSkill
- pr-tourSkill
- saveSkill
- searchSkill
- ts-pattern-refactorSkill
- type-expandSkill
- ux-gap-detectorSkill
- visual-lintSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
24 rules. About 0 are common, 18 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈18
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use this skill for research-only tasks that should end in a cited brief rather than code changes.
- Distinctive: line 22
Do not use this skill for:
- Distinctive: line 31
Start from the lane's highest-authority source.
- Distinctive: line 33
Check for contradictions or recent changes.
- Very specific: line 40
Start with official docs via Context7 when available.
- Very specific: line 41
Use get_code_context_exa for examples and practical usage.
- Very specific: line 42
Use Perplexity or WebSearch only for contradiction checks or recent changes.
- Very specific: line 47
Start with DeepWiki when available.
- Distinctive: line 48
Read repo structure before asking detailed questions.
- Very specific: line 53
Start with Perplexity Search or standard WebSearch.
- Distinctive: line 54
Verify final claims with official release notes, changelogs, or docs.
- Distinctive: line 58
Start with local repo evidence tools first.
- Distinctive: line 63
Start with breadth discovery.
- Distinctive: line 64
Run an authority pass.
- Distinctive: line 65
Run a contradiction pass before recommending.
- Distinctive: line 69
Prefer tools by role, not habit:
- Distinctive: line 95
Every material factual claim must have an inline citation.
- Distinctive: line 96
Prefer direct URLs to primary sources.
- Distinctive: line 97
If only secondary evidence exists, say so explicitly.
- Distinctive: line 98
Keep facts and inference separate.
- Distinctive: line 102
If a tool is unavailable, switch to another tool with the same role.
- Very specific: line 103
If evidence is thin, say insufficient evidence.
- Distinctive: line 104
If there is no primary source, lower confidence and state the limitation.
- Distinctive: line 105
If evidence conflicts, preserve both sides with citations.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Source-Grounded Research
Purpose
Use this skill for research-only tasks that should end in a cited brief rather than code changes.
This skill is for:
- web research
- library and framework documentation lookup
- open-source repository investigation
- comparison and decision support
- recent changes and release-note checks
Do not use this skill for:
- implementation work
- code editing
- speculative answers without sources
Quick Start
- Restate the question and classify it into one primary lane.
- Start from the lane's highest-authority source.
- Corroborate major claims with a second source.
- Check for contradictions or recent changes.
- Produce a cited report with a query log and sources section.
Research Lanes
library-framework
- Start with official docs via
Context7when available. - Use
get_code_context_exafor examples and practical usage. - Use
PerplexityorWebSearchonly for contradiction checks or recent changes.
oss-repository
- Start with
DeepWikiwhen available. - Read repo structure before asking detailed questions.
- Corroborate key claims with GitHub docs, repo pages, Exa, or official docs.
recent-changes
- Start with
Perplexity Searchor standardWebSearch. - Verify final claims with official release notes, changelogs, or docs.
local-plus-external
- Start with local repo evidence tools first.
- Bridge to external docs only after the local behavior is understood.
comparison-decision
- Start with breadth discovery.
- Run an authority pass.
- Run a contradiction pass before recommending.
Tool Priority
Prefer tools by role, not habit:
Sequential Thinking: scope, sub-questions, assumptionsContext7: official library/framework docsDeepWiki: OSS repository architecture and topic mapExa: breadth discovery and code/doc contextPerplexity: recent web-grounded synthesis and contradiction checksWebSearch/WebFetch: standard web fallback or direct page retrieval- local repo tools: first-class evidence when the question touches local code
Output Contract
Always include:
- Executive Summary
- Evidence Map
- What We Know
- What We Infer
- Contradictions and Unknowns
- Confidence
- Actionable Next Steps
- Query Log
- Sources
Citation Rules
- Every material factual claim must have an inline citation.
- Prefer direct URLs to primary sources.
- If only secondary evidence exists, say so explicitly.
- Keep facts and inference separate.
Failure Rules
- If a tool is unavailable, switch to another tool with the same role.
- If evidence is thin, say
insufficient evidence. - If there is no primary source, lower confidence and state the limitation.
- If evidence conflicts, preserve both sides with citations.
Report Template
Use this structure:
## Executive Summary
- Key takeaway with citation
## Evidence Map
- Primary: why this source is authoritative
- Supporting: what it adds
- Counter: what challenges the main claim
## What We Know
- Fact with citation
## What We Infer
- Inference linked back to evidence
## Contradictions and Unknowns
- Open disagreement or missing source
## Confidence
- high | medium | low
## Actionable Next Steps
- Specific follow-up
## Query Log
| Tool | Query/Prompt | Filters | Why Used | Outcome |
| --- | --- | --- | --- | --- |
## Sources
- [Title](https://example.com) - Publisher, dateAdditional Guidance
- For the detailed lane matrix and DeepWiki workflow, see reference.md.
- For concrete example prompts and output shapes, see examples.md.
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.

