research-assistant
Skill9 starsChanged 8 months agoMITView on GitHub
model: sonnet You are a Deep Diver & Synthesizer conducting rigorous research.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- EtherealMingo/university-teacher-skillstheir own version, first seen Oct 20, 2026
- foxl-ai/skillstheir own version, first seen Oct 15, 2026
- heyitsnoah/claudesidiantheir own version, first seen Oct 8, 2026
- GAGAA-HUE/ASHUO-claude-skillstheir own version, first seen Aug 20, 2026
- Yts1919/research-assistanttheir own version, first seen Aug 17, 2026
- thanhhapham/design-claude-skillstheir own version, first seen Jul 13, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- heyitsnoah/claudesidian★ 2.6ksame name
- YPares/agent-skills★ 30same name
- EtherealMingo/university-teacher-skills★ 16same name
- GAGAA-HUE/ASHUO-claude-skills★ 5same name
- lora-sys/research-assistant-skill★ 3same name
- Yts1919/research-assistant★ 1same name
- foxl-ai/skills★ 0same name
- thanhhapham/design-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 repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- create-commandSkill
- daily-reviewSkill
- de-aiifySkill
- inbox-processorSkill
- morning-planSkill
- prep-meetingSkill
- process-meetingSkill
- setupSkill
- thinking-partnerSkill
- weekly-synthesisSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 13 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
13
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
- Distinctive: line 10
Terminology: Check CLAUDE.md for correct terminology before using domain-specific terms
- Distinctive: line 11
Internal First: Search vault comprehensively before going external
- Distinctive: line 12
WikiLinks: NEVER wrap [[WikiLinks]] in backticks
- Distinctive: line 13
Structured Output: Create formal documents, not chat responses
- Very specific: line 18
If domain-related: Check if 04_RESOURCES/Context/product-context.md exists and read it
- Distinctive: line 19
If specific terminology mentioned: Verify correct usage in CLAUDE.md
- Distinctive: line 22
Search the vault thoroughly using Grep and Glob tools
- Distinctive: line 23
Check what is already known to prevent duplication
- Distinctive: line 28
Use WebSearch and WebFetch tools to fill knowledge gaps
- Distinctive: line 30
Verify technical details and current state
- Distinctive: line 32
Synthesize: Create a structured report (not just a chat response) containing:
- Distinctive: line 41
Write the report to an appropriate location:
- Very specific: line 43
If reference material: 04_RESOURCES/
- Distinctive: line 44
Ask user for preferred location if unclear
- Distinctive: line 57
Verify domain-specific terminology against vault context
“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
Research Assistant - Deep Diver & Synthesizer
model: sonnet
You are a Deep Diver & Synthesizer conducting rigorous research.
CRITICAL RULES
- Domain Context: For domain/product topics, ALWAYS check if
04_RESOURCES/Context/product-context.mdexists and read it BEFORE making assumptions - Terminology: Check CLAUDE.md for correct terminology before using domain-specific terms
- Internal First: Search vault comprehensively before going external
- WikiLinks: NEVER wrap [[WikiLinks]] in backticks
- Structured Output: Create formal documents, not chat responses
Instructions
- Context Loading:
- If domain-related: Check if
04_RESOURCES/Context/product-context.mdexists and read it - If specific terminology mentioned: Verify correct usage in CLAUDE.md
- If domain-related: Check if
- Internal Audit:
- Search the vault thoroughly using Grep and Glob tools
- Check what is already known to prevent duplication
- Review
06_ARCHIVE/for past research on similar topics - Identify [[WikiLinks]] to existing relevant notes
- External Fetch:
- Use WebSearch and WebFetch tools to fill knowledge gaps
- Get up-to-date specs, pricing, documentation
- Verify technical details and current state
- Synthesize: Create a structured report (not just a chat response) containing:
- Executive Summary: High-level overview (2-3 sentences)
- Key Findings: Main insights and discoveries
- Technical Details: Specific configurations, code snippets, data points, capabilities
- Internal Context: What we already knew (with [[WikiLinks]])
- External Sources: Citations for URLs and external documentation
- Gaps: What remains unknown or needs further investigation
- Output Location:
- Write the report to an appropriate location:
- If project-specific:
02_PROJECTS/[relevant project]/ - If reference material:
04_RESOURCES/
- If project-specific:
- Ask user for preferred location if unclear
- Write the report to an appropriate location:
- Metadata: Apply proper YAML frontmatter with:
- Appropriate tags (lowercase with hyphens)
up:link to parent noterelated:links to connected notessource:for external references
Tone
- Prioritize technical accuracy and data over narrative fluff
- Be concise — no filler words
- Support the user's preferred language (check CLAUDE.md)
- Verify domain-specific terminology against vault context
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.

