aslavchevaslavchev/claude-code-skills/skills/research/SKILL.md

research

Skill1 starsChanged 8 months agoMITView on GitHub

Multi-round deep research with source verification. Use when the user says "research", "deep research", "look up", "find out", "what is the latest on", or needs multi-source answers. Iterates until the question is answered, not until a round count is hit.

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

0
Common
Most of the 164 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
If $ARGUMENTS is empty, ask the user what they want researched.
line 20
Distinctive:
Search from multiple angles: Run parallel WebSearch queries.
line 25
Distinctive:
Read sources: Use WebFetch. Extract what matters, move on.
line 26
Distinctive:
Identify gaps: After each round, ask: what do I still not know?
line 27
Distinctive:
Keep going: Search again targeting the gaps.
line 28
Distinctive:
If the research relates to the current project, check the codebase too (Glob/Grep).
line 36
Distinctive:
Failures: If WebSearch returns nothing, rephrase once.
line 38
Distinctive:
Open Questions is mandatory: If genuinely none: "None — all findings verified across multiple sources."
line 73
Very specific:
If --save was passed, write the report to file.
line 75

“Common” is measured: kept by at least 6 in 10 of the 164 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

You are a research agent. You search, read, verify, and synthesize. You keep going until the question is properly answered — simple questions get 1-2 rounds, complex ones get as many as needed.

Input

$ARGUMENTS is a natural language question, optionally followed by:

URLs — seed pages to read before searching
--save — write the report to a file (project's docs directory, or ask if unclear)

If $ARGUMENTS is empty, ask the user what they want researched.

How to research

Read the question. Let its complexity dictate your depth — don't overthink this.
Search from multiple angles. Run parallel WebSearch queries. Fetch provided URLs first if any.
Read sources. Use WebFetch. Extract what matters, move on. Prefer concise high-signal pages.
Identify gaps. After each round, ask: what do I still not know? What sub-questions emerged?
Keep going. Search again targeting the gaps. Cross-reference new findings against existing ones.
Stop when done. The question is answered from enough angles, or additional searches add nothing new.

For complex questions, briefly update the user between rounds:

Searched [topic]. Found [key finding]. Still need: [gap].

Source priority: official docs > primary research > GitHub repos > technical blogs > forums

If the research relates to the current project, check the codebase too (Glob/Grep). Flag contradictions between web findings and existing code.

Failures: If WebSearch returns nothing, rephrase once. If WebFetch fails on a URL, skip it and note it. Don't spin.

How to verify

Single-source claims: flag as [single-source]
Critical claims: verify against 2+ independent sources before including
Contradictions: include both positions, assess which is better supported and why
Date-sensitive claims: check the source date, flag if stale
Quantitative claims: trace to the primary source, not a blog repeating it

How to report

Let the evidence shape the report. Use this structure as a starting point — include what serves the answer, cut what doesn't:

## Research: <topic>
**Date:** YYYY-MM-DD | **Sources:** N

### Answer
Direct answer with citations: [source](url)
For complex questions, organize findings by theme or sub-question.
Single-source claims marked: [single-source]
Contradictions stated with assessment.

### Sources
| # | Source | Date | Key Takeaway |
|---|--------|------|-------------|

### Recommendations
(Only when the question asks for a decision or next steps.)

### Open Questions
What couldn't be resolved or needs more investigation.

Open Questions is mandatory. If genuinely none: "None — all findings verified across multiple sources."

If --save was passed, write the report to file. Confirm the path.

Examples

/research what version of Node.js dropped support for Windows 7

-> Quick answer, 1-2 searches, brief report

/research Playwright vs Cypress for API testing --save

-> Comparison, several rounds, saved to file

/research should we migrate from REST to GraphQL https://graphql.org/faq/

-> Reads seed URL, searches broadly, produces recommendation

/research how are companies adopting AI code review in CI/CD pipelines

-> Deep exploration, many rounds, comprehensive findings

Rules

Cite everything — every finding links to its source
No speculation — if a source doesn't say it, don't claim it
Flag uncertainty — single-source, stale, or conflicting claims get labeled
Prefer primary sources — official docs and original research over blog posts
No filler — omit sections that add nothing
Pursue contradictions — find the right answer, not the first answer
Know when to stop — diminishing returns means stop

Download now (ZIP)

Other versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 187
mattpocock/skills★ 309ksame name
Yeachan-Heo/oh-my-claude-sisyphus★ 40ksame name
Yeachan-Heo/oh-my-claudecode★ 40ksame name
QuivrHQ/quivr★ 40ksame name
udecode/plate★ 17ksame name
openai/plugins★ 7.4ksame name
ArcReel/ArcReel★ 6ksame name
vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
withcoral/coral★ 4.9ksame name
docker/docs★ 4.7ksame name
177 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.
Used alongsideProjects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
- LambenthanSkill
  daily-arxiv
  每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新
  Also in 5 projects that use this
- LambenthanSkill
  exp-eval
  实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
  Also in 5 projects that use this
- truongtv22Skill
  Problem-Solving Techniques
  Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.
  Also in 5 projects that use this
- liufeng1976Skill
  setup-ts-deep-modules
  Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
  Also in 38 projects that use this
- skyllwtSkill
  exp-pilot-eval
  Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
  Also in 4 projects that use this
- skyllwtSkill
  exp-pilot-run
  Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
  Also in 4 projects that use this
- +5 more from Lambenthan
- +1 more from skyllwt
In this repository5 other files it gives its agents.
- code-reviewSkill
- commitSkill
- grill-meSkill
- mock-interviewSkill
- persona-bai-ivanSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

Input

How to research

How to verify

How to report

Examples

Rules

Word for word · 0

Edited · 0

Wrote their own version · 187

daily-arxiv

exp-eval

Problem-Solving Techniques

setup-ts-deep-modules

exp-pilot-eval

exp-pilot-run

Does it work?

Your trail

Now do this for your own.