New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Deep Research Methodology

by RightNow-AI in RightNow-AI/openfang

Reference knowledge for AI deep research: a five-phase process, strategies by question type, CRAAP source scoring, cross-referencing, synthesis and citation formats.

Apache-2.0Auto-check passedResearch & Science

Install Deep Research Methodology

skills CLI
$ npx skills add RightNow-AI/openfang --skill researcher-hand-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RightNow-AI/openfang researcher-hand-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RightNow-AI/openfang.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/openfang-hands/bundled/researcher .claude/skills/researcher-hand-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
researcher-hand-skill
GitHub stars
18k
Token cost
~2.6k tokens
SKILL.md length
847 words
Files
2
Skills in repo
68
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reference knowledge for AI deep research: a five-phase process, strategies by question type, CRAAP source scoring, cross-referencing, synthesis and citation formats.

  • Works in 5 steps: Define: Clarify the question, identify… → Search: Systematic multi-strategy search… → Evaluate: Assess source quality, extract… → …
  • Researching an open-ended question across many web sources
  • SKILL.md covers Research Methodology, CRAAP Source Evaluation…, Search Query Optimization and Cross-Referencing Techniques, plus 3 more sections
  • Reaches doi.org

What it does

This skill is a body of reference knowledge rather than a procedure with scripts. Its research process has five phases: define the question, search across varied sources, evaluate them, synthesize findings and resolve contradictions, then verify critical claims and note what stays uncertain.

A table matches question types, such as factual, comparative, causal, predictive, how-to, survey and controversial, to a strategy for each, and complex questions are split into sub-questions. Sources are scored with the CRAAP framework: currency, relevance, authority, accuracy and purpose, with a grade scale that starts at A for sources passing all five criteria. The description also lists search optimization, cross-referencing and citation formats.

When your agent uses it

  • Researching an open-ended question across many web sources
  • Judging whether a source is current, authoritative and unbiased
  • Breaking a broad question into sub-questions before searching
  • Cross-checking critical claims before writing a research report

Example prompts

  • “Research whether our startup should move to microservices and give me a sourced summary.”
  • “Score these five articles on vector databases using CRAAP.”
  • “Compare studies on remote work productivity and flag where the sources disagree.”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Define: Clarify the question, identify what's known vs unknown, set scope
  2. Search: Systematic multi-strategy search across diverse sources
  3. Evaluate: Assess source quality, extract relevant data, note limitations
  4. Synthesize: Combine findings into coherent answer, resolve contradictions
  5. Verify: Cross-check critical claims, identify remaining uncertainties

What it can do on your machine

Read from SKILL.md and the folder at commit acf2587. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • doi.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deep Research Methodology loads about 2.6k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 847 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RightNow-AI/openfang at commit acf2587, republished under its Apache-2.0 licence (© RightNow-AI). 847 words, ~2,624 tokens.

Download SKILL.mdSave it as .claude/skills/researcher-hand-skill/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
researcher-hand-skill
description
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats
version
1.0.0
runtime
prompt_only

Deep Research Expert Knowledge

Research Methodology

Research Process (5 phases)
  1. Define: Clarify the question, identify what's known vs unknown, set scope
  2. Search: Systematic multi-strategy search across diverse sources
  3. Evaluate: Assess source quality, extract relevant data, note limitations
  4. Synthesize: Combine findings into coherent answer, resolve contradictions
  5. Verify: Cross-check critical claims, identify remaining uncertainties
Question Types & Strategies
Question TypeStrategyExample
FactualFind authoritative primary source"What is the population of Tokyo?"
ComparativeMulti-source balanced analysis"React vs Vue for large apps?"
CausalEvidence chain + counterfactuals"Why did Theranos fail?"
PredictiveTrend analysis + expert consensus"Will quantum computing replace classical?"
How-toStep-by-step from practitioners"How to set up a Kubernetes cluster?"
SurveyComprehensive landscape mapping"What are the options for vector databases?"
ControversialMultiple perspectives + primary sources"Is remote work more productive?"
Decomposition Technique

Complex questions should be broken into sub-questions:

Main: "Should our startup use microservices?"
Sub-questions:
  1. What are microservices? (definitional)
  2. What are the benefits vs monolith? (comparative)
  3. What team size/stage is appropriate? (contextual)
  4. What are the operational costs? (factual)
  5. What do similar startups use? (case studies)
  6. What are the migration paths? (how-to)

CRAAP Source Evaluation Framework

Currency
  • When was it published or last updated?
  • Is the information still current for the topic?
  • Are the links functional?
  • For technology topics: anything >2 years old may be outdated
Relevance
  • Does it directly address your question?
  • Who is the intended audience?
  • Is the level of detail appropriate?
  • Would you cite this in your report?
Authority
  • Who is the author? What are their credentials?
  • What institution published this?
  • Is there contact information?
  • Does the URL domain indicate authority? (.gov, .edu, reputable org)
Accuracy
  • Is the information supported by evidence?
  • Has it been reviewed or refereed?
  • Can you verify the claims from other sources?
  • Are there factual errors, typos, or broken logic?
Purpose
  • Why does this information exist?
  • Is it informational, commercial, persuasive, or entertainment?
  • Is the bias clear or hidden?
  • Does the author/organization benefit from you believing this?
Scoring
A (Authoritative):  Passes all 5 CRAAP criteria
B (Reliable):       Passes 4/5, minor concern on one
C (Useful):         Passes 3/5, use with caveats
D (Weak):           Passes 2/5 or fewer
F (Unreliable):     Fails most criteria, do not cite

Search Query Optimization

Query Construction Techniques

Exact phrase: "specific phrase" — use for names, quotes, error messages Site-specific: site:domain.com query — search within a specific site Exclude: query -unwanted_term — remove irrelevant results File type: filetype:pdf query — find specific document types Recency: query after:2024-01-01 — recent results only OR operator: query (option1 OR option2) — broaden search Wildcard: "how to * in python" — fill-in-the-blank

Multi-Strategy Search Pattern

For each research question, use at least 3 search strategies:

  1. Direct: The question as-is
  2. Authoritative: site:gov OR site:edu OR site:org [topic]
  3. Academic: [topic] research paper [year] or site:arxiv.org [topic]
  4. Practical: [topic] guide or [topic] tutorial or [topic] how to
  5. Data: [topic] statistics or [topic] data [year]
  6. Contrarian: [topic] criticism or [topic] problems or [topic] myths
Source Discovery by Domain
DomainBest SourcesSearch Pattern
TechnologyOfficial docs, GitHub, Stack Overflow, engineering blogs[tech] documentation, site:github.com [tech]
SciencePubMed, arXiv, Nature, Sciencesite:arxiv.org [topic], [topic] systematic review
BusinessSEC filings, industry reports, HBR[company] 10-K, [industry] report [year]
MedicinePubMed, WHO, CDC, Cochranesite:pubmed.ncbi.nlm.nih.gov [topic]
LegalCourt records, law reviews, statute databases[case] ruling, [law] analysis
StatisticsCensus, BLS, World Bank, OECDsite:data.worldbank.org [metric]
Current eventsReuters, AP, BBC, primary sources[event] statement, [event] official

Cross-Referencing Techniques

Verification Levels
Level 1: Single source (unverified)
  → Mark as "reported by [source]"

Level 2: Two independent sources agree (corroborated)
  → Mark as "confirmed by multiple sources"

Level 3: Primary source + secondary confirmation (verified)
  → Mark as "verified — primary source: [X]"

Level 4: Expert consensus (well-established)
  → Mark as "widely accepted" or "scientific consensus"
Show full SKILL.md (355 more words)Show less
Contradiction Resolution

When sources disagree:

  1. Check which source is more authoritative (CRAAP scores)
  2. Check which is more recent (newer may have updated info)
  3. Check if they're measuring different things (apples vs oranges)
  4. Check for known biases or conflicts of interest
  5. Present both views with evidence for each
  6. State which view the evidence better supports (if clear)
  7. If genuinely uncertain, say so — don't force a conclusion

Synthesis Patterns

Narrative Synthesis
The evidence suggests [main finding].

[Source A] found that [finding 1], which is consistent with
[Source B]'s observation that [finding 2]. However, [Source C]
presents a contrasting view: [finding 3].

The weight of evidence favors [conclusion] because [reasoning].
A key limitation is [gap or uncertainty].
Structured Synthesis
FINDING 1: [Claim]
  Evidence for: [Source A], [Source B] — [details]
  Evidence against: [Source C] — [details]
  Confidence: [high/medium/low]
  Reasoning: [why the evidence supports this finding]

FINDING 2: [Claim]
  ...
Gap Analysis

After synthesis, explicitly note:

  • What questions remain unanswered?
  • What data would strengthen the conclusions?
  • What are the limitations of the available sources?
  • What follow-up research would be valuable?

Citation Formats

Inline URL
According to a 2024 study (https://example.com/study), the effect was significant.
Footnotes
According to a 2024 study[1], the effect was significant.

---
[1] https://example.com/study — "Title of Study" by Author, Published Date
Academic (APA)
In-text: (Smith, 2024)
Reference: Smith, J. (2024). Title of the article. *Journal Name*, 42(3), 123-145. https://doi.org/10.xxxx

For web sources (APA):

Author, A. A. (Year, Month Day). Title of page. Site Name. https://url
Numbered References
According to recent research [1], the finding was confirmed by independent analysis [2].

## References
1. Author (Year). Title. URL
2. Author (Year). Title. URL

Output Templates

Brief Report
markdown
# [Question]
**Date**: YYYY-MM-DD | **Sources**: N | **Confidence**: high/medium/low

## Answer
[2-3 paragraph direct answer]

## Key Evidence
- [Finding 1] — [source]
- [Finding 2] — [source]
- [Finding 3] — [source]

## Caveats
- [Limitation or uncertainty]

## Sources
1. [Source](url)
2. [Source](url)
Detailed Report
markdown
# Research Report: [Question]
**Date**: YYYY-MM-DD | **Depth**: thorough | **Sources Consulted**: N

## Executive Summary
[1 paragraph synthesis]

## Background
[Context needed to understand the findings]

## Methodology
[How the research was conducted, what was searched, how sources were evaluated]

## Findings

### [Sub-question 1]
[Detailed findings with inline citations]

### [Sub-question 2]
[Detailed findings with inline citations]

## Analysis
[Synthesis across findings, patterns identified, implications]

## Contradictions & Open Questions
[Areas of disagreement, gaps in knowledge]

## Confidence Assessment
[Overall confidence level with reasoning]

## Sources
[Full bibliography in chosen citation format]

Cognitive Bias in Research

Be aware of these biases during research:

  1. Confirmation bias: Favoring information that confirms your initial hypothesis

    • Mitigation: Explicitly search for disconfirming evidence

  2. Authority bias: Over-trusting sources from prestigious institutions

    • Mitigation: Evaluate evidence quality, not just source prestige

  3. Anchoring: Fixating on the first piece of information found

    • Mitigation: Gather multiple sources before forming conclusions

  4. Selection bias: Only finding sources that are easy to access

    • Mitigation: Vary search strategies, check non-English sources

  5. Recency bias: Over-weighting recent publications

    • Mitigation: Include foundational/historical sources when relevant

  6. Framing effect: Being influenced by how information is presented

    • Mitigation: Look at raw data, not just interpretations

Domain-Specific Research Tips

Technology Research
  • Always check the official documentation first
  • Compare documentation version with the latest release
  • Stack Overflow answers may be outdated — check the date
  • GitHub issues/discussions often have the most current information
  • Benchmarks without methodology descriptions are unreliable
Business Research
  • SEC filings (10-K, 10-Q) are the most reliable public company data
  • Press releases are marketing — verify claims independently
  • Analyst reports may have conflicts of interest — check disclaimers
  • Employee reviews (Glassdoor) provide internal perspective but are biased
Scientific Research
  • Systematic reviews and meta-analyses are strongest evidence
  • Single studies should not be treated as definitive
  • Check if findings have been replicated
  • Preprints have not been peer-reviewed — note this caveat
  • p-values and effect sizes both matter — not just "statistically significant"

© RightNow-AI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in crates/openfang-hands/bundled/researcher of RightNow-AI/openfang.

  • SKILL.md
  • HAND.toml

Open the folder on GitHubat commit acf2587

Compare with similar skills

Deep Research Methodology next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deep Research Methodology compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Research Methodology this skillRightNow-AI/openfang18k—~2.6kAutomated safety check: PassApache-2.0
Verify Citationssickn33/agentic-awesome-skills47k1 repos~1kAutomated safety check: PassApache-2.0
ResearchEliasOulkadi/shokunin114—~3.4kAutomated safety check: PassMIT
Citation Verification GuideGalaxy-Dawn/claude-scholar5.7k2 repos~1.9kAutomated safety check: PassMIT
Deep Research WorkflowTokenRhythm/opensquilla7.1k—~1.3kAutomated safety check: PassApache-2.0
Academic Research Suite for CodexImbad0202/academic-research-skills-codex12k—~12kAutomated safety check: PassCustom licence

Similar skills

  • Verify Citations

    sickn33/agentic-awesome-skills

    Verify citations and references in a document, report, or article against real sources.

    47k GitHub starsUsed in 1 repo~1k tokens
    Research & ScienceAuto-check passed

  • Research

    EliasOulkadi/shokunin

    Deep research with web search, source verification, and fact-checking.

    114 GitHub stars~3.4k tokensUpdated 6 days ago
    Research & ScienceAuto-check passed

  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Research & ScienceAuto-check passed

  • Deep Research Workflow

    TokenRhythm/opensquilla

    Runs multi-round research in three stages with a persisted state file, evidence tracking and a long-form report with per-claim citations.

    7.1k GitHub stars~1.3k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Academic Research Suite for Codex

    Imbad0202/academic-research-skills-codex

    A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.

    12k GitHub stars~12k tokensUpdated 7 days ago
    Research & ScienceAuto-check passed

  • Article Fact Checker

    digoal/blog

    三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

More from RightNow-AI/openfang

All 68 skills in this repo

  • Playwright Browser Automation Patterns

    RightNow-AI/openfang

    Reference of CSS selectors, step-by-step web workflows and error recovery tactics for an agent that browses, fills forms and compares prices on live sites.

    18k GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed

  • Intelligence Collection Methodology

    RightNow-AI/openfang

    Reference knowledge for open-source intelligence collection: the collection cycle, source reliability tiers, search query patterns and entity extraction.

    18k GitHub stars~2.1k tokensUpdated 3 mo ago
    Auto-check passed

  • Lead Generation Research Guide

    RightNow-AI/openfang

    Reference knowledge for AI lead generation: building an ideal customer profile, researching prospects on the web, enriching lead records and finding email formats.

    18k GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed

  • Video Clipping Reference

    RightNow-AI/openfang

    Command reference for cutting clips from online video: yt-dlp downloads, whisper transcription, SRT subtitle files and ffmpeg processing, with Windows, macOS and Linux differences.

    18k GitHub stars~4.1k tokensUpdated 3 mo ago
    Auto-check: warnings

  • Forecasting Expert Knowledge

    RightNow-AI/openfang

    Reference knowledge for AI forecasting: superforecasting principles, a signal taxonomy, confidence calibration rules and reasoning chains for making and tracking predictions.

    18k GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Twitter Hand Skill

    RightNow-AI/openfang

    Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking

    18k GitHub stars~2.9k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Deep Research Methodology

What does Deep Research Methodology do?

Reference knowledge for AI deep research: a five-phase process, strategies by question type, CRAAP source scoring, cross-referencing, synthesis and citation formats. This skill is a body of reference knowledge rather than a procedure with scripts. Its research process has five phases: define the question, search across varied sources, evaluate them, synthesize findings and resolve contradictions, then verify critical claims and note what stays uncertain.

When should I use Deep Research Methodology?

Deep Research Methodology fits situations like: researching an open-ended question across many web sources; judging whether a source is current, authoritative and unbiased; breaking a broad question into sub-questions before searching; cross-checking critical claims before writing a research report.

How do I install Deep Research Methodology in Claude Code?

Run `npx skills add RightNow-AI/openfang --skill researcher-hand-skill -a claude-code`. Or copy the skill folder (crates/openfang-hands/bundled/researcher in RightNow-AI/openfang) into .claude/skills/researcher-hand-skill in your project. Claude Code loads it when a task matches its description.

How do I install Deep Research Methodology in Codex?

Run `npx skills add RightNow-AI/openfang --skill researcher-hand-skill -a codex`. Or copy the skill folder (crates/openfang-hands/bundled/researcher in RightNow-AI/openfang) into .agents/skills/researcher-hand-skill in your project. Codex loads it when a task matches its description.

Can I use Deep Research Methodology in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RightNow-AI/openfang --skill researcher-hand-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/researcher-hand-skill, .gemini/skills/researcher-hand-skill, .github/skills/researcher-hand-skill and .opencode/skills/researcher-hand-skill in your project.

What does Deep Research Methodology need to run?

SKILL.md names no scripts, command-line tools or credentials: Deep Research Methodology is instructions for the agent only.

Does Deep Research Methodology access the network?

SKILL.md names 1 domain. In commands or code: doi.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Deep Research Methodology safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deep Research Methodology use?

Deep Research Methodology is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deep Research Methodology use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deep Research Methodology?

Skills that share tags, products or a category with Deep Research Methodology: Verify Citations (sickn33/agentic-awesome-skills, 47k stars), Research (EliasOulkadi/shokunin, 114 stars), Citation Verification Guide (Galaxy-Dawn/claude-scholar, 5.7k stars) and Deep Research Workflow (TokenRhythm/opensquilla, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Research Methodology?

RightNow-AI (a GitHub organization) maintains it in RightNow-AI/openfang, which has 18,214 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on July 2, 2026.

Source: RightNow-AI/openfang on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.