Agent skill

Deep Researcher

by Karanjot786 in Karanjot786/agent-skills-cli

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.

MITAuto-check passedMarketing & SEO

Install Deep Researcher

skills CLI
$ npx skills add Karanjot786/agent-skills-cli --skill deep-researcher -a claude-code

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

GitHub CLI
$ gh skill install Karanjot786/agent-skills-cli deep-researcher --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/Karanjot786/agent-skills-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deep-researcher .claude/skills/deep-researcher && 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
deep-researcher
GitHub stars
182
Token cost
~1.6k tokens
SKILL.md length
584 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.

  • Works in 6 steps: Define Research Scope and Objectives → Conduct Initial Exploratory Research → Deep Dive into Key Areas → …
  • The user needs thorough investigation
  • SKILL.md covers When to use this skill, Research Workflow, Research Strategies and Pitfalls to Avoid, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deep Researcher is an agent skill from Karanjot786/agent-skills-cli. Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Use when the user needs thorough investigation, market research, technical deep-dives, due diligence, or comprehensive analysis on any subject.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Market research and Fundraising and pitch decks. It works with OpenAI and TypeScript. The repository describes itself as: Universal CLI for Agent Skills. Access 200,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitHub Copilot, OpenAI Codex, and Antigravity. The licence is MIT.

When your agent uses it

  • The user needs thorough investigation
  • Market research
  • Technical deep-dives
  • Comprehensive analysis on any subject

Example prompts

  • “Use the deep-researcher skill to perform comprehensive, multi-layered research on any topic with structured analysis and synthesis of information…”
  • “/deep-researcher”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Define Research Scope and Objectives
  2. Conduct Initial Exploratory Research
  3. Deep Dive into Key Areas
  4. Cross-Reference and Validate Findings
  5. Synthesize and Analyze Information
  6. Generate Structured Research Report

What it can do on your machine

Read from SKILL.md and the folder at commit 956140b. 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.

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

  • Network

    No URLs in SKILL.md.

    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 Researcher loads about 1.6k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 584 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 Karanjot786/agent-skills-cli at commit 956140b, republished under its MIT licence (© Karanjot786). 584 words, ~1,551 tokens.

Download SKILL.mdSave it as .claude/skills/deep-researcher/SKILL.md (or your agent's skills folder).
name
deep-researcher
description
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Use when the user needs thorough investigation, market research, technical deep-dives, due diligence, or comprehensive analysis on any subject.
license
MIT
metadata.author
ksd
metadata.version
1.0

Deep Researcher

A comprehensive research workflow skill that guides Claude through systematic, multi-layered research on any topic.

When to use this skill

Use this skill when the user:

  • Asks for "deep research" or "comprehensive research" on a topic
  • Needs thorough investigation or due diligence
  • Requests market research or competitive analysis
  • Wants technical deep-dives or architecture reviews
  • Needs literature reviews or trend analysis
  • Asks for detailed reports with multiple perspectives

Research Workflow

Step 1: Define Research Scope and Objectives

Start by clearly establishing research parameters:

  1. Identify the main research question - What is the primary question to investigate?
  2. Define scope boundaries - What aspects should be included or excluded?
  3. Determine depth requirements - How detailed should the research be?
  4. Clarify expected deliverables - What format and structure for output?
  5. List key areas of focus - What specific subtopics to explore?

Document these parameters before proceeding.

Step 2: Conduct Initial Exploratory Research

Begin with broad reconnaissance to map the landscape:

  1. Search for overview information - Find general information, definitions, and context
  2. Identify key sources - Look for authoritative sources, recent publications, expert opinions
  3. Note initial findings - Create preliminary list of important concepts, terms, themes
  4. Discover related topics - Identify adjacent areas that may be relevant
  5. Assess information gaps - Note what's available vs. what needs deeper investigation

Create an initial research map with main themes and subtopics.

Step 3: Deep Dive into Key Areas

For each identified key area, conduct detailed investigation:

  1. Targeted searches - Use specific queries for each subtopic
  2. Multiple perspectives - Seek diverse viewpoints and approaches
  3. Technical details - Gather specific data, statistics, methodologies
  4. Historical context - Understand evolution and background
  5. Current state - Identify latest developments and trends
  6. Future outlook - Look for predictions, projections, emerging patterns

Document findings systematically, noting sources and credibility.

Step 4: Cross-Reference and Validate Findings

Ensure accuracy and reliability:

  1. Verify key facts - Cross-check important information across multiple sources
  2. Identify contradictions - Note where sources disagree and investigate why
  3. Assess source credibility - Evaluate authority and reliability
  4. Check recency - Ensure information is current and relevant
  5. Look for consensus - Identify where experts or multiple sources agree
  6. Flag uncertainties - Mark areas where information is unclear or disputed
Show full SKILL.md (218 more words)Show less
Step 5: Synthesize and Analyze Information

Transform collected data into insights:

  1. Identify patterns - Look for common themes, trends, relationships
  2. Draw connections - Link concepts across sources and subtopics
  3. Generate insights - Develop original observations based on research
  4. Compare and contrast - Analyze similarities and differences
  5. Evaluate implications - Consider significance and consequences
  6. Address the research question - Directly answer original question with evidence
Step 6: Generate Structured Research Report

Create comprehensive, well-organized final report:

## Report Structure

1. **Executive Summary**
   - Brief overview of research question
   - Key findings (3-5 main points)
   - Main conclusions

2. **Introduction**
   - Research scope and objectives
   - Methodology overview
   - Key areas explored

3. **Main Body** (organized by themes)
   - Detailed findings for each key area
   - Supporting evidence and examples
   - Multiple perspectives where relevant
   - Data and statistics

4. **Analysis & Synthesis**
   - Patterns and connections identified
   - Cross-cutting themes
   - Insights and interpretations

5. **Conclusions**
   - Direct answers to research questions
   - Summary of most significant findings
   - Limitations of the research

6. **Sources & References**
   - List of key sources consulted
   - Credibility notes where relevant

Research Strategies

Information Quality Standards
  • Prefer primary sources - Go to original sources when possible
  • Recent is better - Prioritize current information for fast-moving topics
  • Multiple sources - Don't rely on single source for important facts
  • Expert opinion - Seek recognized authorities in the field
  • Data over anecdotes - Prefer statistical evidence to individual stories
Analysis Techniques

Use these frameworks as appropriate:

  • SWOT analysis - Strengths, Weaknesses, Opportunities, Threats
  • Compare/Contrast - Systematic comparison of approaches
  • Timeline analysis - Historical development and trends
  • Stakeholder analysis - Different perspectives and interests
  • Gap analysis - What's missing or needs further research

Pitfalls to Avoid

  • Confirmation bias - Look for information that challenges assumptions
  • Information overload - Know when enough research has been done
  • Outdated information - Always check dates and currency
  • Single-source dependence - Diversify sources
  • Analysis paralysis - Balance thoroughness with timely completion
  • Losing focus - Stay aligned with original objectives

Progress Tracking

Copy and update this checklist as you work:

Research Progress:
- [ ] Step 1: Define scope and objectives
- [ ] Step 2: Initial exploratory research  
- [ ] Step 3: Deep dive into key areas
- [ ] Step 4: Cross-reference and validate
- [ ] Step 5: Synthesize and analyze
- [ ] Step 6: Generate structured report

© Karanjot786, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/deep-researcher of Karanjot786/agent-skills-cli.

Open the folder on GitHubat commit 956140b

Compare with similar skills

Deep Researcher 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 Researcher compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Researcher this skillKaranjot786/agent-skills-cli182—~1.6kAutomated safety check: PassMIT
Consulting Analysisbytedance/deer-flow84k4 repos~8.4kAutomated safety check: PassMIT
Investment AnalysisHainrixz/maia-skill149—~4.2kAutomated safety check: PassMIT
Market Researchcohen-liel/hivemind1106 repos~557Automated safety check: PassApache-2.0
ResearchGerstep/cybos104—~945Automated safety check: PassNone
Market Researchc0x12c/ai-toolkit106—~719Automated safety check: PassNone

Similar skills

  • Consulting Analysis

    bytedance/deer-flow

    A skill your agent uses when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial…

    84k GitHub starsUsed in 4 repos~8.4k tokens
    Marketing & SEOAuto-check passed
  • Investment Analysis

    Hainrixz/maia-skill

    Multi-agent investment research and analysis system by Tododeia.

    149 GitHub stars~4.2k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Market Research

    cohen-liel/hivemind

    Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries.

    110 GitHub starsUsed in 6 repos~557 tokens
    Marketing & SEOAuto-check passed
  • Research

    Gerstep/cybos

    Company due diligence, technology deep-dives, market analysis, and topic exploration for cyber•Fund investment decisions, content creation, and personal projects.

    104 GitHub stars~945 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Market Research

    c0x12c/ai-toolkit

    Run market research, competitive analysis, investor due diligence, and industry scans.

    106 GitHub stars~719 tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Client Deliverables

    garrettjsmith/localseoskills

    When the user needs to create a client-facing document such as an SEO audit, proposal, scope of work, competitive analysis report, onboarding document, or market intelligence report.

    121 GitHub stars~5.8k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed

Categories

Questions about Deep Researcher

What does Deep Researcher do?

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Deep Researcher is an agent skill from Karanjot786/agent-skills-cli. Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.

When should I use Deep Researcher?

Deep Researcher fits situations like: the user needs thorough investigation; market research; technical deep-dives; comprehensive analysis on any subject.

How do I install Deep Researcher in Claude Code?

Run `npx skills add Karanjot786/agent-skills-cli --skill deep-researcher -a claude-code`. Or copy the skill folder (skills/deep-researcher in Karanjot786/agent-skills-cli) into .claude/skills/deep-researcher in your project. Claude Code loads it when a task matches its description.

How do I install Deep Researcher in Codex?

Run `npx skills add Karanjot786/agent-skills-cli --skill deep-researcher -a codex`. Or copy the skill folder (skills/deep-researcher in Karanjot786/agent-skills-cli) into .agents/skills/deep-researcher in your project. Codex loads it when a task matches its description.

Can I use Deep Researcher 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 Karanjot786/agent-skills-cli --skill deep-researcher -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-researcher, .gemini/skills/deep-researcher, .github/skills/deep-researcher and .opencode/skills/deep-researcher in your project.

What does Deep Researcher need to run?

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

Does Deep Researcher access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deep Researcher 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 Researcher use?

Deep Researcher is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deep Researcher use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Researcher?

Skills that share tags, products or a category with Deep Researcher: Consulting Analysis (bytedance/deer-flow, 84k stars), Investment Analysis (Hainrixz/maia-skill, 149 stars), Market Research (cohen-liel/hivemind, 110 stars) and Research (Gerstep/cybos, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Researcher?

Karanjot786 (a GitHub user) maintains it in Karanjot786/agent-skills-cli, which has 182 GitHub stars. The repository was last updated on May 17, 2026.

Source: Karanjot786/agent-skills-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.