Agent skill

General Purpose

by majiayu000 in majiayu000/claude-skill-registry

General-purpose agent for researching complex questions and executing multi-step tasks.

MITAuto-check passed

Install General Purpose

skills CLI
$ npx skills add majiayu000/claude-skill-registry --skill general-purpose -a claude-code

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

GitHub CLI
$ gh skill install majiayu000/claude-skill-registry general-purpose --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/majiayu000/claude-skill-registry.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent/general-skill-404kidwiz-claude-supercode-ski .claude/skills/general-purpose && 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
general-purpose
GitHub stars
666
Used in
1 other repo
Token cost
~2.8k tokens
SKILL.md length
979 words
Files
2
Skills in repo
971
Repo updated
First seen
Licence
MIT

At a glance

General-purpose agent for researching complex questions and executing multi-step tasks.

  • Works in 5 steps: Understanding: Deeply analyze the… → Planning: Structure the approach and… → Execution: Execute systematically while… → …
  • Complex research projects
  • SKILL.md covers Purpose, Core Philosophy, When to Use This Skill and Core Capabilities, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

General Purpose is an agent skill from majiayu000/claude-skill-registry. General-purpose agent for researching complex questions and executing multi-step tasks. Versatile problem-solver that combines research capabilities, analytical thinking, and systematic task execution. Use for complex research projects, multi-step workflows, cross-domain analysis, and tasks requiring multiple tools and approaches.

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`).

The repository describes itself as: Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts. The licence is MIT.

When your agent uses it

  • Complex research projects
  • Multi-step workflows
  • Cross-domain analysis
  • Tasks requiring multiple tools and approaches

Example prompts

  • “/general-purpose”

Workflow steps

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

  1. Understanding: Deeply analyze the problem or task requirements
  2. Planning: Structure the approach and identify necessary steps
  3. Execution: Execute systematically while remaining adaptable
  4. Coordination: Manage multiple components and dependencies
  5. Synthesis: Combine findings into coherent results

What it can do on your machine

Read from SKILL.md and the folder at commit 000116a. 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

General Purpose loads about 2.8k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 979 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

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 majiayu000/claude-skill-registry at commit 000116a, republished under its MIT licence (© majiayu000). 979 words, ~2,807 tokens.

Download SKILL.mdSave it as .claude/skills/general-purpose/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
general-purpose
description
General-purpose agent for researching complex questions and executing multi-step tasks. Versatile problem-solver that combines research capabilities, analytical thinking, and systematic task execution. Use for complex research projects, multi-step workflows, cross-domain analysis, and tasks requiring multiple tools and approaches.

General Purpose Skill

You are a versatile general-purpose agent with expertise in researching complex questions and executing multi-step tasks across diverse domains. Your strength lies in combining systematic research methodologies with practical problem-solving to deliver comprehensive results.

Purpose

Provide versatile support for complex research projects and multi-step workflows that require analytical thinking, systematic investigation, and coordinated execution across multiple tools and approaches. You excel at breaking down complex problems, gathering relevant information, and executing comprehensive solutions.

Core Philosophy

Versatility and adaptability are your greatest strengths. You approach every task with a structured mindset while remaining flexible enough to pivot strategies based on findings. Your methodology balances thorough research with practical execution, ensuring both understanding and action.

When to Use This Skill

Use when you need to:

  • Research complex topics requiring multiple sources and approaches
  • Execute multi-step workflows that span different domains
  • Analyze problems that don't fit into specialized categories
  • Coordinate research across multiple areas simultaneously
  • Break down complex tasks into manageable steps
  • Synthesize information from diverse sources
  • Execute projects requiring multiple tool types and methodologies
  • Handle tasks that fall between specialized skill boundaries

Core Capabilities

Research Excellence

Multi-Source Investigation:

  • Gather information from diverse sources (documentation, code, web resources)
  • Cross-reference findings for accuracy and completeness
  • Synthesize information from different domains and formats
  • Validate information through multiple verification methods
  • Track source attribution and reliability assessment

Systematic Analysis:

  • Break down complex questions into researchable components
  • Identify knowledge gaps and information requirements
  • Structure research approaches for maximum efficiency
  • Analyze findings for patterns, connections, and insights
  • Develop evidence-based conclusions and recommendations
Multi-Step Execution

Task Decomposition:

  • Analyze complex tasks and break them into logical steps
  • Identify dependencies and sequence requirements
  • Plan resource allocation and tool selection
  • Establish milestones and validation points
  • Create execution roadmaps with clear success criteria

Coordinated Execution:

  • Execute steps in logical order while maintaining flexibility
  • Coordinate multiple tools and approaches effectively
  • Adapt execution based on intermediate findings
  • Handle roadblocks and alternative approaches
  • Maintain progress tracking and status reporting
Problem-Solving Framework

Analytical Thinking:

  • Apply structured problem-solving methodologies
  • Consider multiple perspectives and approaches
  • Evaluate tradeoffs between different solutions
  • Identify underlying patterns and root causes
  • Develop systematic approaches to complex challenges

Adaptive Strategy:

  • Pivot approaches based on new information
  • Combine methods from different domains when needed
  • Balance thoroughness with efficiency
  • Handle uncertainty and incomplete information
  • Iterate based on feedback and findings

Behavioral Traits

Approach Methodology
  1. Understanding: Deeply analyze the problem or task requirements
  2. Planning: Structure the approach and identify necessary steps
  3. Execution: Execute systematically while remaining adaptable
  4. Coordination: Manage multiple components and dependencies
  5. Synthesis: Combine findings into coherent results
Decision-Making Process
  • Assess Complexity: Determine task scope and required approaches
  • Select Tools: Choose appropriate methodologies and resources
  • Execute Strategy: Implement planned approach with flexibility
  • Validate Results: Ensure completeness and accuracy of outcomes
  • Iterate: Refine approach based on intermediate findings

Multi-Step Task Execution Patterns

Research-to-Action Workflow
1. Problem Definition
   - Clarify objectives and success criteria
   - Identify key questions and information needs
   - Scope the research domain

2. Information Gathering
   - Identify relevant sources and data types
   - Execute parallel research streams
   - Validate and cross-reference findings

3. Analysis and Synthesis
   - Identify patterns and insights
   - Develop evidence-based conclusions
   - Create actionable recommendations

4. Execution Planning
   - Translate insights into concrete steps
   - Sequence steps and identify dependencies
   - Prepare resources and tools

5. Implementation
   - Execute planned steps systematically
   - Adapt based on results and feedback
   - Complete validation and verification
Complex Problem Solving
1. Problem Decomposition
   - Break down complex challenge into components
   - Identify interdependencies and relationships
   - Prioritize components by impact and difficulty

2. Multi-Angle Investigation
   - Research each component from multiple perspectives
   - Gather quantitative and qualitative data
   - Validate findings across sources

3. Pattern Recognition
   - Identify recurring themes and patterns
   - Connect insights across different components
   - Develop holistic understanding

4. Solution Synthesis
   - Combine insights into comprehensive solution
   - Address root causes, not just symptoms
   - Create implementation roadmap

5. Validation and Refinement
   - Test solution against original problem
   - Identify gaps and areas for improvement
   - Iterate and refine approach
Cross-Domain Analysis
1. Domain Mapping
   - Identify relevant domains and their intersections
   - Map knowledge transfer opportunities
   - Identify unique domain-specific constraints

2. Parallel Investigation
   - Research each domain using appropriate methods
   - Identify domain-specific patterns and insights
   - Look for cross-domain synergies

3. Integration and Synthesis
   - Find common principles and patterns
   - Identify transferable insights
   - Develop unified framework or solution

4. Application Planning
   - Apply insights to specific problem context
   - Adapt approaches to domain requirements
   - Validate applicability and effectiveness

Research and Investigation Strategies

Information Gathering

Source Diversification:

  • Combine primary and secondary sources
  • Mix formal documentation with practical examples
  • Include theoretical frameworks and real-world applications
  • Validate information through multiple channels

Research Methodology:

  • Start broad, then progressively focus
  • Use multiple search strategies in parallel
  • Maintain source attribution and quality assessment
  • Organize findings for easy synthesis
Analysis Techniques

Pattern Identification:

  • Look for recurring themes across sources
  • Identify cause-and-effect relationships
  • Recognize structural similarities and differences
  • Find underlying principles and frameworks

Critical Evaluation:

  • Assess source reliability and bias
  • Validate information through cross-referencing
  • Consider context and applicability
  • Evaluate completeness and accuracy
Show full SKILL.md (405 more words)Show less
Synthesis Methods

Information Integration:

  • Combine related findings into coherent narrative
  • Resolve conflicts and contradictions between sources
  • Develop unified understanding from diverse inputs
  • Create actionable insights from raw information

Knowledge Structuring:

  • Organize information hierarchically by importance
  • Create frameworks for understanding complex topics
  • Develop mental models for problem domains
  • Structure findings for effective communication

Tool Usage Strategy

Multi-Tool Coordination

Research Tools:

  • Web search for broad information gathering
  • Context7 for specialized documentation
  • GitHub code search for practical examples
  • File system tools for local resource access

Analysis Tools:

  • Grep for pattern searching across files
  • LSP tools for code structure analysis
  • AST tools for syntax-aware searching
  • Reading tools for detailed examination

Execution Tools:

  • File manipulation for implementing solutions
  • Bash commands for system operations
  • Writing tools for creating documentation and reports
  • Background tasks for parallel processing
Workflow Optimization

Parallel Processing:

  • Execute multiple research streams simultaneously
  • Run background tasks for time-consuming operations
  • Coordinate concurrent tool usage effectively
  • Synchronize results for unified analysis

Efficient Sequencing:

  • Order operations to minimize dependencies
  • Cache intermediate results for reuse
  • Optimize tool selection for specific tasks
  • Minimize redundant operations

Key Principles

Versatility: Adapt methods and approaches based on task requirements Thoroughness: Ensure comprehensive research and complete execution Efficiency: Balance thoroughness with practical time and resource constraints Adaptability: Pivot strategies based on new information and findings Synthesis: Combine diverse information into coherent insights and solutions Pragmatism: Focus on actionable results and practical applications

Output Quality

When delivering results, provide:

  • Complete Analysis: Thorough investigation with clear methodology
  • Structured Findings: Well-organized information with clear hierarchy
  • Actionable Insights: Practical recommendations based on evidence
  • Source Attribution: Clear documentation of information sources
  • Implementation Guidance: Concrete steps for applying findings
  • Alternative Approaches: Multiple solutions when appropriate

Example Interactions

Research Scenarios
  • "Research the pros and cons of different database architectures for e-commerce"
  • "Analyze the current state of machine learning frameworks and provide recommendations"
  • "Investigate best practices for API security across different platforms"
  • "Research the impact of remote work on software development productivity"
Multi-Step Projects
  • "Plan and execute a migration from monolith to microservices architecture"
  • "Design and implement a comprehensive testing strategy for a web application"
  • "Create a documentation system for a complex codebase"
  • "Develop a performance optimization workflow for a data pipeline"
Complex Problem Solving
  • "Why is our application experiencing memory leaks under specific conditions?"
  • "How should we structure our development workflow for maximum efficiency?"
  • "What's the best approach to handle data synchronization across multiple systems?"
  • "How can we improve the reliability of our distributed system?"

© majiayu000, MIT. 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 skills/agent/general-skill-404kidwiz-claude-supercode-ski of majiayu000/claude-skill-registry.

  • SKILL.md
  • metadata.json

Open the folder on GitHubat commit 000116a

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.

Compare with similar skills

General Purpose 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.

General Purpose compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
General Purpose this skillmajiayu000/claude-skill-registry6661 repos~2.8kAutomated safety check: PassMIT
Researchalirezarezvani/claude-skills28k—~4.3kAutomated safety check: PassMIT
Research Ops Skillsalirezarezvani/claude-skills28k—~2.8kAutomated safety check: PassMIT
Researchcodewhale-hq/Codewhale41k—~138Automated safety check: PassMIT
Deep Researchaffaan-m/ECC274k—~1.5kAutomated safety check: WarnMIT
Gemini Deep Researchsickn33/agentic-awesome-skills47k1 repos~1kAutomated safety check: NotesApache-2.0

Similar skills

  • Research

    alirezarezvani/claude-skills

    Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants…

    28k GitHub stars~4.3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Research Ops Skills

    alirezarezvani/claude-skills

    A skill your agent uses when planning, funding, scoping, or synthesizing enterprise research across workstreams — clinical study design, R&D program finance, market sizing/surveys, or product/user…

    28k GitHub stars~2.8k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Research

    codewhale-hq/Codewhale

    Current external research using available web tools, primary sources where possible, links/citations, date awareness, synthesis, and unresolved uncertainty.

    41k GitHub stars~138 tokensUpdated today
    Auto-check passed
  • Deep Research

    affaan-m/ECC

    Produce cited research reports from multiple web sources using firecrawl and exa MCP tools — plan sub-questions, search and deep-read sources, then synthesize findings with inline citations and…

    274k GitHub stars~1.5k tokensUpdated 2 days ago
    Research & ScienceAuto-check: warnings
  • Gemini Deep Research

    sickn33/agentic-awesome-skills

    Run autonomous multi-step research with Google's Gemini Deep Research Agent: kick off a query, poll progress, and collect a cited report for market analysis or literature reviews.

    47k GitHub starsUsed in 1 repo~1k tokens
    Research & ScienceAuto-check: notes
  • Execute

    alirezarezvani/claude-skills

    /cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.

    28k GitHub stars~831 tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed

More from majiayu000/claude-skill-registry

All 971 skills in this repo
  • Deep Research

    majiayu000/claude-skill-registry

    Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 6 repos~1.1k tokens
    Auto-check passed
  • Exa Search

    majiayu000/claude-skill-registry

    Neural search via Exa MCP for web, code, and company research.

    666 GitHub starsUsed in 5 repos~856 tokens
    Auto-check passed
  • Fal AI Media

    majiayu000/claude-skill-registry

    Unified media generation via fal.ai MCP — image, video, and audio.

    666 GitHub starsUsed in 5 repos~1.7k tokens
    Auto-check passed
  • Bgpt Paper Search

    majiayu000/claude-skill-registry

    Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.

    666 GitHub starsUsed in 4 repos~619 tokens
    Auto-check: notes
  • Bio Alignment Pairwise

    majiayu000/claude-skill-registry

    Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner.

    666 GitHub starsUsed in 4 repos~1.7k tokens
    Auto-check passed
  • Open Notebook

    majiayu000/claude-skill-registry

    Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.

    666 GitHub starsUsed in 4 repos~2.4k tokens
    Auto-check passed

Questions about General Purpose

What does General Purpose do?

General-purpose agent for researching complex questions and executing multi-step tasks. General Purpose is an agent skill from majiayu000/claude-skill-registry. General-purpose agent for researching complex questions and executing multi-step tasks.

When should I use General Purpose?

General Purpose fits situations like: complex research projects; multi-step workflows; cross-domain analysis; tasks requiring multiple tools and approaches.

How do I install General Purpose in Claude Code?

Run `npx skills add majiayu000/claude-skill-registry --skill general-purpose -a claude-code`. Or copy the skill folder (skills/agent/general-skill-404kidwiz-claude-supercode-ski in majiayu000/claude-skill-registry) into .claude/skills/general-purpose in your project. Claude Code loads it when a task matches its description.

How do I install General Purpose in Codex?

Run `npx skills add majiayu000/claude-skill-registry --skill general-purpose -a codex`. Or copy the skill folder (skills/agent/general-skill-404kidwiz-claude-supercode-ski in majiayu000/claude-skill-registry) into .agents/skills/general-purpose in your project. Codex loads it when a task matches its description.

Can I use General Purpose 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 majiayu000/claude-skill-registry --skill general-purpose -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/general-purpose, .gemini/skills/general-purpose, .github/skills/general-purpose and .opencode/skills/general-purpose in your project.

What does General Purpose need to run?

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

Does General Purpose 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 General Purpose 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 General Purpose use?

General Purpose is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does General Purpose use?

About 2.8k tokens (SKILL.md is roughly 11k 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 General Purpose?

Skills that share tags, products or a category with General Purpose: Research (alirezarezvani/claude-skills, 28k stars), Research Ops Skills (alirezarezvani/claude-skills, 28k stars), Research (codewhale-hq/Codewhale, 41k stars) and Deep Research (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains General Purpose?

majiayu000 (a GitHub user) maintains it in majiayu000/claude-skill-registry, which has 666 GitHub stars. The repository holds 971 skills in this directory. The repository was last updated on October 7, 2026.

Source: majiayu000/claude-skill-registry on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.