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

Research External

by parcadei in parcadei/Continuous-Claude-v3

External research workflow for docs, web, APIs - NOT codebase exploration

MITAuto-check: notes

Install Research External

skills CLI
$ npx skills add parcadei/Continuous-Claude-v3 --skill research-external -a claude-code

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

GitHub CLI
$ gh skill install parcadei/Continuous-Claude-v3 research-external --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/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/research-external .claude/skills/research-external && 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
research-external
GitHub stars
3.9k
Used in
2 other repos
Token cost
~2.8k tokens
SKILL.md length
573 words
Files
1
Skills in repo
141
Repo updated
First seen
Licence
MIT

At a glance

External research workflow for docs, web, APIs - NOT codebase exploration

  • Works in 10 steps: Research Type → Specific Topic → Library Details (if library focus) → …
  • SKILL.md covers Invocation, Question Flow (No Arguments), Focus Modes (First Argument) and Options, plus 10 more sections
  • Calls uv; needs NIA_API_KEY and PERPLEXITY_API_KEY

What it does

Research External is an agent skill from parcadei/Continuous-Claude-v3. External research workflow for docs, web, APIs - NOT codebase exploration

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. The licence is MIT.

Example prompts

  • “/research-external”

Requirements

  • Python 3
  • Node.js
  • A credential in NIA_API_KEY
  • A credential in PERPLEXITY_API_KEY
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Task

Workflow steps

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

  1. Research Type
  2. Specific Topic
  3. Library Details (if library focus)
  4. Depth
  5. Output
  6. Parse Arguments
  7. Execute Research by Focus
  8. Synthesize Findings
  9. Write Output
  10. Return Summary

What it can do on your machine

Read from SKILL.md and the folder at commit d07ff4b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Task

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • NIA_API_KEY
    • PERPLEXITY_API_KEY
    • FIRECRAWL_API_KEY

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

Context cost

Research External loads about 2.8k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 573 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:440
    TY_API_KEY` in environment or `~/.claude/.env`
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Task

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 parcadei/Continuous-Claude-v3 at commit d07ff4b, republished under its MIT licence (© parcadei). 573 words, ~2,818 tokens.

Download SKILL.mdSave it as .claude/skills/research-external/SKILL.md (or your agent's skills folder).
name
research-external
description
External research workflow for docs, web, APIs - NOT codebase exploration
allowed-tools
Bash, Read, Write, Task
model
sonnet

External Research Workflow

Research external sources (documentation, web, APIs) for libraries, best practices, and general topics.

Note: The current year is 2025. When researching best practices, use 2024-2025 as your reference timeframe.

Invocation

/research-external <focus> [options]

Question Flow (No Arguments)

If the user types just /research-external with no or partial arguments, guide them through this question flow. Use AskUserQuestion for each phase.

Phase 1: Research Type
yaml
question: "What kind of information do you need?"
header: "Type"
options:
  - label: "How to use a library/package"
    description: "API docs, examples, patterns"
  - label: "Best practices for a task"
    description: "Recommended approaches, comparisons"
  - label: "General topic research"
    description: "Comprehensive multi-source search"
  - label: "Compare options/alternatives"
    description: "Which tool/library/approach is best"

Mapping:

  • "How to use library" → library focus
  • "Best practices" → best-practices focus
  • "General topic" → general focus
  • "Compare options" → best-practices with comparison framing
Phase 2: Specific Topic
yaml
question: "What specifically do you want to research?"
header: "Topic"
options: []  # Free text input

Examples of good answers:

  • "How to use Prisma ORM with TypeScript"
  • "Best practices for error handling in Python"
  • "React vs Vue vs Svelte for dashboards"
Phase 3: Library Details (if library focus)

If user selected library focus:

yaml
question: "Which package registry?"
header: "Registry"
options:
  - label: "npm (JavaScript/TypeScript)"
    description: "Node.js packages"
  - label: "PyPI (Python)"
    description: "Python packages"
  - label: "crates.io (Rust)"
    description: "Rust crates"
  - label: "Go modules"
    description: "Go packages"

Then ask for specific library name if not already provided.

Phase 4: Depth
yaml
question: "How thorough should the research be?"
header: "Depth"
options:
  - label: "Quick answer"
    description: "Just the essentials"
  - label: "Thorough research"
    description: "Multiple sources, examples, edge cases"

Mapping:

  • "Quick answer" → --depth shallow
  • "Thorough" → --depth thorough
Phase 5: Output
yaml
question: "What should I produce?"
header: "Output"
options:
  - label: "Summary in chat"
    description: "Tell me what you found"
  - label: "Research document"
    description: "Write to thoughts/shared/research/"
  - label: "Handoff for implementation"
    description: "Prepare context for coding"

Mapping:

  • "Research document" → --output doc
  • "Handoff" → --output handoff
Summary Before Execution
Based on your answers, I'll research:

**Focus:** library
**Topic:** "Prisma ORM connection pooling"
**Library:** prisma (npm)
**Depth:** thorough
**Output:** doc

Proceed? [Yes / Adjust settings]

Focus Modes (First Argument)

FocusPrimary ToolPurpose
librarynia-docsAPI docs, usage patterns, code examples
best-practicesperplexity-searchRecommended approaches, patterns, comparisons
generalAll MCP toolsComprehensive multi-source research

Options

OptionValuesDescription
--topic"string"Required. The topic/library/concept to research
--depthshallow, thoroughSearch depth (default: shallow)
--outputhandoff, docOutput format (default: doc)
--library"name"For library focus: specific package name
--registrynpm, py_pi, crates, go_modulesFor library focus: package registry

Workflow

Step 1: Parse Arguments

Extract from user input:

FOCUS=$1           # library | best-practices | general
TOPIC="..."        # from --topic
DEPTH="shallow"    # from --depth (default: shallow)
OUTPUT="doc"       # from --output (default: doc)
LIBRARY="..."      # from --library (optional)
REGISTRY="npm"     # from --registry (default: npm)
Step 2: Execute Research by Focus
Focus: library

Primary tool: nia-docs - Find API documentation, usage patterns, code examples.

bash
# Semantic search in package
(cd $CLAUDE_OPC_DIR && uv run python -m runtime.harness scripts/mcp/nia_docs.py \
  --package "$LIBRARY" \
  --registry "$REGISTRY" \
  --query "$TOPIC" \
  --limit 10)

# If thorough depth, also grep for specific patterns
(cd $CLAUDE_OPC_DIR && uv run python -m runtime.harness scripts/mcp/nia_docs.py \
  --package "$LIBRARY" \
  --grep "$TOPIC")

# Supplement with official docs if URL known
(cd $CLAUDE_OPC_DIR && uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
  --url "https://docs.example.com/api/$TOPIC" \
  --format markdown)

Thorough depth additions:

  • Multiple semantic queries with variations
  • Grep for specific function/class names
  • Scrape official documentation pages
Focus: best-practices

Primary tool: perplexity-search - Find recommended approaches, patterns, anti-patterns.

bash
# AI-synthesized research (sonar-pro)
(cd $CLAUDE_OPC_DIR && uv run python scripts/mcp/perplexity_search.py \
  --research "$TOPIC best practices 2024 2025")

# If comparing alternatives
(cd $CLAUDE_OPC_DIR && uv run python scripts/mcp/perplexity_search.py \
  --reason "$TOPIC vs alternatives - which to choose?")

Thorough depth additions:

bash
# Chain-of-thought for complex decisions
(cd $CLAUDE_OPC_DIR && uv run python scripts/mcp/perplexity_search.py \
  --reason "$TOPIC tradeoffs and considerations 2025")

# Deep comprehensive research
(cd $CLAUDE_OPC_DIR && uv run python scripts/mcp/perplexity_search.py \
  --deep "$TOPIC comprehensive guide 2025")

# Recent developments
(cd $CLAUDE_OPC_DIR && uv run python scripts/mcp/perplexity_search.py \
  --search "$TOPIC latest developments" \
  --recency month --max-results 5)
Focus: general

Use ALL available MCP tools - comprehensive multi-source research.

Step 2a: Library documentation (nia-docs)

bash
(cd $CLAUDE_OPC_DIR && uv run python -m runtime.harness scripts/mcp/nia_docs.py \
  --search "$TOPIC")

Step 2b: Web research (perplexity)

bash
(cd $CLAUDE_OPC_DIR && uv run python scripts/mcp/perplexity_search.py \
  --research "$TOPIC")

Step 2c: Specific documentation (firecrawl)

bash
# Scrape relevant documentation pages found in perplexity results
(cd $CLAUDE_OPC_DIR && uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
  --url "$FOUND_DOC_URL" \
  --format markdown)

Thorough depth additions:

  • Run all three tools with expanded queries
  • Cross-reference findings between sources
  • Follow links from initial results for deeper context
Show full SKILL.md (258 more words)Show less
Step 3: Synthesize Findings

Combine results from all sources:

  1. Key Concepts - Core ideas and terminology
  2. Code Examples - Working examples from documentation
  3. Best Practices - Recommended approaches
  4. Pitfalls - Common mistakes to avoid
  5. Alternatives - Other options considered
  6. Sources - URLs for all citations
Step 4: Write Output
Output: doc (default)

Write to: thoughts/shared/research/YYYY-MM-DD-{topic-slug}.md

markdown
---
date: {ISO timestamp}
type: external-research
topic: "{topic}"
focus: {focus}
sources: [nia, perplexity, firecrawl]
status: complete
---

# Research: {Topic}

## Summary
{2-3 sentence summary of findings}

## Key Findings

### Library Documentation
{From nia-docs - API references, usage patterns}

### Best Practices (2024-2025)
{From perplexity - recommended approaches}

### Code Examples
```{language}
// Working examples found

Recommendations

  • {Recommendation 1}
  • {Recommendation 2}

Pitfalls to Avoid

  • {Pitfall 1}
  • {Pitfall 2}

Alternatives Considered

OptionProsCons
{Option 1}......

Sources


#### Output: `handoff`

Write to: `thoughts/shared/handoffs/{session}/research-{topic-slug}.yaml`

```yaml
---
type: research-handoff
ts: {ISO timestamp}
topic: "{topic}"
focus: {focus}
status: complete
---

goal: Research {topic} for implementation planning
sources_used: [nia, perplexity, firecrawl]

findings:
  key_concepts:
    - {concept1}
    - {concept2}

  code_examples:
    - pattern: "{pattern name}"
      code: |
        // example code

  best_practices:
    - {practice1}
    - {practice2}

  pitfalls:
    - {pitfall1}

recommendations:
  - {rec1}
  - {rec2}

sources:
  - title: "{Source 1}"
    url: "{url1}"
    type: {documentation|article|reference}

for_plan_agent: |
  Based on research, the recommended approach is:
  1. {Step 1}
  2. {Step 2}
  Key libraries: {lib1}, {lib2}
  Avoid: {pitfall1}
Step 5: Return Summary
Research Complete

Topic: {topic}
Focus: {focus}
Output: {path to file}

Key findings:
- {Finding 1}
- {Finding 2}
- {Finding 3}

Sources: {N} sources cited

{If handoff output:}
Ready for plan-agent to continue.

Error Handling

If an MCP tool fails (API key missing, rate limited, etc.):

  1. Log the failure in output:

    yaml
    tool_status:
  nia: success
  perplexity: failed (rate limited)
  firecrawl: skipped

  2. Continue with other sources - partial results are valuable

  3. Set status appropriately:

    • complete - All requested tools succeeded
    • partial - Some tools failed, findings still useful
    • failed - No useful results obtained

  4. Note gaps in findings:

    markdown
    ## Gaps
- Perplexity unavailable - best practices section limited to nia results

Examples

Library Research (Shallow)
/research-external library --topic "dependency injection" --library fastapi --registry py_pi
Best Practices (Thorough)
/research-external best-practices --topic "error handling in Python async" --depth thorough
General Research for Handoff
/research-external general --topic "OAuth2 PKCE flow implementation" --depth thorough --output handoff
Quick Library Lookup
/research-external library --topic "useEffect cleanup" --library react

Integration with Other Skills

After ResearchUse SkillFor
--output handoffplan-agentCreate implementation plan
Code examples foundimplement_taskDirect implementation
Architecture decisioncreate_planDetailed planning
Library comparisonPresent to userDecision making

Required Environment

  • NIA_API_KEY or nia server in mcp_config.json
  • PERPLEXITY_API_KEY in environment or ~/.claude/.env
  • FIRECRAWL_API_KEY and firecrawl server in mcp_config.json

Notes

  • NOT for codebase exploration - Use research-codebase or scout for that
  • Always cite sources - Include URLs for all findings
  • 2024-2025 timeframe - Focus on current best practices
  • Graceful degradation - Partial results better than no results

© parcadei, 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 .claude/skills/research-external of parcadei/Continuous-Claude-v3.

Open the folder on GitHubat commit d07ff4b

Used in 2 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in parcadei/Continuous-Claude-v3, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Research External 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.

Research External compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research External this skillparcadei/Continuous-Claude-v33.9k2 repos~2.8kAutomated safety check: NotesMIT
External Linksthedaviddias/Front-End-Checklist74k—~773Automated safety check: PassMIT
Broken External Linksthedaviddias/Front-End-Checklist74k—~401Automated safety check: PassMIT
Moodle External API Developmentdavila7/claude-code-templates32k8 repos~4.6kAutomated safety check: PassMIT
External AgentsBuilderIO/agent-native7.1k—~7.2kAutomated safety check: NotesNone
External Context ResearchYeachan-Heo/oh-my-claudecode40k—~545Automated safety check: PassMIT

Similar skills

  • External Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing content pages for citation quality, suggesting authoritative sources to link for factual claims, or reviewing whether a page's external link attributes…

    74k GitHub stars~773 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

  • Broken External Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Fix or remove broken external links.

    74k GitHub stars~401 tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed

  • Moodle External API Development

    davila7/claude-code-templates

    Create custom external web service APIs for Moodle LMS. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 8 repos~4.6k tokens
    DevelopmentAuto-check passed

  • External Agents

    BuilderIO/agent-native

    Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native…

    7.1k GitHub stars~7.2k tokensUpdated today
    MobileAuto-check: notes

  • External Context Research

    Yeachan-Heo/oh-my-claudecode

    Breaks a research question into two to five facets and sends parallel document-specialist agents to search the web and documentation, then merges the results.

    40k GitHub stars~545 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • External Research

    huangruiteng/CS-Notes

    Search and inspect external sources for product, design, technical, or comparative research; verify provenance and turn findings into decisions.

    4k GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check: warnings

More from parcadei/Continuous-Claude-v3

All 141 skills in this repo

  • Tldr Deep

    parcadei/Continuous-Claude-v3

    Full 5-layer analysis of a specific function. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 2 repos~677 tokens
    Auto-check passed

  • Compound Learnings

    parcadei/Continuous-Claude-v3

    Transform session learnings into permanent capabilities (skills, rules, agents).

    3.9k GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check: notes

  • Gradient Methods

    parcadei/Continuous-Claude-v3

    Problem-solving strategies for gradient methods in optimization

    3.9k GitHub starsUsed in 3 repos~1k tokens
    Auto-check: notes

  • Debug Hooks

    parcadei/Continuous-Claude-v3

    Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~863 tokens
    Auto-check: notes

  • Math

    parcadei/Continuous-Claude-v3

    Unified math capabilities - computation, solving, and explanation.

    3.9k GitHub starsUsed in 3 repos~1.6k tokens
    Auto-check: notes

  • Math Model Selector

    parcadei/Continuous-Claude-v3

    Routes problems to appropriate mathematical frameworks using expert heuristics

    3.9k GitHub starsUsed in 3 repos~841 tokens
    Auto-check passed

Questions about Research External

What does Research External do?

External research workflow for docs, web, APIs - NOT codebase exploration. Research External is an agent skill from parcadei/Continuous-Claude-v3.

How do I install Research External in Claude Code?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill research-external -a claude-code`. Or copy the skill folder (.claude/skills/research-external in parcadei/Continuous-Claude-v3) into .claude/skills/research-external in your project. Claude Code loads it when a task matches its description.

How do I install Research External in Codex?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill research-external -a codex`. Or copy the skill folder (.claude/skills/research-external in parcadei/Continuous-Claude-v3) into .agents/skills/research-external in your project. Codex loads it when a task matches its description.

Can I use Research External 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 parcadei/Continuous-Claude-v3 --skill research-external -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-external, .gemini/skills/research-external, .github/skills/research-external and .opencode/skills/research-external in your project.

What does Research External need to run?

Going by SKILL.md and its folder, Research External needs the command-line tools its instructions call (uv) and credentials named NIA_API_KEY, PERPLEXITY_API_KEY and FIRECRAWL_API_KEY. Our summary lists: Python 3; Node.js; A credential in NIA_API_KEY; A credential in PERPLEXITY_API_KEY. Its frontmatter pre-approves these tools: Bash, Read, Write, Task.

Does Research External access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Research External safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Research External use?

Research External 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 Research External 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 Research External?

Skills that share tags, products or a category with Research External: External Links (thedaviddias/Front-End-Checklist, 74k stars), Broken External Links (thedaviddias/Front-End-Checklist, 74k stars), Moodle External API Development (davila7/claude-code-templates, 32k stars) and External Agents (BuilderIO/agent-native, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research External?

parcadei (a GitHub user) maintains it in parcadei/Continuous-Claude-v3, which has 3,940 GitHub stars. The repository holds 141 skills in this directory. The repository was last updated on January 26, 2026.

Source: parcadei/Continuous-Claude-v3 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.