Skill

research

Verifies sources by fetching actual content from GitHub repos, npm packages, and docs before presenting research findings. Use when asked to research links or documentation.

Github

Bash

Node

documentation

developer-tools

npx claudepluginhub spences10/claude-code-toolkit --plugin toolkit-skills

Tool Access

This skill uses the workspace's default tool permissions.

Preview

1. Fetch actual source content (don't trust snippets)

Supporting Assets

references/ai-search-providers.mdreferences/hallucination-prevention.mdreferences/npm-package-research.mdreferences/partial-data-failures.mdreferences/repo-cloning-pattern.mdreferences/verification-patterns.md

SKILL.md

Similar Skills

research

533

Conducts focused research on technical questions like dependency versions, best practices, docs, and patterns, producing Markdown reports with confidence-rated findings, citations, and action suggestions.

2 files

citadel

research

Gathers read-only external knowledge on libraries, frameworks, SDKs, APIs via 5-tier source priority (official docs first). Use for API queries, migration guides, version changes, RFCs.

odin

Research

Loads research.md to enable research tasks in coding conversations. Useful for information gathering; auto-activates on relevant topics or invoke via /Research.

1 file

eidos

Stats

Parent Repo Stars27

Parent Repo Forks3

Last CommitMar 11, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Verified Research

Quick Start

Fetch actual source content (don't trust snippets)

Verify claims before presenting

Report failures explicitly

Tool Priority

GitHub repos → gh api via Bash

npm packages → npmx.dev API via WebFetch (see npm-package-research.md)

Doc pages → tavily_extract_process

Quick answers → ai_search (perplexity/kagi_fastgpt/exa_answer)

Discovery → web_search or github_search

Fallback → Clone repo via subagent

Core Rules

Never present unverified findings - fetch actual content first

Partial data ≠ success - try next tool, report failures

No source substitution without user consent

Flag contradictions - don't silently pick one source

References

Verified Research

Quick Start

Fetch actual source content (don't trust snippets)
Verify claims before presenting
Report failures explicitly

Tool Priority

GitHub repos → gh api via Bash
npm packages → npmx.dev API via WebFetch (see npm-package-research.md)
Doc pages → tavily_extract_process
Quick answers → ai_search (perplexity/kagi_fastgpt/exa_answer)
Discovery → web_search or github_search
Fallback → Clone repo via subagent

Core Rules

Never present unverified findings - fetch actual content first
Partial data ≠ success - try next tool, report failures
No source substitution without user consent
Flag contradictions - don't silently pick one source

References

verification-patterns.md - Source conflicts, cutoff handling
ai-search-providers.md - exa_answer, perplexity, kagi usage
hallucination-prevention.md - CoVe, atomic facts
repo-cloning-pattern.md - Subagent clone workflow
partial-data-failures.md - Rate limits, fallbacks
npm-package-research.md - npmx.dev type docs, version resolution, fallbacks