agentleFS
Sign inStart free
karim-bhalwanikarim-bhalwani/agent-skills-collection/skills/researcher/SKILL.md

researcher

Skill0 starsChanged 10 months agoMITView on GitHub

Specialized in verifying technical facts, fetching external documentation, and validating syntax to prevent hallucinations. Use when fact-checking technical information, researching technologies, validating implementation approaches, or confirming documentation accuracy.

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use build-premium-website, cost-reducer and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • yawningwhaleAISkill

    build-premium-website

    Build a premium, animated marketing website (React + Vite + Tailwind + GSAP) for any industry. Use when the user asks to "build a website", "make a landing page for [business]", "build a marketing site", or wants a high-end animated company website. Adapts color, copy, services, and signature animation to the industry.

    Also in 7 projects that use this

  • huyvpSkill

    cost-reducer

    Reduce cloud, infrastructure, and operational costs while maintaining performance. Use when writing database queries, configuring cloud resources, optimizing bundles, setting up caching, choosing between services, sizing instances, configuring CDN, managing storage, or reviewing code for cost inefficiencies. Covers AWS/GCP/Vercel pricing, database optimization, serverless tuning, image pipelines, observability costs, and FinOps practices.

    Also in 11 projects that use this

  • yawningwhaleAISkill

    instantly-campaign

    Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.

    Also in 6 projects that use this

  • xfstudioSkill

    trigger-dev

    Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.

    Also in 10 projects that use this

  • ffsshhttiikkSkill

    scalability

    Core foundational concepts and principles for Scalability

    Also in 10 projects that use this

  • h-mascotSkill

    self-healing

    Wrap long-running or fragile OpenClaw work in checkpointed retries, watchdogs, fallback models, and proof-of-completion so failed subagents can resume instead of silently dying.

    Also in 12 projects that use this

  • +4 more from yawningwhaleAI

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Fact Checking: Verify library versions via pyproject.toml, package.json, or environment checks.

    line 20
  2. Distinctive:

    Doc Hunting: Search and read official documentation for specific versions of tools/libraries.

    line 21
  3. Very specific:

    Deep Search: Use search_web and read_url_content to fetch documentation for that specific version.

    line 28
  4. Distinctive:

    Validation: Check if proposed methods, arguments, or schemas are deprecated or valid within the detected version.

    line 29
  5. Distinctive:

    Source Attribution: Always provide the link to the official documentation source.

    line 30
  6. Distinctive:

    When using a third-party library or API.

    line 34
  7. Distinctive:

    When encountering "deprecated" warnings or unexpected behavior in a framework.

    line 35
  8. Distinctive:

    Before implementation to ensure the chosen syntax is optimal for the current version.

    line 36
  9. Distinctive:

    DO NOT guess: If a documentation source is unavailable, state it clearly.

    line 41
  10. Distinctive:

    Read-Only: Only fetch and report information.

    line 42
  11. Distinctive:

    Success Criteria: All claims are backed by authoritative links and examples that match the target version

    line 66
  12. Distinctive:

    Technical Constraints: Avoid making implementation changes.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Researcher Skill - Documentation & Fact Verification

Overview

The Researcher skill ensures that technical decisions are based on verified facts and official documentation. It acts as a safety against AI hallucinations of library implementations.

Core Capabilities

  1. Fact Checking: Verify library versions via pyproject.toml, package.json, or environment checks.
  2. Doc Hunting: Search and read official documentation for specific versions of tools/libraries.
  3. Syntax Validation: Compare proposed implementation snippets against official examples to ensure correctness.
  4. Environment Audit: Identify installed versions and their available features.

Verification Protocol

  1. Version Audit: Identify the exact version of the technology in use.
  2. Deep Search: Use search_web and read_url_content to fetch documentation for that specific version.
  3. Validation: Check if proposed methods, arguments, or schemas are deprecated or valid within the detected version.
  4. Source Attribution: Always provide the link to the official documentation source.

When to Use

  • When using a third-party library or API.
  • When encountering "deprecated" warnings or unexpected behavior in a framework.
  • Before implementation to ensure the chosen syntax is optimal for the current version.

Constraints

  • NO implementation code. Provide confirmed snippets or links only.
  • DO NOT guess. If a documentation source is unavailable, state it clearly.
  • Read-Only. Only fetch and report information.

Common Pitfalls

  • Outdated Documentation: Copy-pasting from old blog posts instead of checking official docs for the current version. Always verify version compatibility.
  • Ignoring Deprecation Warnings: "This still works" isn't good enough. Check changelogs; new versions may break APIs you're using.
  • Trusting Stack Overflow: Great for ideas, terrible for truth. Always verify against official documentation and source code.
  • Assuming Compatibility: "This library should work with that version" requires evidence. Check dependency specs explicitly.
  • Missing Edge Cases: Official docs show the happy path. Check issues/discussions for known gotchas and workarounds.
  • Not Citing Sources: Recommendations without sources are hallucinations. Every claim must have a link to official docs or source code.

Integration Points

PhaseInput FromOutput ToContext
InvestigationQuestion about library/APIFact verificationResearch current version and features
ValidationProposed implementationimplementerConfirm proposed syntax matches official docs
DecisionTechnology comparisonarchitectProvide version-accurate comparisons for arch decisions
PreventionBefore implementationimplementerValidate approaches against official capabilities

Outputs & Deliverables

  • Primary Output: Verified documentation references, version-accurate code snippets, and source links
  • Secondary Output: Compatibility notes and deprecation warnings relevant to the project's versions
  • Success Criteria: All claims are backed by authoritative links and examples that match the target version
  • Quality Gate: implementer or requestor review for actionable code snippets

Additional Constraints

  • Technical Constraints: Avoid making implementation changes; provide exact references and examples only
  • Governance Constraints: Cite official docs and avoid relying on unverified third-party blogs for critical claims

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free