agentleFS
aws-solutionsaws-solutions/konductor/skills/external-research/SKILL.md

external-research

Skill11 starsChanged 49 days agoApache-2.0View on GitHub

Search external documentation, web resources, and best practices. Use when gathering information about open-source libraries, AWS services, industry patterns, or external tools.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when you need to:

    line 16
  2. Distinctive:

    Look up AWS service documentation, limits, or pricing

    line 18
  3. Distinctive:

    Do NOT use for private or authenticated resources that require credentialed access.

    line 23
  4. Very specific:

    Use WebFetch to retrieve content from a known URL.

    line 27
  5. Distinctive:

    Always prefer Tier 1–2 sources.

    line 48
  6. Distinctive:

    Not checking version relevance for library/framework guidance

    line 76
  7. Distinctive:

    Not cross-referencing when sources conflict

    line 77

“Common” is measured: kept by at least 6 in 10 of the 4 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

External Research

Overview

Guides systematic searching of external resources — official documentation, open-source repositories, and industry best practices. Ensures findings are reliable, current, and properly cited.

Usage

Use this skill when you need to:

  • Look up AWS service documentation, limits, or pricing
  • Research open-source library APIs, patterns, or known issues
  • Find industry best practices or design patterns
  • Evaluate third-party tools or frameworks

Do NOT use for private or authenticated resources that require credentialed access.

Tools

Use WebFetch to retrieve content from a known URL. When no URL is known, use WebSearch to find relevant public and internal sources, then WebFetch the pages identified.

Search Strategy

  1. Start broad, then narrow — begin with official docs, then drill into specifics
  2. Cross-reference multiple sources — never rely on a single blog post or answer
  3. Prefer official docs over community content — blogs and forums may be outdated or wrong
  4. Check version relevance — ensure docs match the version you're actually using
  5. Note recency — flag if content is older than 12 months for fast-moving technologies

Source Reliability

Ranked from most to least reliable:

TierSourceTrust Level
1Official documentation (AWS docs, library docs)High — authoritative
2GitHub repos (source code, issues, changelogs)High — primary source
3Stack Overflow (highly voted, accepted answers)Medium — verify independently
4Blog posts, tutorials, Medium articlesLow — cross-reference required

Always prefer Tier 1–2 sources. Use Tier 3–4 only to supplement or when higher-tier sources lack coverage.

Output Format

  1. Cite URLs — include the full URL for every finding
  2. Summarize key findings — extract actionable insights, not full page content
  3. Note version and date — include the library/service version and when the source was published
  4. Flag conflicts — if sources disagree, present both sides with reliability tiers
  5. State applicability — note any caveats about environment, version, or scale

Example:

### Finding: S3 Event Notifications support SQS FIFO queues (since Nov 2023)
- **Source:** https://docs.aws.amazon.com/AmazonS3/latest/userguide/notification-how-to-event-types-and-destinations.html
- **Version:** Current (verified May 2025)
- **Confidence:** High (official AWS docs)

Quality Gate

CRITICAL:

  • Presenting information without citing the source URL
  • Using Tier 4 sources as sole evidence for architectural decisions

IMPORTANT:

  • Not checking version relevance for library/framework guidance
  • Not cross-referencing when sources conflict

SUGGESTION:

  • Could include additional alternative approaches from different sources
  • Could note when a technology is changing rapidly and findings may become stale

Optional: Official Slack MCP

Optional: the researcher can also search Slack via the official Slack MCP — see docs/guides/slack-integration.md for setup.

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.