agentleFS
Sign inStart free
aws-solutionsaws-solutions/konductor/skills/find-aws-skills/SKILL.md

find-aws-skills

Skill11 starsChanged 50 days agoApache-2.0View on GitHub

Discovers and retrieves additional AWS skills for specialized tasks not covered by the default bundled skills. Searches the AWS MCP server when a user's request involves an AWS service or workflow without a matching default skill. Use when the user asks about an AWS service or workflow and no bundled skill covers it.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Use aws___search_documentation with the translated search phrase as search_phrase, topics=["agent_skills"], and limit=3.

    line 16
  2. Distinctive:

    Read the returned results' descriptions and scores.

    line 34
  3. Very specific:

    Use aws___retrieve_skill with the exact skill_name from the selected result.

    line 38
  4. Very specific:

    Follow the loaded skill's instructions.

    line 41
  5. Distinctive:

    If none of the returned results are relevant to the user's request, treat it the same as no results and proceed to Step 3.

    line 45
  6. Distinctive:

    If the search returns no results, no result is relevant, or skill retrieval fails for any reason, give the user a friendly message …

    line 50
  7. Very specific:

    Do not silently fall back to direct AWS API calls via aws___run_script.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Find AWS Skills

Workflow

Step 1: Search for skills

Use aws___search_documentation with the translated search phrase as search_phrase, topics=["agent_skills"], and limit=3.

Translate the user's intent into a somewhat verbose search phrase that preserves context — this improves vector search relevance over minimal keywords.

User saysSearch phrase
"Create a production VPC with multiple AZs"create production VPC multi-AZ networking
"My Lambda is timing out"Lambda function timeout debugging troubleshooting
"Lock down my S3 buckets"secure S3 bucket access policy hardening
"Deploy my app to AWS"deploy application AWS infrastructure
"I'm getting access denied on S3"S3 access denied error troubleshooting

New skills are added regularly. Do not assume a skill does not exist without searching first.

Step 2: Pick and load a skill

Read the returned results' descriptions and scores. Results are ordered by relevance — the first result is the strongest match. Pick the most relevant one based on this ordering and the user's context.

Use aws___retrieve_skill with the exact skill_name from the selected result. Skill names are opaque identifiers — do not guess or fabricate them.

Follow the loaded skill's instructions. If the skill references additional files (e.g., references/architecture.md), retrieve them by calling aws___retrieve_skill again with the same skill_name and the file parameter set to the referenced path.

If none of the returned results are relevant to the user's request, treat it the same as no results and proceed to Step 3.

Step 3: Handle failures

If the search returns no results, no result is relevant, or skill retrieval fails for any reason, give the user a friendly message explaining what happened and offer options:

  1. Retry with a different search phrase
  2. Proceed with direct AWS API calls via aws___run_script (sandboxed Python)
  3. Let the user guide you on how they'd like to proceed

Do not silently fall back to direct AWS API calls via aws___run_script. Wait for the user's confirmation first.

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