agentleFS
jjenkinsjjenkins/agent-image-skills/.claude/skills/image-files/SKILL.md

image-files

Skill1 starsChanged 9 months agoMITView on GitHub

List and browse uploaded images stored on Lab Nocturne. View file names, sizes, types, and CDN URLs with pagination and sorting. Image asset management for AI agents — find previously uploaded screenshots, photos, and files. Use this skill whenever the user wants to see what images they have, find an image ID, look up a previously uploaded file, or browse their hosted assets. Triggered by /files or naturally.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    If the user asks for "page N", calculate offset as (N - 1) * limit.

    line 33
  2. Very specific:

    Follow the steps in references/auth.md to resolve the API key and base URL.

    line 37
  3. Distinctive:

    After the list, show pagination info: "Showing X-Y of Z files"

    line 76
  4. Very specific:

    If there are more files (i.e.

    line 77
  5. Very specific:

    If the list is empty, tell the user they have no uploaded files yet.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

List Files

List uploaded files from your Lab Nocturne Images account with pagination and sorting.

Invocation

/files [options] — also triggered naturally (e.g. "list my hosted images", "show my image uploads", "what images have I stored", "find the image I uploaded earlier").

Options can be specified naturally (e.g. /files newest first, /files limit 10, /files page 2).

Instructions

1. Parse options

Extract optional parameters from the user's input:

  • limit: number of files to return (1-100, default 100)
  • offset: number of files to skip for pagination (default 0)
  • sort: one of uploaded_at_desc (default), uploaded_at_asc, size_desc, size_asc

Map natural language to sort values:

  • "newest first", "most recent" → uploaded_at_desc
  • "oldest first" → uploaded_at_asc
  • "largest first", "biggest" → size_desc
  • "smallest first" → size_asc

If the user asks for "page N", calculate offset as (N - 1) * limit.

2. Authenticate

Follow the steps in references/auth.md to resolve the API key and base URL.

3. Fetch the file list

Run:

curl -s -w '\n%{http_code}' \
  -H "Authorization: Bearer <api_key>" \
  "<base_url>/files?limit=<limit>&offset=<offset>&sort=<sort>"

Parse the last line as the HTTP status code and everything before it as the response body.

4. Handle the response

Success (HTTP 200) — the response body is:

{
  "files": [
    {
      "id": "img_...",
      "url": "https://cdn.labnocturne.com/...",
      "filename": "photo.jpg",
      "size": 245678,
      "mime_type": "image/jpeg",
      "uploaded_at": "2025-01-01T00:00:00Z"
    }
  ],
  "pagination": {
    "total": 50,
    "limit": 100,
    "offset": 0,
    "next": "https://..."
  }
}

Present to the user as a formatted list:

  • For each file show: ID, filename, size (human-readable, e.g. "240 KB"), type (mime_type), uploaded (relative time, e.g. "2 days ago")
  • After the list, show pagination info: "Showing X-Y of Z files"
  • If there are more files (i.e. pagination.next is present), tell the user how to see the next page (e.g. "Use /files page 2 to see more")
  • If the list is empty, tell the user they have no uploaded files yet. Suggest using /upload <path> to get started

Error — see references/auth.md for common error codes. If the server returns a non-JSON response or an unexpected HTTP status, tell the user the API may be temporarily unavailable.

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.