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

image-delete

Skill1 starsChanged 9 months agoMITView on GitHub

Delete an image from Lab Nocturne image storage. Remove uploaded screenshots, photos, or other hosted files by image ID. Soft-delete with confirmation — clean up old uploads, free storage space, remove unwanted images from CDN. Use this skill whenever the user wants to remove, delete, or clean up an image — even if they say 'get rid of that image' or 'I don't need that upload anymore'. Triggered by /delete <image_id> or naturally.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 no ID is given, ask the user which image to delete.

    line 21
  2. Very specific:

    If the user provides a raw ULID without the img_ prefix, prepend img_ automatically.

    line 22
  3. Distinctive:

    This is a destructive action: Before executing, tell the user which image ID will be deleted and ask for confirmation.

    line 27
  4. Very specific:

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

    line 31
  5. Very specific:

    If the user was deleting to free space, suggest running /stats to check updated usage

    line 58
  6. Distinctive:

    If the server returns a non-JSON response or an unexpected HTTP status, tell the user the API may be temporarily unavailable.

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Delete Image

Soft-delete an image from your Lab Nocturne Images account.

Invocation

/delete <image_id> — also triggered naturally (e.g. "delete image img_abc...", "remove that image", "clean up my old uploads").

Instructions

1. Resolve the image ID

  • The user provides an image ID as the argument (e.g. /delete img_01JXYZ...).
  • If no ID is given, ask the user which image to delete. Suggest using /files to find the ID.
  • If the user provides a raw ULID without the img_ prefix, prepend img_ automatically.
  • The ID should match the pattern img_ followed by a ULID (26 alphanumeric characters).

2. Confirm with the user

This is a destructive action. Before executing, tell the user which image ID will be deleted and ask for confirmation. Only proceed if the user confirms.

3. Authenticate

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

4. Delete the image

Run:

curl -s -w '\n%{http_code}' -X DELETE \
  -H "Authorization: Bearer <api_key>" \
  <base_url>/i/<image_id>

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

5. Handle the response

Success (HTTP 200) — the response body is:

{
  "success": true,
  "message": "File deleted successfully",
  "id": "img_..."
}

Present to the user:

  • Confirm the image was deleted successfully
  • Show the deleted image ID
  • If the user was deleting to free space, suggest running /stats to check updated usage

Error — see references/auth.md for common error codes. Additional delete-specific codes:

codeSuggested fix
file_not_foundThe image ID was not found. Use /files to list your images and find the correct ID

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.