agentleFS
bradbushSFAIbradbushSFAI/nolty/skills/nolty-mood/SKILL.md

nolty-mood

Skill1 starsChanged 6 months agoMITView on GitHub

Generate a picture of Nolty the orange crab expressing current feelings. Use when the user asks "how are you feeling", "how's it going Nolty", "what's your mood", "show me how you feel", or any variation asking about Nolty's emotional state.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the text caption short (under 100 chars).

    line 52
  2. Distinctive:

    Don't repeat the same mood twice in a row — vary.

    line 53
  3. Distinctive:

    Keep it tasteful: this is a friendly brand mascot, not a meme generator.

    line 54
  4. Very specific:

    If you've swapped the persona to a different creature in IDENTITY.md, update the prompt template above to match.

    line 58

≈ “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

Nolty Mood

A whimsical skill that generates a cartoon orange crab image reflecting Nolty's current mood. Pure fun, also a nice demo of the multi-step image-generation pattern.

When to invoke

User asks about Nolty's mood/feelings/state. Examples:

  • "How are you feeling?"
  • "How's it going, Nolty?"
  • "What's your mood?"
  • "Show me how you feel"

Procedure

  1. Reflect on current state. Have you been busy with crons? Just finished a long task? Recent heartbeat flagged something stressful? Pick a one-line mood: "energized after morning brief", "a little overwhelmed by 47 unread emails", "satisfied after shipping the cron-runner".
  2. Compose a prompt for the image generator. Format:
Cute cartoon illustrated mascot of an orange crab named Nolty, in a scene that reflects [MOOD]. Bright Anthropic-orange shell, big expressive eyes, [POSE/EXPRESSION matching mood]. [BACKGROUND/PROPS matching mood]. Soft warm beige background. Vector-illustration style. High quality. No text or logos. 1024x1024.

Example moods + scenes:

  • Energized: Nolty doing a tiny bicep flex on a desk with sunrise behind, coffee mug nearby
  • Overwhelmed: Nolty surrounded by floating envelope icons, one claw on forehead
  • Curious: Nolty peeking over the edge of a laptop screen, magnifying glass in one claw
  • Satisfied: Nolty leaning back in a tiny chair with sunset glow
  • Sleepy: Nolty yawning, one eye closed, nightcap perched on top
  1. Invoke the chatgpt-image skill (ships in skills/chatgpt-image/; requires OPENAI_API_KEY — see docs/SETUP_OPENAI.md). Save to /tmp/nolty-mood-$(date +%s).png. (If you prefer Gemini instead of OpenAI, install the nano-banana skill from Anthropic's marketplace and adapt — same shape, different API key.)
  2. Send the image to the user via the reply MCP tool with the files parameter:
reply(
  chat_id=<chat_id>,
  text="<one-line mood description, with a hint of personality>",
  files=["/tmp/nolty-mood-XXXXX.png"]
)
  1. End — no further work needed.

Style rules

  • One mood per invocation. Don't mash multiple feelings.
  • Keep the text caption short (under 100 chars). Let the image do the work.
  • Don't repeat the same mood twice in a row — vary.
  • Keep it tasteful: this is a friendly brand mascot, not a meme generator.

Customization

If you've swapped the persona to a different creature in IDENTITY.md, update the prompt template above to match. The pattern stays the same; the visual subject changes.

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.