agentleFS
gdhub-iogdhub-io/character-forge-mcp/skills/character-prompts/SKILL.md

character-prompts

Skill1 starsChanged 4 days agoMITView on GitHub

Write generation prompts for a saved character-forge character, only the kinds the user asks for — concept (A-pose sheet), illustration (a key-art scene from their story), voice (TTS voice design + audition script), video (an image-to-video clip), song (Suno style + lyrics), theme (instrumental leitmotif for a looping background, as an ElevenLabs Music composition plan). Prompts only; no generator is called. Use when the user asks for a prompt, a voice, a video, a song, background music / a theme or an illustration of a character.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

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

    Call character_prompt with id and kind.

    line 14
  2. Very specific:

    Write the prompt in English, following the rules exactly: limits, required sections, no artist or actor names.

    line 15
  3. Distinctive:

    If the user asks for changes, rewrite and save again.

    line 19

≈ “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

Generation prompts for a character (on request only)

Requires the character-forge MCP server (tools named character_*).

Make ONLY the kinds the user asked for. Never produce the whole set unprompted, and never add this step to creating a character.

  1. Find the character id (character_list if unclear). If the user didn't say which kind, ask: concept, illustration, voice, video, song or theme.
  2. For each requested kind:
    • Call character_prompt with id and kind. It returns that target's rules and the card material to use.
    • Write the prompt in English, following the rules exactly: limits, required sections, no artist or actor names. Use only facts from the card; the look must match the card's look section (marks with sides, signature item, palette).
    • Self-check against the rules, then call character_prompt_save with id, kind and the named sections.
  3. Show the user the finished prompt text, ready to copy, plus the saved file path. Explain anything in the user's language; keep the prompt itself in English.

If the user asks for changes, rewrite and save again; the file for that kind is overwritten.

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.