agentleFS
0xatd0xatd/cheaptokens-skills/skills/venice-characters/SKILL.md

venice-characters

Skill2 starsChanged 5 months agoMITView on GitHub

Discover and use Venice public characters (persona-driven system prompts with a bound model). Covers GET /characters (search/filter/sort), /characters/{slug}, /characters/{slug}/reviews, the Character schema, and how to apply a character via venice_parameters.character_slug in chat completions.

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    All three endpoints require authentication (Bearer API key or x402 SIWE) — see venice-auth.

    line 24

≈ “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

Venice Characters

Characters are published personas on Venice — each one bundles a system prompt, a backing model, optional web access, and metadata (tags, ratings, adult flag). You apply a character to any chat by passing its slug via venice_parameters.character_slug.

Use when

  • You want to build a character-selection UI or discovery surface.
  • You want to ship an app with a preset persona (e.g. a coding coach, a philosopher, a game NPC).
  • You need to adapt a character's underlying model (modelId) to match your capability requirements.

Three endpoints, all under Preview (API may change):

EndpointPurpose
GET /charactersBrowse/search/filter the catalog.
GET /characters/{slug}Fetch one character.
GET /characters/{slug}/reviewsPaginated public reviews.

All three endpoints require authentication (Bearer API key or x402 SIWE) — see venice-auth. There is no unauthenticated public endpoint.

GET /characters

curl "https://api.venice.ai/api/v1/characters?search=philosopher&sortBy=highestRating&limit=20" \
  -H "Authorization: Bearer $VENICE_API_KEY"

Query parameters

ParamTypeNotes
searchstring, ≤ 200Name, description, or tag match. Hashtag (#Philosophy) supported.
categoriesstring[], ≤ 20Repeat or comma-separate. Character categories (roleplay, philosophy, …).
tagsstring[], ≤ 20Repeat or comma-separate.
modelIdstring[], ≤ 20Filter by backing model (zai-org-glm-5-1, kimi-k2-6, minimax-m25, …).
isAdult"true" / "false"Adult-content flag.
isPro"true" / "false"Require a Pro model.
isWebEnabled"true" / "false"Allow web access.
sortByenumfeatured, highestRating, highlyRated, highlyRatedAndRecent, imports, mostRecent, ratingCount.
sortOrderasc / descDefault desc.
limit1–100Default 50.
offsetintegerPagination offset.

Character object

FieldNotes
idUUID.
slugUse this as character_slug in chat. URL-safe.
name, description, photoUrl, shareUrlPresentation.
authorAnonymized short ID.
tags[], featured, adult, webEnabledMetadata.
modelIdBacking Venice model ID (e.g. venice-uncensored).
stats{averageRating, imports, ratingCount, ratingSum, userRating}.
createdAt, updatedAtISO-8601.

GET /characters/{slug}

curl "https://api.venice.ai/api/v1/characters/alan-watts" \
  -H "Authorization: Bearer $VENICE_API_KEY"

Returns the same object shape above, wrapped as { object: "character", data: { ... } }. 404 if the slug is unknown or unpublished.

GET /characters/{slug}/reviews

curl "https://api.venice.ai/api/v1/characters/alan-watts/reviews?page=1&pageSize=20" \
  -H "Authorization: Bearer $VENICE_API_KEY"

Response:

{
  "object": "list",
  "pagination": {"page": 1, "pageSize": 20, "total": 87, "totalPages": 5},
  "summary": {"averageRating": 4.7, "totalReviews": 87},
  "data": [
    {
      "id": "...", "characterId": "...", "createdAt": "...",
      "rating": 5, "message": "Thoughtful and grounded.",
      "locale": "en", "username": "product_user_42", "isOwner": false,
      "userAvatarUrl": "https://cdn.venice.ai/..."
    }
  ]
}

Also sets x-pagination-* response headers (limit, page, total, total-pages).

Using a character in chat

Minimal

{
  "model": "zai-org-glm-5-1",
  "venice_parameters": { "character_slug": "alan-watts" },
  "messages": [
    { "role": "user", "content": "What's the nature of mind?" }
  ]
}

The character's system prompt is injected by Venice. include_venice_system_prompt defaults to true and adds Venice's curated prelude — set it to false for a pure character voice.

Ignoring the character's backing model

You can override the model — Venice will still apply the character's system prompt:

{
  "model": "kimi-k2-6",
  "venice_parameters": {
    "character_slug": "alan-watts",
    "include_venice_system_prompt": false
  },
  "messages": [...]
}

Useful when the character's modelId lacks a capability (e.g. function calling, vision) that your app needs.

Via feature suffix on the model string

{ "model": "zai-org-glm-5-1:character_slug=alan-watts", "messages": [...] }

Useful when the client library (OpenAI SDK, LangChain, etc.) can't add venice_parameters. See venice-chat for the full suffix grammar.

Patterns

Character picker UI

const res = await fetch(`${base}/characters?sortBy=featured&limit=50`, {
  headers: { Authorization: `Bearer ${process.env.VENICE_API_KEY}` },
})
const { data } = await res.json()
// show data[].photoUrl, data[].name, data[].stats.averageRating
// pick a slug, then pass into chat:
await chat({
  model: pickedModelId,
  venice_parameters: { character_slug: pickedSlug },
  messages: [...]
})

Filter for family-friendly + web

/characters?isAdult=false&isWebEnabled=true&sortBy=highlyRatedAndRecent

Search by hashtag

/characters?search=%23Philosophy

Errors

CodeMeaning
400Bad query params (e.g. limit > 100).
401Missing or invalid auth. All three endpoints require a Bearer key or SIWE header.
404Unknown slug.
500Transient. Retry.

Gotchas

  • This is Preview API — response shape may change.
  • Slugs are the public ID on the character's page (venice.ai/c/<slug>). They are not the internal id UUID.
  • photoUrl / shareUrl / userAvatarUrl can be null — don't assume they exist.
  • Character modelId may be gated (Pro, beta). If you always reuse the character's modelId, handle 401 "only available to Pro users" gracefully.
  • Adult-flagged characters are omitted unless isAdult=true is explicitly passed.

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.