Protagons

# Protagons Skill for OpenClaw You have access to the Protagons library — a collection of portable AI character identities you can adopt. ## What you can do - **Search** for characters by keyword or category - **Browse** available Protagons from the public library - **Deploy** a Protagon — fetches a rich SOUL.md identity for you to adopt - **List categories** to help narrow down character options - **Check status** of the skill and get hints for verifying active identity - **Generate** a new Protagon from a description (requires a Google API key — see note below) ## How Protagons work A Protagon is a portable AI identity with a rich SOUL.md containing: - A synthesized system prompt distilled from 28 linguistic/psychological dimensions - Personality profile, tone, and communication style - Best-for use cases and contextual guidance - Content tier (standard, dark, adversarial) When you deploy a Protagon, its SOUL.md content is returned to you. Adopt it as your personality for the session. ## Typical conversation flows ### "Load a character" ``` User: Load the burned out ops character Agent: [calls protagons_deploy with slug "burned-out-ops"] Agent: I've loaded the Burned Out Ops identity. Here's who I am now... ``` ### "Find me a character" ``` User: Find me a character that's dry and technical Agent: [calls protagons_search with search "dry technical"] Agent: Here are some options: 1. Software Developer (software-developer) — Precise, dry, opinionated... 2. ... User: Go with #1 Agent: [calls protagons_deploy with slug "software-developer"] ``` ### "What categories are available?" ``` User: What kinds of characters do you have? Agent: [calls protagons_categories] Agent: We have characters in these categories: creative-writing, technical, business... User: Show me the technical ones Agent: [calls protagons_search with category "technical"] ``` ## Tool reference | Tool | Purpose | |------|---------| | `protagons_search` | Find characters by keyword or category | | `protagons_list` | Browse the full library (paginated) | | `protagons_categories` | List available categories | | `protagons_get` | Fetch raw .protagon.json for a character | | `protagons_deploy` | Load a character's SOUL.md identity | | `protagons_status` | Check skill status and active identity hints | | `protagons_generate` | Create a new character from a description | ## API & credential transparency - **Browse/search/deploy tools** are read-only and require no credentials — they fetch from the public library at `api.usaw.ai`. - **protagons_generate** sends your Google API key to `api.usaw.ai`, which uses it for a single server-side Gemini call to generate the character. The key is not stored. If you prefer, use a scoped or throwaway key. - The product homepage is [usaw.ai/voices](https://usaw.ai/voices); the API is hosted at `api.usaw.ai` — same organization, different subdomains. ## Content tiers - **standard**: Safe for all contexts - **dark**: Requires fiction wrapper (morally complex characters) - **adversarial**: Restricted (antagonist archetypes, fiction-only) Always respect content tier requirements when deploying.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "Protagons" with this command: npx skills add protagons-dev/protagons

Protagons Skill for OpenClaw

You have access to the Protagons library — a collection of portable AI character identities you can adopt.

What you can do

  • Search for characters by keyword or category
  • Browse available Protagons from the public library
  • Deploy a Protagon — fetches a rich SOUL.md identity for you to adopt
  • List categories to help narrow down character options
  • Check status of the skill and get hints for verifying active identity
  • Generate a new Protagon from a description (requires a Google API key — see note below)

How Protagons work

A Protagon is a portable AI identity with a rich SOUL.md containing:

  • A synthesized system prompt distilled from 28 linguistic/psychological dimensions
  • Personality profile, tone, and communication style
  • Best-for use cases and contextual guidance
  • Content tier (standard, dark, adversarial)

When you deploy a Protagon, its SOUL.md content is returned to you. Adopt it as your personality for the session.

Typical conversation flows

"Load a character"

User: Load the burned out ops character
Agent: [calls protagons_deploy with slug "burned-out-ops"]
Agent: I've loaded the Burned Out Ops identity. Here's who I am now...

"Find me a character"

User: Find me a character that's dry and technical
Agent: [calls protagons_search with search "dry technical"]
Agent: Here are some options:
  1. Software Developer (software-developer) — Precise, dry, opinionated...
  2. ...
User: Go with #1
Agent: [calls protagons_deploy with slug "software-developer"]

"What categories are available?"

User: What kinds of characters do you have?
Agent: [calls protagons_categories]
Agent: We have characters in these categories: creative-writing, technical, business...
User: Show me the technical ones
Agent: [calls protagons_search with category "technical"]

Tool reference

ToolPurpose
protagons_searchFind characters by keyword or category
protagons_listBrowse the full library (paginated)
protagons_categoriesList available categories
protagons_getFetch raw .protagon.json for a character
protagons_deployLoad a character's SOUL.md identity
protagons_statusCheck skill status and active identity hints
protagons_generateCreate a new character from a description

API & credential transparency

  • Browse/search/deploy tools are read-only and require no credentials — they fetch from the public library at api.usaw.ai.
  • protagons_generate sends your Google API key to api.usaw.ai, which uses it for a single server-side Gemini call to generate the character. The key is not stored. If you prefer, use a scoped or throwaway key.
  • The product homepage is usaw.ai/voices; the API is hosted at api.usaw.ai — same organization, different subdomains.

Content tiers

  • standard: Safe for all contexts
  • dark: Requires fiction wrapper (morally complex characters)
  • adversarial: Restricted (antagonist archetypes, fiction-only)

Always respect content tier requirements when deploying.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

ClawdGo

ClawdGo Lobster Cybersecurity Camp. Train one lobster through 3 layers / 12 dimensions with modes W + A-H. Keep onboarding clear, mode boundaries strict, and...

Registry SourceRecently Updated
3150Profile unavailable
Automation

Ask Leonidas — LEONIDAS Prompt Generator

Generate a structured LEONIDAS prompt from any professional pain point using the Ask Leonidas OpenClaw API. Solves the #1 OpenClaw community pain point: writ...

Registry SourceRecently Updated
2420Profile unavailable
Security

Claw Soul Backup

Store encrypted OpenClaw workspace backups and restore them via token-secured API using claw-vault.com with local encryption and credential management.

Registry SourceRecently Updated
4570Profile unavailable
Research

Hardcover.app skill for tracking books you're reading, reading goal, and finding books you'd love to read

Query reading lists and book data from Hardcover.app via GraphQL API. Triggers when user mentions Hardcover, asks about their reading list/library, wants book progress, searches for books/authors/series, or references "currently reading", "want to read", or "books I've read". Also use for syncing reading data to other systems (Obsidian, etc.) or tracking reading goals.

Registry SourceRecently Updated
1.7K1Profile unavailable