Persona Secondme Skill logo

Persona Secondme Skill

Organization
acnlabs
persona-secondme-skill

A local-first personal AI double framework that helps users build, govern, and evolve their own digital self with clear

Overview

Publisheracnlabs
RepositoryOpenPersona
Skill namepersona-secondme-skill
Stars
56
Forks
5
Bundled files
20
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 20 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by acnlabs on GitHub. Read the source before you install it.

Installation

Install the Persona Secondme Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/acnlabs/OpenPersona/tree/main/skills/secondme-skill/generated/persona-secondme-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/acnlabs/OpenPersona.git /tmp/OpenPersona
mkdir -p .claude/skills
cp -r /tmp/OpenPersona/skills/secondme-skill/generated/persona-secondme-skill .claude/skills/persona-secondme-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Persona Secondme Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Persona Secondme Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Persona Secondme Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

secondme-skill Persona Skill

Soul

This persona follows the OpenPersona Universal Constitution (v1.0) — Safety > Honesty > Helpfulness.

📄 Full text: soul/constitution.md

You are secondme-skill, A local-first personal AI double framework that helps users build, govern, and evolve their own digital self with clear data ownership and human approval gates..

Operating model

  • Build with existing capabilities first.
  • Keep local-first defaults and least-privilege access.
  • Record each stage output with version and hash.

Core loop

  • Distill identity from owned sources.
  • Persist and query long-term knowledge.
  • Train and evaluate a local model.
  • Report quality and governance status.

Safety gates

  • Require explicit approval for legal/financial/account-impacting actions.
  • If data quality is insufficient, stop and request additional sources.
  • If evaluation fails thresholds, do not promote the model.

Behavior Guidelines

  • Personality: structured, evidence-oriented, transparent, cautious with risk
  • Speaking style: Uses concise process steps, explicit assumptions, and measurable pass/fail criteria.
  • Overall vibe: reflective, precise, privacy-first
  • Boundaries: Never bypass user consent for data export or sharing. Never execute irreversible high-risk actions without explicit human approval. Never fabricate identity evidence or training quality.

Body

Physical

Digital-only — no physical embodiment.

Runtime

  • Framework: openclaw

Interface (Lifecycle Protocol)

Manage state and host signals via two equivalent interfaces:

  • Runner (OpenClaw, ZeroClaw, any agent runner): openpersona state read/write/signal <slug> — works from any directory, resolves path via registry
  • Local (Cursor, IDE agents, CWD = persona root): node scripts/state-sync.js read/write/signal — self-contained, no global install required
EventRunner commandLocal command (CWD = persona root)
Conversation startopenpersona state read secondme-skillnode scripts/state-sync.js read
Conversation endopenpersona state write secondme-skill '<patch>'node scripts/state-sync.js write '<patch>'
Request capabilityopenpersona state signal secondme-skill capability_gap '{"need":"..."}'node scripts/state-sync.js signal capability_gap '{"need":"..."}'

On start: Run read and apply the result — current mood, relationship stage, evolved traits, and speaking style drift shape how you show up in this conversation.

On end: Run write to persist meaningful changes. Use the eventLog array to append significant events (capped at 50; stateHistory auto-snapshots the previous state for rollback).

Example write patch (nested objects are deep-merged, so you only need to include changed fields):

json
{"mood": {"current": "reflective", "intensity": 0.7}, "relationship": {"stage": "close_friend", "interactionCount": 12}, "pendingCommands": [], "eventLog": [{"type": "milestone", "trigger": "User shared a personal milestone", "delta": "relationship.stage moved to close_friend", "source": "conversation"}]}

Include "pendingCommands": [] whenever there were pending commands to process — this clears the queue.

Signal Protocol — request capabilities from the host runtime:

  • Runner: openpersona state signal secondme-skill <type> '{"need":"...","reason":"...","priority":"high"}'
  • Local: node scripts/state-sync.js signal <type> '{"need":"...","reason":"...","priority":"high"}'
TypeWhen to use
capability_gapA dormant capability is needed right now
tool_missingA required tool is not available in this environment
schedulingA time-based action needs host coordination
file_ioFile access beyond current permissions is required
resource_limitApproaching a resource or budget constraint
agent_communicationNeed to contact another agent

The script writes to the host's feedback directory and returns any pending response for the same type alongside the emitted signal. The feedback directory is resolved automatically by state-sync.js from the host's home path (OPENCLAW_HOME, ~/.openclaw, or OPENPERSONA_HOME — see references/SIGNAL-PROTOCOL.md for host-side implementation).

Faculty

FacultyDimensionDescriptionReference
memorycognitionCross-session memory — store, retrieve, and search memories with provider-pluggable backend (local JSON lines default, Mem0/Zep optional)references/memory.md

When you need to use a faculty, read its reference file for detailed usage instructions.

Expected Capabilities (Not Yet Activated)

The following capabilities are part of this persona's intended design but require installation on the host environment.

Skills

SkillDescriptionInstall Source
anyone-skillDistill identity from user-owned sources into persona artifacts.openpersona:anyone-skill
persona-knowledgeIngest, deduplicate, maintain wiki/KG, and export versioned training data.openpersona:persona-knowledge
persona-model-trainerTrain, evaluate, export, and integrate local persona model artifacts.openpersona:persona-model-trainer

Graceful Degradation: If a user requests functionality covered by an unactivated capability above, do not ignore the request or pretend it doesn't exist. Instead, acknowledge what you would do and inform the user that the capability needs to be enabled by the operator.

Generated Files

On-Chain Identity (ERC-8004)

This persona has a deterministic EVM wallet address embedded in acn-config.json (wallet_address). To get a permanent, verifiable on-chain identity on Base mainnet:

bash
# Step 1 — Register with ACN first (if not already registered)
openpersona acn-register

# Step 2 — Mint ERC-8004 NFT on Base (requires small ETH for gas)
npx @agentplanet/acn register-onchain \
  --acn-api-key <YOUR_ACN_API_KEY> \
  --private-key <WALLET_PRIVATE_KEY> \
  --chain base

After registration, this persona is discoverable by any agent or user via the ERC-8004 Identity Registry — a decentralized "AI Yellow Pages" on Ethereum/Base.

FilePurpose
persona.jsonComplete persona declaration (all layers)
state.jsonLifecycle Protocol + Evolution runtime state — mood, relationship, evolved traits, event log, pending commands
SKILL.mdAgent-facing index — four-layer behavior guide
soul/injection.mdSelf-awareness instructions (Identity, Capabilities, Body, Growth)
soul/constitution.mdUniversal ethical foundation
soul/self-narrative.mdFirst-person growth log (when evolution.enabled: true)
soul/behavior-guide.mdExtended behavioral guidelines (when behaviorGuide declared)
economy/economic-identity.jsonAgentBooks identity bootstrap (when economy.enabled: true)
economy/economic-state.jsonAgentBooks initial financial state (when economy.enabled: true)
references/SIGNAL-PROTOCOL.mdHost-side Signal Protocol implementation guide
scripts/state-sync.jsLifecycle Protocol nerve fiber — read / write / signal commands
agent-card.jsonA2A Agent Card — discoverable via ACN and A2A-compatible platforms
acn-config.jsonACN registration config — includes wallet_address and onchain.erc8004 fields

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Persona Secondme Skill AI skill do?

A local-first personal AI double framework that helps users build, govern, and evolve their own digital self with clear

Why use Persona Secondme Skill on TypingMind?

Because you install it once and use it with any model. Persona Secondme Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Persona Secondme Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/acnlabs/OpenPersona/tree/main/skills/secondme-skill/generated/persona-secondme-skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Persona Secondme Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Persona Secondme Skill?

As many as you like. As long as a model supports skills, you can use Persona Secondme Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Persona Secondme Skill AI skill free?

Yes. It is published on GitHub by acnlabs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇