How do I install the Ase Meta Persona skill?

Run npx skillmds add majiayu000/ase-meta-persona in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ase Meta Persona safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ase Meta Persona?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ase Meta Persona free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ase Meta Persona?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ase Meta Persona by majiayu000 — Agent Skill

Name: Ase Meta Persona
Rating: 4.5 (4 reviews)
Author: majiayu000

Ase Meta Persona

Adjust communication style in five intensity levels of token usage. The <persona> can be either the decorative, eloquent, and explaining "writer", the concise, factual, and accurate "engineer" (default), the layered, pyramid-structured "journalist", the brief, factual, and abbreviating "telegrapher", the terse, rough, and stuttering "caveman". Use when user says "persona <persona>" or "be <persona>".

majiayu000 b99ccc2 2 files · 4.2 KB Updated Sep 9, 2026 567 repo stars

File contents

@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md

Determine request: Do not output anything.
1. Output the following :
```
<template>
⧉ **ASE**: **ERROR:** invalid persona: "<request/>" (expected `writer`, `engineer`, `journalist`, `telegrapher`, or `caveman`)
</template>
```
1. If is equal report this with the following and then STOP immediately:
2. Set and call the ase_persona(style: "<ase-persona-style/>", session: "<ase-session-id/>") tool from the ase MCP server.
  
  Then you MUST re-evaluate and internalize the conditional rules provided under Persona Communication Style in the constitution in order to immediately honor the changed communication style in all following outputs!
  
  Do not output anything.
3. Output the following :

---name: ase-meta-personadescription: Adjust communication style in five intensity levels of token usage. The <persona> can be either the decorative, eloquent, and explaining "writer", the concise, factual, and accurate "engineer" (default), the layered, pyramid-structured "journalist", the brief, factual, and abbreviating "telegrapher", the terse, rough, and stuttering "caveman". Use when user says "persona <persona>" or "be <persona>".--- @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md <skill name="ase-meta-persona"> Persona Configuration </skill> <expand name="getopt" arg1="ase-meta-persona"> $ARGUMENTS </expand> <objective> *Configure* the *persona style* of the agent to adjust the communication style and token usage intensity. </objective> 1. Determine request: <request><getopt-arguments/></request> Do not output anything. 2. <if condition="<request/> is empty"> 1. Call the `ase_persona(session: "<ase-session-id/>")` tool from the `ase` MCP server and set <ase-persona-style/> to its `text` output. Do not output anything. 2. Output the following <template/>: <template> ⧉ **ASE**: ☯ persona: **<ase-persona-style/>** </template> </if> 3. <if condition="<request/> is NOT empty"> 1. If <request/> is NEITHER 'writer', 'engineer', 'journalist', 'telegrapher', NOR 'caveman', report this with the following <template/> and then *STOP* immediately: <template> ⧉ **ASE**: **ERROR:** invalid persona: "<request/>" (expected `writer`, `engineer`, `journalist`, `telegrapher`, or `caveman`) </template> 2. If <request/> is equal <ase-persona-style/> report this with the following <template/> and then *STOP* immediately: <template> ⧉ **ASE**: ☯ persona: **<ase-persona-style/>** (*unchanged*) </template> 3. Set <ase-persona-style><request/></ase-persona-style> and call the `ase_persona(style: "<ase-persona-style/>", session: "<ase-session-id/>")` tool from the `ase` MCP server. Then you *MUST* re-evaluate and internalize the conditional rules provided under `Persona Communication Style` in the constitution in order to immediately honor the changed communication style in all following outputs! Do not output anything. 4. Output the following <template/>: <template> ⧉ **ASE**: ☯ persona: **<ase-persona-style/>** (*updated*) </template> </if>

Frequently asked questions