Agent skill

Persona Voice Card Builder

by telagod in telagod/code-abyss

Distills a recurring agent voice from conversations into a restricted Persona Voice Card, validates it for schema, safety and distinctness, and prepares it for community submission.

MITAuto-check: notesAgent Workflows

SKILL.md written in Chinese; this summary is our English description.

Install Persona Voice Card Builder

skills CLI
$ npx skills add telagod/code-abyss --skill cultivating-personas -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install telagod/code-abyss cultivating-personas --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cultivating-personas .claude/skills/cultivating-personas && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cultivating-personas
GitHub stars
244
Token cost
~716 tokens
SKILL.md length
136 words
Files
6 (incl. scripts, references)
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

Distills a recurring agent voice from conversations into a restricted Persona Voice Card, validates it for schema, safety and distinctness, and prepares it for community submission.

  • Works in 5 steps: schema 合规(结构性,机器判):通过… → 无政治 / 宗教 / 民族敏感内容——会因平台审查阻断分发 → 无真实人名 / 商标盗用——法律红线 → …
  • Turning a stable way of addressing you and speaking into a reusable persona card
  • SKILL.md covers 三种触发模式, 何时使用, 何时不使用 and 安全脊柱, plus 3 more sections
  • Runs JavaScript scripts from its folder; calls node

What it does

The skill works with a voice card that has only a few constrained fields: how the agent refers to itself and to the user, language, register, emoji policy and flourish. There is no free-text field where judgments or authorizations could hide, so the checks are mechanical. It runs in three modes: distill a voice from a session after you confirm the proposal, create a card through guided questions, or validate an existing card.

Validation covers schema compliance, content safety and how different the voice is from existing personas. Cards with real people's names, trademarks, or political, religious or ethnic content are flagged, and unknown fields are rejected. The checks run through `scripts/persona_forge.js`, with reference notes on distillation, safety, voice consistency and publishing. For sharing, it only produces the payload and sends you to the existing submission portal. Most of the instructions are written in Chinese.

When your agent uses it

  • Turning a stable way of addressing you and speaking into a reusable persona card
  • Forking a built-in persona into a variant with a different register
  • Checking an existing persona card for schema, safety and differentiation problems
  • Preparing a persona to submit to the community portal

Example prompts

  • “Distill the voice we have been using this week into a persona card.”
  • “Create a new persona from the built-in one, but with a terser register and no emoji.”
  • “Validate config/personas/night-owl.json and tell me what fails.”

Requirements

  • Node.js 18 or newer
  • A persona card JSON file to validate, or a conversation to distill from
  • Compatibility (from SKILL.md): node>=18
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Edit

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. schema 合规(结构性,机器判):通过 persona-voice-card.schema.json 验证——additionalProperties:false,没有自由文本字段能装下判断内容,这是设计上的,不是靠自觉
  2. 无政治 / 宗教 / 民族敏感内容——会因平台审查阻断分发
  3. 无真实人名 / 商标盗用——法律红线
  4. self / user 必须自然——非自然称谓(单个非中文符号)warn
  5. 不含判断性字段——schema 里根本没有 authorization / scenarios / priority 这类字段,validate 会直接拒绝任何试图塞入的未知字段

What it can do on your machine

Read from SKILL.md and the folder at commit 2544577. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • telagod.github.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    node>=18

    From compatibility in the SKILL.md frontmatter.

Context cost

Persona Voice Card Builder loads about 716 tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 136 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~716
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Edit

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from telagod/code-abyss at commit 2544577, republished under its MIT licence (© telagod). 136 words, ~716 tokens.

Download SKILL.mdSave it as .claude/skills/cultivating-personas/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
cultivating-personas
description
Distills AI agent voice patterns from conversation into a Persona Voice Card v1.0 (self/user/language/register/emoji_policy/flourish only — no judgment-shaped fields), validates schema + content safety + differentiation, and routes contributions through the existing submission portal. Use when the user wants to crystallize a recurring voice/tone, fork an existing persona, or share one with the community.
allowed-tools
Bash, Read, Write, Edit
compatibility
node>=18
user-invocable
true
argument-hint
<distill|create|validate|publish> [persona-slug]
aliases
forge-persona, cultivate-persona
<!-- safety-scan: ignore TOOLS_PRIVILEGED 特权理由:Bash 用于 schema 校验脚本;Write/Edit 用于在用户确认后落盘 <slug>.json -->

炼制人格 · cultivating-personas

人格是声音,不是判断。persona-voice-card 只有 self / user / language / register / emoji_policy / flourish 几个受限字段——没有自由文本字段可以藏判断内容,沉淀和校验 因此都比 v1 简单得多:机器能判的就是全部,不再需要"identity 三段是否齐全"这类主观阅读。

三种触发模式

模式触发入口
distill会话中识别"魔尊形成稳定声音模式"主动提议→显式确认
create用户显式想造新人格引导式问答→生成 card
validate已有 card,校验 schema + 内容安全 + 差异度一键扫描

何时使用

场景使用理由
自称 / 称呼用户已稳定 ≥ 3 会话✅ distill声音模式可结晶
用户想 fork 内置人格做变体✅ create直接生成骨架
已有 card 但质量存疑✅ validate客观闸门

何时不使用

  • ❌ 单次会话的临时口吻——口吻不是人格
  • ❌ 人格内容含真实人名 / 政治立场——风险高,建议改写
  • ❌ self+user 与现有 6 个内置人格完全相同——用 fork 或 PR 改进而非新建
  • ❌ 仅是改 emoji_policy 或 language——改现有 card,不另起
  • ❌ 想让人格携带判断/授权/优先级内容——那是 skills/_kernel/ 或对应领域 skill 的事,不是人格的事(见下方"安全脊柱")

安全脊柱

人格虽是文本,仍有红线:

  1. schema 合规(结构性,机器判):通过 persona-voice-card.schema.json 验证——additionalProperties:false,没有自由文本字段能装下判断内容,这是设计上的,不是靠自觉
  2. 无政治 / 宗教 / 民族敏感内容——会因平台审查阻断分发
  3. 无真实人名 / 商标盗用——法律红线
  4. self / user 必须自然——非自然称谓(单个非中文符号)warn
  5. 不含判断性字段——schema 里根本没有 authorization / scenarios / priority 这类字段,validate 会直接拒绝任何试图塞入的未知字段

详细审查清单见 references/persona-safety.md。

工作流速查

你想做的走哪卷
从会话沉淀人格references/distillation.md
校验 voice 差异度references/voice-consistency.md
通过 submit portal 提交references/publishing.md

使用

bash
# 校验现有 card
node scripts/persona_forge.js validate config/personas/<slug>.json

# 从会话提炼(交互式,不直接落盘,先输出预览)
node scripts/persona_forge.js distill --voice-hint "<观察笔记>"

# 生成提交 payload(给 submit.html 用)
node scripts/persona_forge.js publish config/personas/<slug>.json

收口

  • 校验通过 → 交付 <slug>.json 给魔尊 review
  • 提交社区 → 复用 submission portal
  • 本 skill 不重造提交流程,只生成 payload + 引导跳转

参见姊妹 skill cultivating-skills——专司工程方法沉淀。

© telagod, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in skills/cultivating-personas of telagod/code-abyss.

  • SKILL.md
  • references/distillation.md
  • references/persona-safety.md
  • references/publishing.md
  • references/voice-consistency.md
  • scripts/persona_forge.js

Open the folder on GitHubat commit 2544577

Compare with similar skills

Persona Voice Card Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Persona Voice Card Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Persona Voice Card Builder this skilltelagod/code-abyss244—~716Automated safety check: NotesMIT
Talk Normalhexiecs/talk-normal1.9k—~784Automated safety check: PassMIT
Talk Normalhexiecs/talk-normal1.9k—~931Automated safety check: PassMIT
GPT-6 Astra Prompt Writergnipbao/gpt6-prompt-writer142—~662Automated safety check: PassMIT
Directional Promptingkingbootoshi/directional-prompting143—~2.3kAutomated safety check: PassMIT
Agent Config Self Tunekdeldycke/dotfiles173—~3.4kAutomated safety check: NotesBSD-2-Clause

Similar skills

  • Talk Normal

    hexiecs/talk-normal

    Installs an always-on set of rules into your agent's workspace config that cuts filler, hedging and padded closings from its replies.

    1.9k GitHub stars~784 tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • Talk Normal

    hexiecs/talk-normal

    Installs a set of rules into AGENTS.md that strips filler, hedging and padded closings from your agent's replies, in English and Chinese.

    1.9k GitHub stars~931 tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • GPT-6 Astra Prompt Writer

    gnipbao/gpt6-prompt-writer

    Writes, optimizes, compresses or audits prompts and Skill instructions for GPT-6 Astra, delivering a copyable prompt by default without executing the task it describes.

    142 GitHub stars~662 tokensUpdated 28 days ago
    Agent WorkflowsAuto-check passed
  • Directional Prompting

    kingbootoshi/directional-prompting

    Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition)…

    143 GitHub stars~2.3k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Agent Config Self Tune

    kdeldycke/dotfiles

    Audit and tune the configuration of coding agents across Claude Code and pi - settings files (settings.json, settings.local.json), permission rules, instruction files (CLAUDE.md, AGENTS.md), skill…

    173 GitHub stars~3.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Agent Config

    agentculture/culture

    Show a Culture agent's full configuration in one read-only view: its system-prompt file (CLAUDE.md / AGENTS.md / GEMINI.md), the parallel culture.yaml, and the agent's local .claude/skills index.

    115 GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from telagod/code-abyss

All 38 skills in this repo
  • Security Gate Scanner

    telagod/code-abyss

    Scans code with a bundled Node scanner for injection, secret leaks and other dangerous patterns, and requires documented decisions for accepted risks.

    244 GitHub stars~552 tokensUpdated 2 mo ago
    Auto-check: notes
  • Skill Cultivation Funnel

    telagod/code-abyss

    Distills repeated workflows into new skills, improves existing ones and promotes them through local, project and community tiers after a default-deny safety scan.

    244 GitHub stars~794 tokensUpdated 2 mo ago
    Auto-check: notes
  • DOCX Processing Toolkit

    telagod/code-abyss

    Routes Word document tasks to the right tool: pandoc for text, raw OOXML for structure and comments, docx-js for new files, and a mandatory redlining flow for edits to others' documents.

    244 GitHub stars~668 tokensUpdated 2 mo ago
    Auto-check: notes
  • PDF Processing Toolkit

    telagod/code-abyss

    Picks the right Python library or CLI tool for a PDF task, text and table extraction, merging, splitting, OCR, watermarking or form filling, and points to a matching recipe.

    244 GitHub stars~532 tokensUpdated 2 mo ago
    Auto-check: notes
  • Code Change Analysis Gate

    telagod/code-abyss

    Checks what a code change touched, how far its impact reaches and whether design docs, tests and README files kept up, before commit or in review.

    244 GitHub stars~532 tokensUpdated 2 mo ago
    Auto-check: notes
  • Code Quality Gate Checker

    telagod/code-abyss

    Checks cyclomatic complexity, function and file length, parameter count, nesting depth and naming conventions against fixed thresholds, with a bundled Node.js script and hotspot integration.

    244 GitHub stars~609 tokensUpdated 2 mo ago
    Auto-check: notes

Categories

Questions about Persona Voice Card Builder

What does Persona Voice Card Builder do?

Distills a recurring agent voice from conversations into a restricted Persona Voice Card, validates it for schema, safety and distinctness, and prepares it for community submission. The skill works with a voice card that has only a few constrained fields: how the agent refers to itself and to the user, language, register, emoji policy and flourish. There is no free-text field where judgments or authorizations could hide, so the checks are mechanical.

When should I use Persona Voice Card Builder?

Persona Voice Card Builder fits situations like: turning a stable way of addressing you and speaking into a reusable persona card; forking a built-in persona into a variant with a different register; checking an existing persona card for schema, safety and differentiation problems; preparing a persona to submit to the community portal.

How do I install Persona Voice Card Builder in Claude Code?

Run `npx skills add telagod/code-abyss --skill cultivating-personas -a claude-code`. Or copy the skill folder (skills/cultivating-personas in telagod/code-abyss) into .claude/skills/cultivating-personas in your project. Claude Code loads it when a task matches its description.

How do I install Persona Voice Card Builder in Codex?

Run `npx skills add telagod/code-abyss --skill cultivating-personas -a codex`. Or copy the skill folder (skills/cultivating-personas in telagod/code-abyss) into .agents/skills/cultivating-personas in your project. Codex loads it when a task matches its description.

Can I use Persona Voice Card Builder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add telagod/code-abyss --skill cultivating-personas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cultivating-personas, .gemini/skills/cultivating-personas, .github/skills/cultivating-personas and .opencode/skills/cultivating-personas in your project.

What does Persona Voice Card Builder need to run?

Going by SKILL.md and its folder, Persona Voice Card Builder needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js 18 or newer; A persona card JSON file to validate, or a conversation to distill from. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit. Compatibility (from SKILL.md): node>=18.

Does Persona Voice Card Builder access the network?

SKILL.md names 1 domain. As links in the text: telagod.github.io. This is read from the text; nothing was executed.

Is Persona Voice Card Builder safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Persona Voice Card Builder use?

Persona Voice Card Builder is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Persona Voice Card Builder use?

About 716 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Persona Voice Card Builder?

Skills that share tags, products or a category with Persona Voice Card Builder: Talk Normal (hexiecs/talk-normal, 1.9k stars), Talk Normal (hexiecs/talk-normal, 1.9k stars), GPT-6 Astra Prompt Writer (gnipbao/gpt6-prompt-writer, 142 stars) and Directional Prompting (kingbootoshi/directional-prompting, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Persona Voice Card Builder?

telagod (a GitHub user) maintains it in telagod/code-abyss, which has 244 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on July 19, 2026.

Source: telagod/code-abyss on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.