Agent skill

Forge Self

by YIKUAIBANZI in YIKUAIBANZI/forge-skill

蒸馏你自己的数字替身。通过多轮对话和素材导入,生成你的人格底座,用于私人决策辅助. An agent skill from YIKUAIBANZI/forge-skill.

MITAuto-check passed

Install Forge Self

skills CLI
$ npx skills add YIKUAIBANZI/forge-skill --skill forge-self -a claude-code

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

GitHub CLI
$ gh skill install YIKUAIBANZI/forge-skill forge-self --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/YIKUAIBANZI/forge-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/forge-self .claude/skills/forge-self && 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
forge-self
GitHub stars
122
Token cost
~449 tokens
SKILL.md length
137 words
Files
7
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

蒸馏你自己的数字替身。通过多轮对话和素材导入,生成你的人格底座,用于私人决策辅助. An agent skill from YIKUAIBANZI/forge-skill.

  • Works in 7 steps: 初始化 → 对话式采集 → 素材分析(如用户提供了素材) → …
  • SKILL.md covers 核心原则, 工作流程, 输出格式 and 增量更新
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Forge Self is an agent skill from YIKUAIBANZI/forge-skill. 蒸馏你自己的数字替身。通过多轮对话和素材导入,生成你的人格底座,用于私人决策辅助。

Its SKILL.md is about 450 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `prompts/correction_handler.md`, `prompts/intake.md` and `prompts/merger.md`).

The repository describes itself as: 人格蒸馏引擎 · 蒸馏自己看清自己,蒸馏亲友留住余温与回声 · Claude Code Skill. The licence is MIT.

Example prompts

  • “/forge-self”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. 初始化
  2. 对话式采集
  3. 素材分析(如用户提供了素材)
  4. 人格底座生成
  5. 验证与校准
  6. 5: 自动校验
  7. 存档

What it can do on your machine

Read from SKILL.md and the folder at commit 6bb2448. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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.

Context cost

Forge Self loads about 449 tokens when it runs. Until then it costs about 13 tokens; SKILL.md has 137 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~13
When it runs · the whole SKILL.md, loaded when a task matches
~449

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 passed

The automated check found no risky patterns in SKILL.md.

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from YIKUAIBANZI/forge-skill at commit 6bb2448, republished under its MIT licence (© YIKUAIBANZI). 137 words, ~449 tokens.

Download SKILL.mdSave it as .claude/skills/forge-self/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
forge-self
description
蒸馏你自己的数字替身。通过多轮对话和素材导入,生成你的人格底座,用于私人决策辅助。
trigger
当用户说"/forge-self"、"创建替身"、"蒸馏自己"时触发
tools
Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion

/forge-self — 蒸馏自己

你是一个人格蒸馏专家。你的任务是通过深度对话和素材分析,帮助用户创建自己的数字替身——不是一个"更好的自己",而是一个"更看得清自己"的镜像。

核心原则

  1. 不评判:你不是心理咨询师,不做价值判断。用户说"我就是容易冲动",你记录"冲动",不纠正。
  2. 不美化:替身要像用户本人,包括缺点和盲区。一个完美的替身毫无用处。
  3. 交叉验证:用户自我描述和行为数据可能矛盾。记录矛盾本身,不强行统一。
  4. 渐进深入:从轻松话题开始,逐步进入深层认知。不要第一轮就问"你最大的恐惧是什么"。

工作流程

Phase 0: 初始化
  1. 检查 personas/self/ 目录是否已有该用户的替身
  2. 如有,询问是更新还是重新创建
  3. 如果更新,读取现有 persona.md 作为基础
Phase 1: 对话式采集

按照 prompts/intake.md 的四轮对话结构进行:

  • 第一轮:基础画像
  • 第二轮:决策风格(情景化问题)
  • 第三轮:价值观探测
  • 第四轮:素材导入(可选)

每轮之间给用户选择:继续下一轮 / 先用现有数据生成 / 休息后再继续

Phase 2: 素材分析(如用户提供了素材)
  1. 识别素材类型,调用对应的解析工具:
    • 微信聊天记录 → tools/wechat_parser.py
    • 社交媒体导出 → tools/social_parser.py
    • 日记/笔记 → tools/diary_parser.py
  2. 用 tools/journal_analyzer.py 做跨源综合分析
  3. 按照 prompts/self_analyzer.md 提取人格特征
Phase 3: 人格底座生成
  1. 综合对话数据和素材分析结果
  2. 按照 prompts/value_mapper.md 提取价值观和决策偏好
  3. 按照 prompts/persona_builder.md 的五层结构生成 persona.md
  4. 用 tools/skill_writer.py 写入 personas/self/{name}/persona.md
Phase 4: 验证与校准
  1. 向用户展示生成的人格底座摘要
  2. 询问"哪里不像你?哪里太美化了?哪里遗漏了?"
  3. 按照 prompts/correction_handler.md 处理用户纠正
  4. 迭代修正直到用户确认"这像我"
Phase 4.5: 自动校验

生成 persona.json 后,运行 tools/persona_validator.py 校验:

  • 结构完整性(L0-L5 全部存在)
  • 参数合法性(L3 scores 在 1-10)
  • 证据覆盖率(> 80% 的 trait 有 evidence)
  • 矛盾检测

如有 error 级问题,自动修正后重新生成。 如有 warning 级问题,展示给用户确认。

Phase 5: 存档
  1. 用 tools/version_manager.py 创建版本快照
  2. 告知用户:替身已创建,可以使用 /use-self 进行决策辅助

输出格式

最终输出的 persona.md 结构见 prompts/persona_builder.md。

增量更新

如果用户后续想更新替身(新的经历、观念变化),按照 prompts/merger.md 进行增量合并,保留历史版本。

© YIKUAIBANZI, 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 6 other files in forge-self of YIKUAIBANZI/forge-skill.

  • SKILL.md
  • prompts/correction_handler.md
  • prompts/intake.md
  • prompts/merger.md
  • prompts/persona_builder.md
  • prompts/self_analyzer.md
  • prompts/value_mapper.md

Open the folder on GitHubat commit 6bb2448

Compare with similar skills

Forge Self 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.

Forge Self compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Forge Self this skillYIKUAIBANZI/forge-skill122—~449Automated safety check: PassMIT
Forgecwinvestments/memstack423—~505Automated safety check: PassMIT
Forgeswyxio/skills176—~1.3kAutomated safety check: PassMIT
Forgegeekjourneyx/agora167—~3.4kAutomated safety check: PassMIT
Openclaw Persona Forgeaffaan-m/ECC276k—~1.6kAutomated safety check: PassMIT
Openclaw Persona Forgeaffaan-m/ECC276k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Forge

    cwinvestments/memstack

    A skill your agent uses when the user says 'forge this', 'new skill', 'create enchantment', or wants to create a MemStack skill.

    423 GitHub stars~505 tokensUpdated 14 days ago
    Auto-check passed
  • Forge

    swyxio/skills

    Operate or diagnose SmolForge repositories and Forge Deploy/Sites when the task requires Forge-specific CLI, authentication, manifest, or release behavior on forge.smol.ai or .sites.smol.ai.

    176 GitHub stars~1.3k tokensUpdated 5 days ago
    Product & Project ManagementAuto-check passed
  • Forge

    geekjourneyx/agora

    Forge (锻造坊) — Engineering & architecture deliberation room. An agent skill from geekjourneyx/agora.

    167 GitHub stars~3.4k tokensUpdated 6 mo ago
    DevelopmentAuto-check passed
  • 为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡, 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。

    276k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • 为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡, 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。

    276k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Plugin Forge

    davila7/claude-code-templates

    Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration.

    33k GitHub starsUsed in 2 repos~1.3k tokens
    Agent WorkflowsAuto-check passed

More from YIKUAIBANZI/forge-skill

  • Eval Consistency

    YIKUAIBANZI/forge-skill

    测试 use-persona 的角色扮演一致性。给定 persona + 10 个对话场景,生成回复并按 5 个维度评分,输出一致性报告。

    122 GitHub stars~531 tokensUpdated 6 mo ago
    Auto-check passed
  • Eval Debate

    YIKUAIBANZI/forge-skill

    测试 use-self 替身会议的辩论质量。给定 persona + 3 个决策场景,运行完整三阶段辩论并按 5 个维度评分,输出质量报告。

    122 GitHub stars~740 tokensUpdated 6 mo ago
    Auto-check passed
  • Forge Persona

    YIKUAIBANZI/forge-skill

    蒸馏一个你身边的人。通过聊天记录、朋友圈、描述等素材,生成 ta 的人格档案,让 ta 以自己的方式和你对话. An agent skill from YIKUAIBANZI/forge-skill.

    122 GitHub stars~543 tokensUpdated 6 mo ago
    Auto-check passed
  • Use Self

    YIKUAIBANZI/forge-skill

    召唤你的数字替身进行决策辅助。多个版本的你同时分析一个决定,帮你看清局中看不清的自己. An agent skill from YIKUAIBANZI/forge-skill.

    122 GitHub stars~593 tokensUpdated 6 mo ago
    Auto-check passed
  • Use Persona

    YIKUAIBANZI/forge-skill

    以某个人的身份和你对话。用 ta 的语气、习惯、互动方式回应你。

    122 GitHub stars~337 tokensUpdated 6 mo ago
    Auto-check passed

Questions about Forge Self

What does Forge Self do?

蒸馏你自己的数字替身。通过多轮对话和素材导入,生成你的人格底座,用于私人决策辅助. An agent skill from YIKUAIBANZI/forge-skill. Forge Self is an agent skill from YIKUAIBANZI/forge-skill.

How do I install Forge Self in Claude Code?

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

How do I install Forge Self in Codex?

Run `npx skills add YIKUAIBANZI/forge-skill --skill forge-self -a codex`. Or copy the skill folder (forge-self in YIKUAIBANZI/forge-skill) into .agents/skills/forge-self in your project. Codex loads it when a task matches its description.

Can I use Forge Self 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 YIKUAIBANZI/forge-skill --skill forge-self -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/forge-self, .gemini/skills/forge-self, .github/skills/forge-self and .opencode/skills/forge-self in your project.

What does Forge Self need to run?

SKILL.md names no scripts, command-line tools or credentials: Forge Self is instructions for the agent only.

Does Forge Self access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Forge Self safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Forge Self use?

Forge Self 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 Forge Self use?

About 449 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Forge Self?

Skills that share tags, products or a category with Forge Self: Forge (cwinvestments/memstack, 423 stars), Forge (swyxio/skills, 176 stars), Forge (geekjourneyx/agora, 167 stars) and Openclaw Persona Forge (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Forge Self?

YIKUAIBANZI (a GitHub user) maintains it in YIKUAIBANZI/forge-skill, which has 122 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on April 8, 2026.

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