distill-meta

distill-meta is a skill for Claude Code from XRenSiu/claude-code-forge. It costs 231 tokens per session (6,456 once invoked), scanned A, original, MIT.

A workflow coordinator that builds a self-contained persona skill from source material about a person, domain, or set of rules. A persona skill is a reusable instruction package describing how an assistant should act or reason.

In plain words
What is it for?
It is for turning chats, public sources, or other documents into a portable persona package with memories, reasoning patterns, style, and decision guidance.
Why use it?
It organizes collection, extraction, conflict handling, validation, and later correction instead of relying on one unstructured prompt.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Part of the persona-distill plugin — 5 skills, 16 agents shipped together

Good fit It is for turning chats, public sources, or other documents into a portable persona package with memories, reasoning patterns, style, and decision guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xrensiu/claude-code-forge/distill-meta
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add XRenSiu/claude-code-forge --skill distill-meta
Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Made for: Claude Code.

Or install persona-distill, the plugin that ships this one along with the rest of its 5 skills, 16 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for distill-meta

README.md
[![agentmods](https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/distill-meta/github.svg)](https://agentmods.dev/skills/xrensiu/claude-code-forge/distill-meta)
Your own site
<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/distill-meta"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/distill-meta/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for distill-meta

Your own site · 80×15
<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/distill-meta"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/distill-meta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 231 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00231 $0.06456
Opus 5.5 $0.00092 $0.02582
Sonnet 5.5 $0.00046 $0.01291
Haiku 4.5 $0.00023 $0.00646

Measured 1mo ago against content hash a8d9e9f31a60, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

distill-meta scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/persona-distill/skills/distill-meta/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

distill-meta

把一个人(或领域/规则体系)蒸馏成一个自包含的 persona skill。

Announce at start: "I'm using the distill-meta skill to orchestrate an 8-phase persona distillation pipeline and produce a self-contained persona skill."

前置条件: 深度蒸馏会并行 spawn 多个 sub-agent(语料侦查、维度提取、张力发现、迭代深化、验证)。 如果启用 Agent Teams 实验功能(CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1), Phase 1/Phase 2/Phase 2.5 会自动切换到并行团队模式。

Overview / 概览

distill-meta 的产物是一个独立的 persona skill——它可以被复制、移动、分发,不依赖 distill-meta 自身即可在任何 Claude Code 环境中运行。

与"一次性蒸馏 prompt"相比,distill-meta 的差异化:

维度 单次蒸馏 prompt distill-meta
对象覆盖 通常只针对名人/同事一种 9 种 schema(self/collaborator/mentor/loved-one/friend/public-mirror/public-domain/topic/executor)
结构 固定模板 参数化组件(19 个组件按 schema 拼装)
深度 一次产出 迭代深化(最多 3 轮扫描遗漏维度)
执行层 描述即终点 CDM 执行画像(Phase 3.7 把描述编译为 8 类 Macrocognition 指令性条款)
质量保证 无 dog-food 验证(调用 persona-judge,三项测试 + 12 维 rubric + 密度评分)
矛盾处理 抹平 保留并存档到 conflicts.md
进化 无 通过对话修正层持续校正

核心原则

  1. Self-Contained 产物(借鉴 nuwa-skill):每个生成的 persona skill 都是可复制/可移动/可独立运行的独立单元。产出目录没有对 distill-meta 的任何依赖。
  2. Progressive Disclosure:这份 SKILL.md 只做入口决策和编排;深层内容在 references/ 和 agents/ 中,按需加载。
  3. No Interrogate:用户只说"蒸馏张三"时自动兜底(见 §Invocation)。
  4. Preserve Tensions:人的内在矛盾是信号不是噪音,禁止抹平。

8-Phase Workflow(执行流程)

完整流程源自 PRD §3.2,覆盖意图澄清 → schema 决策 → 语料采集 → 维度提取 → 迭代深化 → 组装 → 冲突检测 → 执行画像提取 → 质量验证 → 交付。

Phase 0    意图澄清             → 对象 + 目的 + 现有 skill 检测 + consent-attestation 闸门(real-person/composite)
Phase 0.5  Schema 决策           → 9 选 1 + 组件选定 + 立即建目录(强制 self-contained)
Phase 1    语料采集             → 私有(distill-collector)+ 公开(并行 agent 调研)
Phase 1.5  Research Review      → 覆盖率表格 + 缺口标注 + 用户确认 + corpus_access_declared 与 schema_type 交叉校验
Phase 2    维度提取             → 并行按组件提取 + 三重验证 + 七轴 DNA + 张力识别 + 密度分类
Phase 2.5  迭代深化             → 最多 3 轮多轮扫描 + Jaccard 收敛 + 高置信度自动回填
Phase 3    Skill 组装           → SKILL.md + manifest.json + 组件文件(hard-rules 嵌入 Untrusted-Corpus Discipline)
Phase 3.5  冲突检测             → 自动 surface 组件/语料/时期间的事实性矛盾到 conflicts.md(不 resolve)
Phase 3.7  执行画像提取(v0.3) → CDM 4-sweep:从 knowledge/ 事件反推 8 类 Macrocognition 指令条款
Phase 3.8  自包含+指纹校验(新)→ self-containment-linter 6 项 + fingerprint-verifier,任一失败阻塞 Phase 4
Phase 4    质量验证             → 调用 persona-judge:三项测试 + 12 维 rubric + 密度评分
Phase 5    交付与后续           → 告知路径 + 触发词 + 进化方式(debate / router)

Read the full file on GitHub · 283 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 283 lines · 231 tokens per session scan A a8d9e9f31a60

Subscribe to this mod's changes

distill-meta is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 231 tokens to every session and 6,456 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens