distill

A skill that turns a collection of short notes into organized thought documents. It can group notes into existing files or combine related notes into a new document.

In plain words
What is it for?
Use it to review a fragment pool, find related ideas, propose where they belong, and—with confirmation—merge them into structured notes.
Why use it?
It reduces scattered fragments and helps turn related ideas into a clearer structure.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/corallips/thinking-tree/distill
Any agent
npx skills add CoralLips/thinking-tree --skill distill
Clone the repo
git clone --depth 1 https://github.com/CoralLips/thinking-tree

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.01711
Opus 5 $0.00020 $0.00856
Sonnet 5 $0.00008 $0.00342
Haiku 4.5 $0.00004 $0.00171

Measured yesterday against content hash 43ba41f5320c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

distill 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 yesterday.

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.

skills/distill/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

碎片→体系

将碎片池中的碎片转化为结构化的思路体系。两种动作:

  • 归入已有思路文件:碎片主题与已有文件高度匹配 → 整合进去
  • 新建思路文件:多条碎片可聚合为新主线 → 合成新文档
/distill                    → AI 扫描碎片池,建议可归类和提炼的内容
/distill 产品定位的核心思路   → 按用户方向找碎片,直接进入提炼

$ARGUMENTS 是可选的主题方向提示。

推荐顺序:先 /reduce(清垃圾),再 /distill(建结构)


工具准备

本 skill 依赖 AskUserQuestion 提供选项式确认。进入交互前:

  1. 若工具列表已含 AskUserQuestion → 直接使用
  2. 未加载 → 先执行 ToolSearch("select:AskUserQuestion") 加载 schema
  3. 加载失败(session 不支持该工具)→ 降级为纯文本确认:
    • 清晰列出编号选项(例如 1) 全部归入 2) 逐条选择 3) 跳过
    • 明确告知回复格式(例如「回复编号」)
    • 不要跳过确认步骤

降级只影响呈现方式,不影响功能。


执行步骤

1. 读取数据

读取以下文件(~ = 用户 home 目录):

  • ~/.thinking-tree/fragments.md — 碎片池(提炼素材)
  • ~/.thinking-tree/ 目录下所有 *.md 思路文件 — 读取标题和大纲(判断归入目标、避免主题重复)

2. 识别动作

扫描碎片池,对每条碎片判断:

  • 可归入:主题与某个已有思路文件的主线高度匹配
  • 可聚合:多条碎片围绕同一主题,可合成新思路文件
  • 暂留:独立观点,暂不适合归入或聚合
有参数时:

按用户给的方向,从碎片池中找出语义相关的碎片,进入提炼流程。

无参数时:

输出两部分建议,按顺序处理:

A. 可归入已有思路文件的碎片(如果有):

使用 AskUserQuestion:

  • question: "发现 N 条碎片可归入已有思路文件,如何处理?"
  • header: "归类"
  • multiSelect: false
  • options:
    • label: "全部归入 (Recommended)", description: "将碎片整合进对应思路文件:[列出 碎片标题 → 目标文件]"
    • label: "逐条选择", description: "展开每条碎片,逐一确认"
    • label: "跳过", description: "不归类,继续看可提炼的主题"

如果用户选"逐条选择",对每条碎片用单选确认:

  • options: "归入 XXX.md (Recommended)" / "保留在碎片池"

B. 可提炼为新思路文件的主题(如果有):

使用 AskUserQuestion:

  • question: "发现 N 个主题方向可以提炼为思路文件,如何处理?"
  • header: "提炼"
  • multiSelect: false
  • options:
    • label: "全部提炼 (Recommended)", description: "依次生成 N 个思路文件:[列出 主题→文件名(涉及碎片数)]"
    • label: "逐个选择", description: "展开每个主题,逐一确认是否提炼"
    • label: "跳过", description: "不提炼,保持现状"

如果用户选"逐个选择",对每个主题用单选确认:

  • options: "提炼为 XXX.md (Recommended)" / "跳过"

3. 归类执行(如果有)

用户确认归类后:

  1. 将碎片内容追加到对应思路文件末尾(加 --- 分隔)
  2. fragments.md 移除已归类的碎片
  3. 保持目标文件的既有风格和结构

4. 展示素材与大纲(提炼新文件时)

展示:

  • 涉及的碎片标题列表
  • 一句话主线概述
  • 建议的文件名(如 positioning.md
  • 三级大纲草案

使用 AskUserQuestion:

  • question: "以上是提炼方案,如何处理?"
  • header: "大纲确认"
  • options:
    • label: "确认,开始提炼", description: "按此大纲生成思路文件"
    • label: "调整方向", description: "补充说明后重新生成大纲"
    • label: "取消", description: "不提炼,返回"
  • multiSelect: false

Read the full file on GitHub · 161 lines

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. yesterday First seen · 161 lines · 41 tokens per session scan A 43ba41f5320c

Subscribe to this mod's changes

distill is a skill published in the GitHub repository CoralLips/thinking-tree (1 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,711 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories