capability-distill

capability-distill is a skill for Codex from majiayu000/spellbook. It costs 136 tokens per session (2,704 once invoked), scanned A, original, MIT.

A workflow for extracting specific decision rules from approved expert-model interviews or real task records and packaging them for skill review.

In plain words
What is it for?
It is for creating auditable judgment packets, checking evidence and overlap with existing skills, and feeding evaluation problems into later revisions.
Why use it?
It separates useful judgment from ordinary procedures while controlling which private material may be read or shared.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Codex.

Good fit It is for creating auditable judgment packets, checking evidence and overlap with existing skills, and feeding evaluation problems into later revisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/spellbook/capability-distill
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 majiayu000/spellbook --skill capability-distill
Clone the repo
git clone --depth 1 https://github.com/majiayu000/spellbook

Made for: Codex.

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 capability-distill

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/spellbook/capability-distill/github.svg)](https://agentmods.dev/skills/majiayu000/spellbook/capability-distill)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/spellbook/capability-distill"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/capability-distill/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 capability-distill

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/spellbook/capability-distill"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/capability-distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,704 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00136 $0.02704
Opus 5 $0.00068 $0.01352
Sonnet 5 $0.00027 $0.00541
Haiku 4.5 $0.00014 $0.00270

Measured 10d ago against content hash 661da634f632, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

capability-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 10d 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.

skills/capability-distill/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capability Distill

把“为什么在两个合理选项中选择其中一个”提取成证据支持的判断规则。不要把操作步骤、通用建议或原始会话内容换个格式包装成 skill。

与现有技能的边界

  • capability-distill:选择获准证据、还原决策事件、提取判断规则、输出 judgment packet。
  • skill-audit:判断这些规则是否值得成为 skill、归属哪个现有 skill、是否重复以及如何分层。
  • skill-creator:创建或修改具体的 SKILL.md、设计 with-skill/baseline eval、迭代和验证触发描述。
  • skill-lifeguard:当产物属于高影响工作流时补可靠性契约和漂移修复闭环。

不要在本 skill 中复制后三者的完整写作、注册或评测流程。目标是提供它们可消费的高信号输入。

Operating Contract

  • Direct actions: 使用当前对话和用户明确批准的本地材料;先读元数据再读内容;生成脱敏的 judgment packet;运行本地只读检查。
  • Escalate before: 读取未获准的会话历史、memory、home 目录或其他仓库;把任何轨迹内容发送给外部模型;覆盖已有 skill;写入共享仓库;发布或安装产物。
  • Evidence-backed pushback: 判断密度低、证据不足或已有 skill 完整覆盖时,给出具体重叠项并建议不蒸馏或只更新原 skill。
  • Feedback loop: 把 eval 中的“未生效 / 机械化 / 误触发”连同对应 rule_id 回写到下一轮 judgment packet,而不是只改措辞。

0. 建立数据边界

在读取额外材料前记录以下字段:

source_scope:
  approved_roots: []
  approved_artifact_types: []
  external_model_destination:
  raw_content_authorized: false
  output_path:

当前对话和用户本次明确附带的文件可直接使用。其他路径、历史日志和 memory 不因“可能有帮助”而自动进入范围;缺少批准时先询问并暂停对应读取。

执行以下数据纪律:

  • 不假定 ~/.claude~/.codex 或任何固定运行时路径存在。使用用户给出的路径、当前工作区和当前运行时可用的搜索工具。
  • 先查看文件名、时间、提交主题等元数据,只对候选决策事件读取最小必要片段。
  • 不把 token、密钥、cookie、个人身份信息、客户数据、私有源码或完整 prompt/response 写入 packet 或 eval。
  • 如需外部强模型,只发送经用户批准的脱敏场景摘要;没有目标模型和数据发送授权就标记阻塞,不假装完成窗口蒸馏。
  • provenance 只写可验证的来源标签和日期。模型名、版本或作者未知时留空,不猜测。

1. 判断是否适合蒸馏

先区分对象:

  • 可由固定命令或 checklist 完成的是流程,交给 skill-audit / skill-creator,不做判断蒸馏。
  • 需要根据上下文在多个合理选项间权衡,并且存在切换、停止或上抛信号的,才是候选判断。
  • 只包含“谨慎、验证充分、保持简洁”等通用态度时,直接判为低判断密度。

对候选场景记录 judgment_densityevidence_strengthexisting_coverage(high / medium / low)。只保留判断密度高、证据至少中等且现有覆盖不完整的场景。

2. 还原决策事件

从获准证据中提取事件摘要,而不是复制原文。每个事件至少包含:

decision_event:
  evidence_ref:
  context:
  viable_options: []
  chosen_option:
  observed_signal:
  outcome:
  counterfactual:
  redactions_applied: []

evidence_ref 使用本地、非敏感的定位信息,例如仓库相对路径和 commit SHA;不要把原始聊天文本塞进该字段。没有 outcome 的事件只能作为假设,不能升级为高置信规则。

3. 写作前重叠审计

在写任何 judgment_rule 前,先在 source_scope 获准的 roots 或已附 inventory 内搜索现有 rules、skills、registry 和相近 owner;先查索引和元数据,再读最可能相关的最小片段。没有获准的 owner 根目录或清单时,先请求范围并暂停规则起草,不能把“未提供”当作“无覆盖”。

Read the full file on GitHub · 173 lines

Files

What ships with it

5 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. 10d ago First seen · 173 lines · 136 tokens per session scan A 661da634f632

Subscribe to this mod's changes

capability-distill is a skill published in the GitHub repository majiayu000/spellbook (277 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 2,704 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

pneuma-session

Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.

pandazki/pneuma-skills · 127 tokens

session-handoff

Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…

will-pagane/claude-superdev-harness · 91 tokens

aenv

Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…

Blevene/aenv · 176 tokens

cao-session-management

Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.

awslabs/cli-agent-orchestrator · 49 tokens

adhoc-flow

Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.

griddynamics/rosetta · 22 tokens

session-handoff-resume

Skill to save ultra-compact project checkpoints and seamlessly resume work across accounts or new chat sessions with minimum token consumption / Skill untuk menyimpan checkpoint proyek yang super ringkas dan melanjutkan pekerjaan secara efisien saat ganti akun/sesi tanpa boros token.

roedyrustam/vibes-plug · 59 tokens