Publish Sign in

Xi-Kari Semantic Deduction Framework Agent Skill

Executes a rigorous 13-stage non-skippable structural inference pipeline featuring full-source validation, competitive mechanism analysis…

Install this skill Read the source first Free Written by xi-kari
Context cost
847.6k tokensestimated from the bundle; more than a 200k window holds
Bundle
198 of 447 fileshanded out here; the rest is at its source
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

依据作者自定义的完整结构推演框架，执行21卷全源阅读、证据核查、机制比较与一至三阶递归，形成明确可反驳的判断及完整分析、决策建议、制度草案、计划或评论。Use when 用户精确点名 Xi-Kari Skill、xi-kari skill、xi-kari-skill、$xi-kari-skill 或 /xi-kari-skill；不得被动触发。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

data science
Filed under

Analytics & Monitoring

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md12.5 kB · preview
--- name: xi-kari-skill ---
6# Xi-Kari Skill
7
8本文件是指挥层：只规定必须做什么、按什么顺序、细则在哪份文件。规则的完整定义都在必读文件里，执行时以那些文件为准，不要凭印象复述，也不要复制成第二套实现合同。
9
10理论权威为 source/跨尺度多圈层结构推演框架v9.0.docx 及通过校验的 references/source/v9.0/ 快照。软件为 4.0.0，运行合同为 v4。
11
12## 激活
13
14仅在用户精确点名后运行。不要由“深度”“最大算力”“完整分析”等近似表达推断激活，也不要用任何其他技能、框架或简化流程替代本 Skill。
15
16## 必读文件
17
18- 读取顺序、全源与全候选闭包：[runtime-read-map.md](references/runtime-read-map.md)
19- 源加载与降档规则：[worldview-loading.md](protocols/worldview-loading.md)
20- 面向用户的交付合同：[answer-contract.md](references/answer-contract.md)
21- 外部材料与来源质量：[retrieval-policy.md](references/retrieval-policy.md)、[source-quality-policy.md](references/source-quality-policy.md)
22- Windows/PowerShell 宿主命令卡：[host-adapter-powershell.md](references/host-adapter-powershell.md)
23- 各阶段执行细则：protocols/；活动结构字段与严格拒绝条件：schemas/xk-v4-*.schema.json 及其明确引用的共享 schema，不能按文件名前缀推断兼容性
24- 概念阅读材料：references/ontology/v9.0/cards/、references/ontology/v9.0/bundles/、references/learning-packs/v9.0/；领域入口为 references/domains/index.json，正文为 references/learning-packs/domains/
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md212 words
Files198
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈50
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
847,575
on trigger
The instruction body and 197 supporting files, read only when the skill fires.
4.2×
a 200k window
It does not fit in the window: loaded whole, it would need more room than the model has.
050k100k150k200k context window

847.6k tokens, estimated from the bundle at four bytes to the token — more than the whole window, so it cannot all be held at once: the model reads SKILL.md when the skill fires and the other files only as the instructions call for them. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

The download carries 198 of the 447 files in its source folder; the list here names 198 files, 3961.0 kB on disk. Mostly text — the instructions the model reads — with 43 scripts in it that your client would run only if the instructions tell it to. The other 249 are not in the download, nor are at least 4 files of types a skill download does not carry — the first 100 are listed after these, with why.

  • SKILL.md12.5 kB
  • AGENTS.md3.8 kB
  • CONTRIBUTING.md2.0 kB
  • DESIGN.md11.8 kB
  • LICENSE1.1 kB
  • pyproject.toml0.3 kB
  • README.md10.5 kB

Not in the download

The first 100 are named here, those the skill reads first. Too big is over our 2 MB file limit, not carried is a type a skill download does not hold and over the limit is past 200 files or 4 MB a skill. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take them from its source.

  • docs/assets/hero-landscape.jpgread · not carried
  • source/跨尺度多圈层结构推演框架v8.3.docxread · not carried
  • scripts/xi_kari_runtime/contracts.pyread · over the limit
  • scripts/xi_kari_runtime/execution.pyread · over the limit
  • scripts/xi_kari_runtime/materialization.pyread · over the limit
  • references/ontology/bundles/core-human-empirical-instance.mdread · over the limit
  • references/ontology/bundles/human-variable-interface-complete.mdread · over the limit
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 43 scripts beside the text, so the download is 198 files — not the whole of its source: at least 253 files are left out, and the skill reads 25 of them. The first 100 are listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Xi-Kari Semantic Deduction Framework · 847.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/xi-kari-semantic-deduction-framework/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/xi-kari-semantic-deduction-framework" ] && { [ ! -e .claude/skills/xi-kari-semantic-deduction-framework ] || { mv .claude/skills/xi-kari-semantic-deduction-framework "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/xi-kari-semantic-deduction-framework" .claude/skills/ && echo "Installed .claude/skills/xi-kari-semantic-deduction-framework"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add xi-kari/xi-kari-semantic-deduction-framework

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/xi-kari-semantic-deduction-framework/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/xi-kari-semantic-deduction-framework/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/xi-kari-semantic-deduction-framework" ] && { [ ! -e ~/.claude/skills/xi-kari-semantic-deduction-framework ] || { mv ~/.claude/skills/xi-kari-semantic-deduction-framework "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/xi-kari-semantic-deduction-framework" ~/.claude/skills/ && echo "Installed ~/.claude/skills/xi-kari-semantic-deduction-framework" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/xi-kari-semantic-deduction-framework/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as xi-kari-skill in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, xi-kari-semantic-deduction-framework. Not in this download: at least 253 files of its source, 25 of them read by its SKILL.md or scripts (the list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencexi-kari/xi-kari-semantic-deduction-framework

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

XK
xi-kari

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill