knowledge-architecture-evaluation SKILL.md skillA

knowledge-architecture-evaluation from kimyx0207/kim_service is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kimyx0207/kim_service/knowledge-architecture-evaluation@git:20261114.fa2ad6c

Pins git:20261114.fa2ad6c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kimyx0207/kim_service
Path
skills/knowledge-architecture-evaluation/SKILL.md
Versions recorded
1
Latest version
git:20261114.fa2ad6c, committed Nov 14, 2026
Size
2,735 bytes
Repository stars
193
License
MIT

知识库架构评估(RAG LLM Wiki CAG KV cache GraphRAG agentic retrieval)。用于选择或重评知识问答、长期知识复用、跨文档研究方案,比较原文检索、编纂知识、缓存和图检索的任务适配、版本、权限撤回、质量及全周期成本;不把检索命中当答案正确,不代替实现或发布批准。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 知识库架构评估

先读 [method.json](method.json) 与 [专业方法](references/professional-method.md),再读取调用方当前项目上下文和数据事实。术语“LLM-KV”不明确时分别说明 LLM Wiki 与 KV cache 的含义,结合材料消歧;其余可完成工作继续。

## 输入

`projectContext`:使用者、任务、价值类型、阶段、预算;`corpus`:来源、语言、token/规模、更新、权限和撤回要求;`currentSystem`:真实模型/索引/运行时版本与现有路线;`evaluationEvidence`:问题集、原文、轨迹、成本、时延及尚未观察项。

## 执行

1. 将任务分为定位事实、精确术语、跨文档综合、整体关系、持续知识复用等真实类别;核资料和身份变化。
2. 按类别比较混合检索、长上下文/CAG、LLM Wiki、图检索和分解检索。区分层次,只组合能解决已观察问题的机制。
3. 查当前作者仓库、官方文档、论文修订和兼容限制。记录每个来源改变的决定,不用旧对照分数宣称普遍胜出。
4. 固定基线、数据/权限快照、问题与预算后做小对照;答案正确、引用支撑、权限、撤回、延迟和成本分开判断。
5. 输出 `projectContext`、`comparisons`、`evidenceLedger`、`decision`、`lifecyclePlan`、`validationPlan`、`projectCapabilityRequirements`、`facts`、`handoff`,并入现有设计。项目独立专业能力由宿主创建或原地迭代,保留全局基底与领域差异。

## 可选检查

按 [轨迹检查 API](references/helper-api.md) 对原文—切块—Wiki/图—缓存的实际依赖与权限快照做离线一致性审查:

```sh
node scripts/audit-knowledge-trace.mjs --input-json - < supplied-trace.json
```

它不执行删除、不确认真实用户身份、不验证答案语义;实际系统须提供完整暴露轨迹并运行更新/撤回/权限变更测试。真实操作与人工复核缺失时保留未观察。检索 ID 指标交现有 `retrieval-evaluation`;完整架构与用户结果由当前项目负责人验收。

阅读 [交付示例](references/delivery-template.md)、[作者正反例](evals/professional-cases.json)。`node --test tests/*.test.mjs` 验证本包结构与确定性反例,不代表本项目架构已实测胜出。

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_mlicaaov4pea32as/da2574eebef0d8ba6a9762511df7d6aa84ed3378b15880b9bcc395207d7c7049.json

Then /plugin install knowledge-architecture-evaluation@markdownregistry-mlicaaov4pea32as in Claude Code. It installs git:20261114.fa2ad6c, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add kimyx0207/kim_service/knowledge-architecture-evaluation@sha256:da2574eebef0d8ba

The line at the top of this page pins the label git:20261114.fa2ad6c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_mlicaaov4pea32as.svg)](https://markdownregistry.com/a/art_mlicaaov4pea32as)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in kimyx0207/kim_service/knowledge-architecture-evaluation since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of knowledge-architecture-evaluation from somewhere else? Ask it: where did my knowledge-architecture-evaluation come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 14, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261114.fa2ad6c latest2026-11-14 fa2ad6c 2,735 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2735 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

kimyx0207/kim_service · 193 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mlicaaov4pea32as
GET https://markdownregistry.com/api/v1/resolve?ref=kimyx0207/kim_service/knowledge-architecture-evaluation
GET https://markdownregistry.com/api/v1/blob/da2574eebef0d8ba6a9762511df7d6aa84ed3378b15880b9bcc395207d7c7049

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from kimyx0207/kim_service

accessibility-audit SKILL.md skill
kimyx0207/kim_service · skills/accessibility-audit/SKILL.md · 可访问性检查与修复(accessibility WCAG keyboard screen reader audit)。用真实任务检查键盘、阅读器、焦点、文字和错误恢复,并把问题落实到修复位置。用于检查页面能否用键盘和阅读器操作。;帮我修表单…
git:20261111.89b2b28 · audit A · 193 stars
agent-evaluation SKILL.md skill
kimyx0207/kim_service · skills/agent-evaluation/SKILL.md · 用相同数据集比较不同模型客户端的已有输出,保留缺失项、关键断言、分层回归和成本延迟预算。 agent evaluation offline regression budget
git:20261117.56fee03 · audit A · 193 stars
agent-teams-playbook SKILL.md skill
kimyx0207/kim_service · skills/agent-teams-playbook/SKILL.md · Cross-runtime playbook for multi-agent collaboration, agent teams, swarm orchestration, parallel task distribution…
v4.10.0 · audit A · 193 stars
agent-thinking-patterns SKILL.md skill
kimyx0207/kim_service · skills/agent-thinking-patterns/SKILL.md · 全行业、所有专业 Agent 可按任务选用的通用思考与行动方法。适合目标澄清、反证审查、目标倒推、专家方法比较、方案取舍、机会探索、先练后评、重复工作系统化、知识提炼或战略聚焦;不限定教育场景、不替换原 Agent…
git:20261115.381cd57 · audit A · 193 stars
api-contract-review SKILL.md skill
kimyx0207/kim_service · skills/api-contract-review/SKILL.md · API 契约审查(API contract OpenAPI compatibility idempotency)。检查接口是否能被真实调用、正确失败并兼容现有消费者。用于前后端要并行,先定接口。;API改版会不会破坏现有客户端?;接口重试和…
git:20261111.89b2b28 · audit A · 193 stars
construction-information-review SKILL.md skill
kimyx0207/kim_service · skills/construction-information-review/SKILL.md · 核对建筑模型信息要求、IFC/IDS版本、属性覆盖和交付证据 construction BIM IFC IDS information delivery review
git:20261110.c4dcec8 · audit A · 193 stars
customer-case-operations SKILL.md skill
kimyx0207/kim_service · skills/customer-case-operations/SKILL.md · 按可配置阶段、角色、材料和事件重放客户事项,输出下一步与缺项,独立保留验证、回执与采纳。 customer case operations workflow receipt
git:20261113.9c7ee35 · audit A · 193 stars
data-lineage-impact SKILL.md skill
kimyx0207/kim_service · skills/data-lineage-impact/SKILL.md · 核对字段血缘、变更影响范围、证据完整性与回归责任 data lineage impact analysis column change
git:20261113.3967162 · audit A · 193 stars
database-migration SKILL.md skill
kimyx0207/kim_service · skills/database-migration/SKILL.md · 数据库渐进迁移(database migration expand contract rollback PostgreSQL)。把数据库结构变更拆成兼容扩展、可重跑回填、切换和清理,保留可恢复路径。用于给已有大表加字段并迁移旧数据。;字段改…
git:20261111.89b2b28 · audit A · 193 stars
evidence-pack SKILL.md skill
kimyx0207/kim_service · skills/evidence-pack/SKILL.md · 把长文原文保留成带来源哈希的分页分块索引,按字节预算取回当前模块所需材料。 evidence source chunk context budget
git:20261113.9c7ee35 · audit A · 193 stars
experiment-analysis SKILL.md skill
kimyx0207/kim_service · skills/experiment-analysis/SKILL.md · 设计和审查随机实验、分流质量、指标与效果解释 experiment analysis A/B testing randomization SRM
git:20261110.c4dcec8 · audit A · 193 stars
feedback-to-requirements SKILL.md skill
kimyx0207/kim_service · skills/feedback-to-requirements/SKILL.md · 将客户反馈、明确重复关系与分组转成需求候选,计算独立客户数,保留矛盾证据和版本绑定采纳记录。 feedback requirements evidence ledger
git:20261117.56fee03 · audit A · 193 stars

Every file in kimyx0207/kim_service

Browse by kind, by grade A, or by owner.