citation-anchor-resolver SKILL.md skillA

citation-anchor-resolver from ethanyoq/skill-hub is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ethanyoq/skill-hub/citation-anchor-resolver@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ethanyoq/skill-hub
Path
archives/user-installed-skills/citation-anchor-resolver/de29313b62832c40/citation-anchor-resolver/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Sep 12, 2026
Size
7,785 bytes
Repository stars
11
License
MIT

Cite-or-Block 架构的基石原子 skill。把报告里的 citation 锚点 (例如 [guideline:CSCO-2024-NSCLC:§5.5.2] / [pmid:12345678:abstract]) 解析为源文件片段,并核对事实声明里的关键词是否在引用源原文里出现。 Foundation atomic skill for the Cite-or-Block architecture. Resolves citation anchors (e.g. [guideline:CSCO-2024-NSCLC:§5.5.2] / [pmid:12345678:abstract]) to raw source text fragments, and verifies whether claim keywords actually appear in the cited source. 使用场景 / Use when: 1. 报告生成后要做 fact-check (resolve_citation + verify_claim_against_source) 2.…

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

# citation-anchor-resolver

## TL;DR

输入:报告文本 + 一个 citation 锚点字符串 + sources_dir 目录
输出:锚点对应的源原文片段、或事实声明的关键词核对结果(verified True/False)

3 个公开函数:
- `parse_citations_in_text(text)` — 扫描文本提取所有锚点 + 上下文
- `resolve_citation(anchor, sources_dir)` — 锚点 → 源文本片段
- `verify_claim_against_source(claim_text, citation, sources_dir)` — 核对 claim 关键词

## Iron Law(P0 守护,绝对不可违反)

本 skill 是 **Cite-or-Block 架构的基石**。**永远不**做以下事:

- ❌ 维护"已知 PMID 列表 / 已知指南列表 / 已知药品列表"等任何字典
- ❌ 在 resolve 失败时 fallback 到"内置答案"
- ❌ 用 LLM 生成关键词的"语义匹配",必须用严格 substring(可加规范化)
- ❌ 任何形如 `_known_xxx_fallback.py` / `KNOWN_XX_LIST = [...]` 的代码

**唯一允许的姿势**:
- ✅ 打开 `sources_dir` 内的源文件(JSON/HTML/PDF/text)
- ✅ 用字符串 `in` 操作核对关键词
- ✅ 源里没有 → 返回 `verified=False`
- ✅ 锚点解析不出文件 → 返回 `None`

源里没有 = verified=False,无例外。

## Citation 锚点 schema

格式:`[<source_type>:<source_id>:<locator>]`

| source_type | source_id 形如 | 文件路径(相对 sources_dir)| locator 例 |
|------------|---------------|------------------------|-----------|
| `guideline` | `CSCO-2024-NSCLC` | `guidelines/CSCO-2024-NSCLC.{txt,md,html,pdf}` + `.toc.json` | `§5.5.2` |
| `pmid` | `12345678` | `pubmed/12345678.json` | `abstract` / `title` |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ethanyoq/skill-hub/citation-anchor-resolver@sha256:732bbfb7527a8253

The line at the top of this page pins the label v1.0.0, 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_6ps4tvexfpcbyaf7.svg)](https://markdownregistry.com/a/art_6ps4tvexfpcbyaf7)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 12, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-12 c74de71 7,785 BA view

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 (7785 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

ethanyoq/skill-hub · 11 stars · license MIT · pushed 2026-11-07 · branch mine

API

GET https://markdownregistry.com/api/v1/artifacts/art_6ps4tvexfpcbyaf7
GET https://markdownregistry.com/api/v1/resolve?ref=ethanyoq/skill-hub/citation-anchor-resolver
GET https://markdownregistry.com/api/v1/blob/732bbfb7527a8253f617719ebe3660044ffb98d39679577adadcffcef5610bf6

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 ethanyoq/skill-hub

AGENTS.md AGENTS.md file
ethanyoq/skill-hub · AGENTS.md
git:20260730.c96ba6e · audit A · 11 stars
aact-bulk-trials SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/aact-bulk-trials/e07736f27453c7b6/aact-bulk-trials/SKILL.md · 使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据仓库进行批量、历史、聚合性临床试验数据挖掘。Use this skill when the user…
git:20260912.c74de71 · audit A · 11 stars
aact-bulk-trials SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/aact-bulk-trials/e171d39ba5bce7c9/aact-bulk-trials/SKILL.md · 使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据库进行大批量临床试验历史分析与数据挖掘。触发场景包括:AACT 查询、临床试验批量分析、PostgreSQL…
git:20260912.c74de71 · audit A · 11 stars
adaptive-quality-gate SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/adaptive-quality-gate/b5189ce6c1bdba9b/adaptive-quality-gate/SKILL.md · Use when work produces a deliverable, factual claim, dataset, code change, decision, publication, deployment…
git:20260912.c74de71 · audit A · 11 stars
add-changeset SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/add-changeset/eca9273317fbdf81/add-changeset/SKILL.md · Create a changeset file in .changeset/ that describes a user-facing change for the release notes
git:20260912.84c6c93 · audit A · 11 stars
add-competitor SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/add-competitor/72939df8cfcf87bc/add-competitor/SKILL.md · Add a new competitor to the AI Visibility Tool Directory — researches the tool, generates data, takes a screenshot, and…
git:20260912.84c6c93 · audit A · 11 stars
add-lang SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/add-lang/00700e7d79525f4e/add-lang/SKILL.md · Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark…
git:20260912.84c6c93 · audit A · 11 stars
aesthetic SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/aesthetic/a4c80565d9241341/aesthetic/SKILL.md · Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing…
git:20260912.84c6c93 · audit A · 11 stars
agent-eval SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/agent-eval/61ca5bbbd5c736b7/agent-eval/SKILL.md · Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use…
git:20260912.84c6c93 · audit A · 11 stars
agent-reach SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/agent-reach/330e35da8cf10b5e/agent-reach/SKILL.md · MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g. 全网调研 X / 帮我调研一下 X / 查一下 X…
git:20260912.84c6c93 · audit A · 11 stars
agent-reach SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/agent-reach/81c9cf0fc08ce044/agent-reach/SKILL.md · MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g. 全网调研 X / 帮我调研一下 X / 查一下 X…
git:20260912.84c6c93 · audit A · 11 stars
aliyun-swas-manage SKILL.md skill
ethanyoq/skill-hub · archives/user-installed-skills/aliyun-swas-manage/1f89c6ea527741b3/aliyun-swas-manage/SKILL.md · Use when managing Alibaba Cloud Simple Application Server (SWAS OpenAPI 2020-06-01) resources end-to-end, including…
v1.0.0 · audit A · 11 stars

Every file in ethanyoq/skill-hub

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