D
docsor1212/cite-holmes
Cite Holmes - deep research skill that interrogates its own citations
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"docsor1212-cite-holmes": {
"command": "npx",
"args": ["skills"]
}
}
}解析自我们于 2026-10-26 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"docsor1212-cite-holmes": {
"command": "npx",
"args": ["skills"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio docsor1212-cite-holmes -- npx skills
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 0 ★ · docsor1212/cite-holmes · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型：开源项目
- 收录与活跃
- 收录于 2026-10-25 · 最近见到 2026-11-14 · 共见到 24 次 · 被 1 个来源列出
- 评分构成
- 综合分 103 · 1 个来源 · repo
- 安装
npx skills
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx skills。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: 开源项目。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
docsor1212/cite-holmes；我们收录于 2026-10-25；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# Cite Holmes 🔍
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Deep research that interrogates its own sources.
Every AI research report you've ever read had a dirty secret: some of those polished references were probably fabricated. A Nature news analysis suggests tens of thousands of 2025 publications might include invalid AI-generated references. GPTZero scanned 4,841 NeurIPS 2025 submissions; as independently reported, at least 100 hallucinated citations were found across 51 accepted papers.
Cite Holmes is a deep-research skill with a badge and a magnifying glass: it researches like any deep-research agent — then arrests its own citations before you can cite them.
(Demo is real output: 8 references, 3 deliberately planted fabrications — a fake DOI, a dead URL, and a no-URL citation. All 3 were caught and excluded; the 5 real ones passed. Measured: 7.7 s for all 8 — 4.2 s of pure network checks, the rest is deliberate throttling.)
Reproduce it yourself — the planted-fakes file ships with the repo:
bash
python scripts/verifyrefs.py --refs examples/demorefs.json
## 30-second quickstart
bash
# MCP server (for agents — Claude Code / Codex / Cursor):
uvx --from "git+https://github.com/docsor1212/cite-holmes#subdirectory=mcp" cite-holmes-mcp
bash
python scripts/verifyrefs.py --refs refs.json --out report.md
# or verify straight from your reference manager (v1.9):
python scripts/verifyrefs.py --refs bibliography.bib --out report.md
# v3.7.0 context check — verify in-text citations inside a finished draft:
python scripts/verifyrefs.py --refs bibliography.bib --check-document paper.md --out report.md
China mirror (ModelScope 魔搭): — if you find this skill useful, a like there helps others find it.
Open report.md: CiteScore + pre-submission conclusion at the top,
per-reference verdicts below.
Medical work: add --profile medical. Writing a paper: add --export bibtex.
Institution/CI: add --mailto you@lab.edu (Crossref polite pool).
## What NOT to do (anti-patterns)
Don't feed semantic fields from the same model that wrote the draft —
the semantic cap trusts structured model judgments; self-review defeats it.
Don't treat verified as "the paper supports my claim" — verified means
the source exists at an authoritative tier and registry metadata matches the
claimed title/authors/journal/year. Whether the specific sentence is
supported is the semantic layer (agent judgment, or L4 cascade with a judge).
Don't batch >50 references per MCP call — the server rejects oversized
batches by design; split them.
Don't hand-edit mcp/verifyrefs.py — it is a sha-gated copy of
scripts/verifyrefs.py; edit the trunk and run mcp/syncengine.sh.
Don't cite from the report without reading needshumancheck flags —
partial/unreachable items carry explicit re-check instructions on purpose.
Don't skip --cn on lossy CN egress and then report unreachable as
"fake" — unreachable is not invalid; re-run with --cn or a proxy first.
## How it works
Five phases, two modes:
| Phase | What happens |
| CALIBRATE | Asks you 3–5 sharp questions first (scope, timeframe, audience) — prevents researching the wrong question |
| PLAN | Breaks your question into 3–7 sub-questions with a search budget |
| SEARCH | Diamond-shaped iterative search: broad → narrow → gap-filling, Chinese + English, source-tier pyramid |
Every AI research report you've ever read had a dirty secret: some of those polished references were probably fabricated. A Nature news analysis suggests tens of thousands of 2025 publications might include invalid AI-generated references. GPTZero scanned 4,841 NeurIPS 2025 submissions; as independently reported, at least 100 hallucinated citations were found across 51 accepted papers.
Cite Holmes is a deep-research skill with a badge and a magnifying glass: it researches like any deep-research agent — then arrests its own citations before you can cite them.
(Demo is real output: 8 references, 3 deliberately planted fabrications — a fake DOI, a dead URL, and a no-URL citation. All 3 were caught and excluded; the 5 real ones passed. Measured: 7.7 s for all 8 — 4.2 s of pure network checks, the rest is deliberate throttling.)
Reproduce it yourself — the planted-fakes file ships with the repo:
bash
python scripts/verifyrefs.py --refs examples/demorefs.json
## 30-second quickstart
bash
# MCP server (for agents — Claude Code / Codex / Cursor):
uvx --from "git+https://github.com/docsor1212/cite-holmes#subdirectory=mcp" cite-holmes-mcp
bash
python scripts/verifyrefs.py --refs refs.json --out report.md
# or verify straight from your reference manager (v1.9):
python scripts/verifyrefs.py --refs bibliography.bib --out report.md
# v3.7.0 context check — verify in-text citations inside a finished draft:
python scripts/verifyrefs.py --refs bibliography.bib --check-document paper.md --out report.md
China mirror (ModelScope 魔搭): — if you find this skill useful, a like there helps others find it.
Open report.md: CiteScore + pre-submission conclusion at the top,
per-reference verdicts below.
Medical work: add --profile medical. Writing a paper: add --export bibtex.
Institution/CI: add --mailto you@lab.edu (Crossref polite pool).
## What NOT to do (anti-patterns)
Don't feed semantic fields from the same model that wrote the draft —
the semantic cap trusts structured model judgments; self-review defeats it.
Don't treat verified as "the paper supports my claim" — verified means
the source exists at an authoritative tier and registry metadata matches the
claimed title/authors/journal/year. Whether the specific sentence is
supported is the semantic layer (agent judgment, or L4 cascade with a judge).
Don't batch >50 references per MCP call — the server rejects oversized
batches by design; split them.
Don't hand-edit mcp/verifyrefs.py — it is a sha-gated copy of
scripts/verifyrefs.py; edit the trunk and run mcp/syncengine.sh.
Don't cite from the report without reading needshumancheck flags —
partial/unreachable items carry explicit re-check instructions on purpose.
Don't skip --cn on lossy CN egress and then report unreachable as
"fake" — unreachable is not invalid; re-run with --cn or a proxy first.
## How it works
Five phases, two modes:
| Phase | What happens |
| CALIBRATE | Asks you 3–5 sharp questions first (scope, timeframe, audience) — prevents researching the wrong question |
| PLAN | Breaks your question into 3–7 sub-questions with a search budget |
| SEARCH | Diamond-shaped iterative search: broad → narrow → gap-filling, Chinese + English, source-tier pyramid |
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/docsor1212-cite-holmes/)
- 来源
- github · https://github.com/docsor1212/cite-holmes
- 按领域浏览
- 开源项目
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。