How should Cite Holmes — Deep Research × Hallucination-Free Citations be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Cite Holmes — Deep Research × Hallucination-Free Citations

Deep research that interrogates its own sources (Verified Deep Research): calibrates scope first (3-5 sharp questions), then searches iteratively and machine-verifies every citation. Also a standalone citation checker: paste any reference list and it runs full citation verification (it will verify citations before you cite) against official registries — hallucinated references, fabricated DOIs, fake PMIDs, arXiv IDs, stitched fakes, retracted papers; a fact check for your bibliography. Five verdicts; unverified references never masquerade as real (AI hallucination detection). Medical mode (Cochrane/BMJ/ChiCTR/NMPA/CDC/NICE presets, PMID check) and bibliography export (BibTeX/GB·T 7714-2025/RIS/CSV + JSON workpaper) built in. Trigger matching is semantic, not exact — mis-triggers are harmless; state your real intent to avoid them. Skill: Cite Holmes — Deep Research × Hallucination-Free Citations Owner: docsor1212 Summary: Deep research that interrogates its own sources (Verified Deep Research): calibrates scope first (3-5 sharp questions), then searches iteratively and machine-verifies every citation. Also a standalone citation checker: paste any reference list and it runs full citation verification (it will verify citations before you cite) a

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.6k

Updated

Oct 10, 2026

Version

3.11.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.6K downloadsadoption · observed Oct 10, 2026
Latest release: 3.11.0release · observed Oct 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dagtwyk21qs6vpz98bzcrh1853t29:cite-holmes

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-docsor1212-cite-holmes/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: cite-holmes
version: 3.11.0
author: DoctorQ Lab
license: MIT
description: >-
  Deep research that interrogates its own sources (Verified Deep Research):
  calibrates scope first (3-5 sharp questions), then searches iteratively and
  machine-verifies every citation. Also a standalone citation checker: paste
  any reference list and it runs full citation verification (it will verify
  citations before you cite) against official registries —
  hallucinated references, fabricated DOIs, fake PMIDs, arXiv IDs, stitched
  fakes, retracted papers; a fact check for your bibliography. Five verdicts;
  unverified references never masquerade as real (AI hallucination detection).
  Medical mode (Cochrane/BMJ/ChiCTR/NMPA/CDC/NICE presets, PMID check) and
  bibliography export (BibTeX/GB·T 7714-2025/RIS/CSV + JSON workpaper) built
  in. Trigger matching is semantic, not exact — mis-triggers are harmless;
  state your real intent to avoid them.
when_to_use: >-
  Use when the user says "deep research", "look into", "investigate",
  "compare A vs B", "fact check", "verify this claim", "is it true that...",
  "check these references", "are these citations real", wants a research
  report with sources, a literature review, a medical evidence lookup, or
  wants references verified before submission — even if they never say the
  word "research".
---

# cite-holmes (Cite Holmes): deep research with citation verification

One line: **a question goes in — a verified report comes out.**

Three differences from a plain "search and summarize":

1. **Calibrate before working** — ask sharp questions first; the most expensive
   waste is researching the wrong question.
2. **Conclusions carry evidence grades** — 🟢 two independent sources agree /
   🟡 single authority / 🔴 contested.
3. **Every citation is checked** — mechanical layer (reachability, domain
   authority, field completeness, dedup) plus semantic layer (does the source
   actually support the claim?). Unverified references never masquerade as real.

## ⛔ Iron rules (zero exceptions)

1. **Never fabricate**: citations must come from pages actually fetched this
   session. Re-search rather than write URLs from memory.
2. **Never pretend**: unchecked references are marked `unverified`; fetch
   failures are `unreachable` (≠ nonexistent — flagged for human review).
3. **Don't hide conflicts**: when sources disagree, present the disagreement,
   mark 🔴, show each side's evidence.
4. **Budgeted search**: QUICK ≤6 searches, FULL ≤15. Out of budget → state the
   gaps honestly instead of forcing conclusions.
5. **Calibrate before searching** (FULL mode): scope / timeframe / audience /
   output format must be locked first.

## Step 0: mode selection

| Mode | Fits | Calibration | Budget | Output |
|---|---|---|---|---|
| **QUICK** | Single fact-check: "is this claim true", "when was X released" | skipped | ≤6 | short report |
| **FULL** | Open research: "state of X", "A vs B", "do a survey" | mandatory | ≤15

examples/end-to-end/README.md

# 端到端对照示例（输入 → 命令 → 实际输出）

输入 → 命令 → 实际输出，三件套可直接复跑：

```bash
python scripts/verify_refs.py --refs end-to-end/research_refs.json \
    --check-document end-to-end/paper_excerpt.md \
    --export gbt7714,ris,bibtex,csv --out end-to-end/report.md
```

| 文件 | 是什么 |
|---|---|
| research_refs.json | 输入：1 条真实 DOI 引用（含正确标题） |
| paper_excerpt.md | 输入：含 in-text 引用标记的正文片段（叙述式 + [n] 各一处，其中一处故意跑题） |
| report.md | 实际输出：五态判定 + 上下文核验区（Kucsko 叙述式=锚定 ✓；[1] 企鹅句=低锚 ⚠️ 演示错配检测） |
| report.json | 机读版（含 context_check 与逐项 checks） |
| exports/ | 四种导出的真实产物样例（BibTeX / GB·T 7714-2025 / RIS / CSV） |

> 复跑需网络（DOI.org/PubMed）。判定含时效字段（撤稿/被引），数字可能随时间小幅变化
> ——以你复跑时的输出为准，结构不变。

> SkillHub 包注：为符合平台文件类型白名单，`exports/` 导出样例文件不随
> SkillHub 包分发（GitHub/ClawHub 包完整附带）——格式以本页表格描述为准。

mcp/README.md

# cite-holmes-mcp

**Mechanical citation verification as an MCP server** — feed it the references an
agent is about to cite, get back per-reference verdicts (`verified / partial /
unreachable / invalid`) against official registries (DOI.org, PubMed
E-utilities, arXiv API, Crossref/Retraction Watch, Wayback). Zero API keys
required, zero telemetry, local-first.

Three MCP primitives:

| Primitive | Name | What it does |
|---|---|---|
| tool | `verify_references` | Verify a batch of references (≤50); returns CiteScore 0–100 + per-item verdicts with evidence chain |
| tool | `check_document` | Context-level check: parse in-text markers ([12]/[1-4]/(Author, Year)/doi.org links), bind to the reference list, flag low anchor-word overlap as possible mis-citations |
| tool | `explain_verdict` | Plain-language explanation of one verdict (evidence steps + suggested action); zero network |
| resource | `cite-holmes://capability-matrix` | What the mechanical layer catches vs. what stays with the semantic layer |
| resource | `cite-holmes://changelog` | Version history |
| prompt | `fact_check_workflow` | Three-step research-then-verify workflow for agents |

## Install (three channels)

```bash
# 1) uvx from GitHub (recommended — always current)
uvx --from "git+https://github.com/docsor1212/cite-holmes#subdirectory=mcp" cite-holmes-mcp

# 2) uvx from a local checkout
git clone https://github.com/docsor1212/cite-holmes
uvx --from ./cite-holmes/mcp cite-holmes-mcp --help

# 3) pip install (module + console script)
pip install "git+https://github.com/docsor1212/cite-holmes#subdirectory=mcp"
cite-holmes-mcp --help
```

> This is a Python package (uv/pip ecosystem). There is no npm package — the
> uvx/git channel above is the canonical install for all MCP clients.

## Client configuration

**Claude Code**

```json
{
  "mcpServers": {
    "cite-holmes": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/docsor1212/cite-holmes#subdirectory=mcp",
               "cite-holmes-mcp"]
    }
  }
}
```

**Codex / any stdio MCP client**

```json
{
  "mcpServers": {
    "cite-holmes": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/docsor1212/cite-holmes#subdirectory=mcp",
               "cite-holmes-mcp", "--transport", "stdio"]
    }
  }
}
```

**Cursor** (`~/.cursor/mcp.json`, same shape)

```json
{
  "mcpServers": {
    "cite-holmes": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/docsor1212/cite-holmes#subdirectory=mcp",
               "cite-holmes-mcp"]
    }
  }
}
```

HTTP mode (local): `cite-holmes-mcp --transport http --port 8760`.

## Bounds & behavior

- Batch ≤ 50 references per `verify_references` call (larger batches get a
  clear error — split them).
- Long output fields are clipped (800 chars + truncation marker) so MCP
  messages stay bounded; structure is preserved.
- Per-reference network timeout defaults to 15 s (configurable per call).
- Optional API keys via env: `OPENALEX_A

README.md

# Cite Holmes 🔍

[![GitHub Stars](https://img.shields.io/github/stars/docsor1212/cite-holmes?style=social&label=Star)](https://github.com/docsor1212/cite-holmes/stargazers)

![icon](assets/icon-512.png)

**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](https://www.nature.com/articles/d41586-026-00969-z). [GPTZero scanned 4,841 NeurIPS 2025 submissions; as independently reported, at least 100 hallucinated citations were found across 51 accepted papers](https://medium.com/@ljingshan6/100-fake-citations-just-slipped-through-neurips-2025-peer-review-5f34f4436560).

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](assets/demo.gif)

*(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/verify_refs.py --refs examples/demo_refs.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/verify_refs.py --refs refs.json --out report.md
# or verify straight from your reference manager (v1.9):
python scripts/verify_refs.py --refs bibliography.bib --out report.md
# v3.7.0 context check — verify in-text citations inside a finished draft:
python scripts/verify_refs.py --refs bibliography.bib --check-document paper.md --out report.md
```

**China mirror (ModelScope 魔搭)**: <https://modelscope.cn/skills/Docsor/cite-holmes> — 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 [email protected]` (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 des

_meta.json

{
  "ownerId": "kn7b6sjwend7cwwmhf7mdg1wzx82dfbf",
  "slug": "cite-holmes",
  "version": "3.11.0",
  "publishedAt": 1791566549713
}

Github ReposUpdated 15h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.