clawhub

A data-quality checker for datasets, AI model outputs, and applications. Dingo accepts formats such as JSON, CSV, plaintext, and Parquet, and can use fixed rules or an AI model to assess content.

In plain words
What is it for?
Use it to check files for completeness, privacy issues, and format errors, or to assess text quality and whether retrieval-based answers are supported by their sources.
Why use it?
It helps find formatting problems, personal information, missing data, unsupported answers, and other quality issues before they affect users. Rule checks need no API key; AI-based checks do.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/migoxlab/dingo/clawhub
Any agent
npx skills add MigoXLab/dingo --skill clawhub
Clone the repo
git clone --depth 1 https://github.com/MigoXLab/dingo

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04436
Opus 5 $0.00000 $0.02218
Sonnet 5 $0.00000 $0.00887
Haiku 4.5 $0.00000 $0.00444

Measured yesterday against content hash 8fcf25a814c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clawhub scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fact_check.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

clawhub/SKILL.md · 509 lines

How it starts

The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Quality Evaluation with Dingo

Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool.

Installation

pip install dingo-python

Optional extras

pip install "dingo-python[agent]"    # Agent-based evaluation (fact-checking)
pip install "dingo-python[hhem]"     # HHEM hallucination detection
pip install "dingo-python[all]"      # Everything

Verify installation

python -c "from dingo.config import InputArgs; print('Dingo OK')"

Two evaluation modes

Rule-based LLM-based
API key required No Yes (any OpenAI-compatible API)
Speed Fast Slower (API calls)
Cost Zero Per-token cost
Metrics 50+ deterministic rules Text quality, RAG, 3H, security
Best for Format checks, PII, completeness Semantic quality, faithfulness

Core workflow

  1. Prepare data: JSONL, JSON, CSV, plaintext, or Parquet file
  2. Choose evaluators: Rule-based (free, fast) or LLM-based (semantic understanding)
  3. Run evaluation: CLI with config file or Python SDK
  4. Review results: summary.json + per-item JSONL reports in output directory

CLI Usage

Dingo CLI takes a JSON config file as input:

dingo eval --input config.json

Minimal rule-based config

{
  "input_path": "data.jsonl",
  "dataset": {"source": "local", "format": "jsonl"},
  "evaluator": [
    {
      "fields": {"content": "content"},
      "evals": [
        {"name": "RuleColonEnd"},
        {"name": "RuleSpecialCharacter"},
        {"name": "RuleContentNull"}
      ]
    }
  ]
}

LLM-based config

{
  "input_path": "data.jsonl",
  "dataset": {"source": "local", "format": "jsonl"},
  "evaluator": [
    {
      "fields": {"content": "content"},
      "evals": [
        {
          "name": "LLMTextRepeat",
          "config": {
            "model": "deepseek-chat",
            "key": "${OPENAI_API_KEY}",
            "api_url": "https://api.deepseek.com/v1"
          }
        }
      ]
    }
  ]
}

Read the full file on GitHub · 509 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 509 lines · 0 tokens per session scan A 8fcf25a814c5

Subscribe to this mod's changes

clawhub is a skill published in the GitHub repository MigoXLab/dingo (751 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,436 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

portaljs-check-data-quality

Audit a local or remote tabular file (CSV/TSV) for common data quality issues — schema, nulls, types, duplicates. Read-only. Use when a dataset needs a quality check before publishing, or a showcase renders wrong (blank cells, garbled numbers, an unsortable date column) and the cause needs isolating.

datopian/portaljs · 76 tokens

fastapi-templates

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

ModelEngine-Group/DataMate · 37 tokens

audit-dataset

Audit tabular datasets before analysis or training for schema drift, missing values, duplicate rows or IDs, target imbalance, and entity or group leakage across splits using pure-stdlib helpers.

PKU-YuanGroup/OpenAI4S · 40 tokens

high-stakes-analytics-decision-lab

Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions. Use when an agent must profile and safely prepare uploaded data, turn a real dataset or research question into a reproducible study, investigate drivers without overstating causality, validate a…

limingrui679-design/high-stakes-analytics-decision-lab · 112 tokens

tao-validate-recipe-transfer

Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers. Use this whenever someone wants to reproduce a CV paper, run a paper's repo on their own images, fine-tune a published…

NVIDIA-TAO/tao-skill-bank · 179 tokens

data-cleaning

Use when a raw table is too dirty to trust — nulls, sentinels, duplicate rows, category sprawl, mixed types, bad dates — and you need a re-runnable clean() plus a schema gate that fails loud. NOT emitting .xlsx (that is spreadsheet-ops), NOT acquiring rows (that is data-scraper), NOT parsing PDF/HTML into rows (that…

ericrisco/rsc-harness · 88 tokens