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.
npx skills add ur-grue/autopunk-media-skills --skill data-cleaning-briefgit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-cleaning-brief)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-cleaning-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-cleaning-brief/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-cleaning-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-cleaning-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01909 |
| Opus 5 | $0.00022 | $0.00955 |
| Sonnet 5 | $0.00009 | $0.00382 |
| Haiku 4.5 | $0.00004 | $0.00191 |
Grade A, and why
data-cleaning-brief 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 13d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Cleaning Brief
What This Skill Does
Writes clear, step-by-step instructions for cleaning a messy or inconsistent dataset — specifying exactly what needs to be standardised, corrected, or removed to make the data ready for analysis and publication.
When To Use This Skill
- You have received a dataset that is clearly messy (inconsistent formats, duplicates, blank fields, mixed naming conventions) and need to brief a data analyst or developer on how to clean it
- You want to document your cleaning decisions for editorial transparency and methodological reproducibility
- You are cleaning data yourself and want a structured checklist to work through
- You are handing off a partially cleaned dataset and need to document what has been done and what remains
What You Need To Provide
Required: A description of the dataset and the problems you can see in it — specific examples of inconsistent values, formatting problems, missing data, or structural issues. Column names and a small sample of the messy rows. Optional: The intended analysis goal (what you will do with the data once it is clean); any cleaning decisions that have already been made; the tool the analyst will use (Excel, Python, R, SQL); the deadline.
How the Assistant Approaches This
- Identifies each cleaning problem from the description and categorises it: standardisation (format, spelling, case), deduplication, missing value handling, type conversion, or structural issues.
- Writes a numbered, sequenced instruction set — earlier steps that change data shape (deduplication, column splitting) before later steps that change values (standardisation, type conversion).
- Flags any cleaning decisions that involve editorial judgement — e.g. how to handle ambiguous missing values, or whether to exclude records rather than impute them — and notes that these decisions need journalist sign-off.
Output Format
A structured brief (300–500 words) with two sections: (1) Cleaning checklist — numbered steps in recommended order, each naming the column affected, describing the problem, and specifying the action to take. (2) Decisions requiring editorial sign-off — a separate list of any steps where reasonable people could disagree on the right approach, with the options and recommended default. Plain language throughout; minimal technical jargon, but tool-specific syntax can be included in parentheses where helpful.
What ships with it
1 file 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.
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.
- 13d ago First seen · 102 lines · 44 tokens per session scan A 05f6b541087d
data-cleaning-brief is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 44 tokens to every session and 1,909 once invoked, about $0.0002 per session on Opus 5. 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.
Other skills, from other repositories
entity-extract
This skill should be used when the user wants to extract named entities and the relations between them from a trustworthy ingested document, build an entity/relationship network or knowledge graph from a FOIA PDF, map people / organizations / agencies / vendors and their connections, or produce a reviewed FtM-shaped…
digital-archive
Digital archiving with AI enrichment and entity extraction. Use when building content archives or knowledge graphs.
python-pipeline
Python data pipelines with modular architecture. Use for content workflows, batch jobs, or Google Sheets/Drive integration.
transcript-ingestion
Transcript ingestion authority — capture, normalize, and prioritize transcripts from YouTube videos, podcast pages, captions, show notes, and transcript-like page content for persona systems, RAG pipelines, and grounded synthesis.
entity-graph
Resolve entities across an investigation's documents into a Neo4j graph after a mandatory human review gate. Layer-2, operator-tier, Docker-gated -- run it to deduplicate people/orgs across the corpus, decide the "maybe" matches yourself, then write the resolved network to Neo4j for queryable analysis.
analysis-recipe
This skill should be used when the user asks to "run the analysis recipe", "run the 13-point checklist", "run the per-source investigative pass", "analyze this FOIA/audit-log source for out-of-state / immigration / pretext / mega-users / co-travel", "roll up findings across multiple sources/agencies", or "test the…