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 magnus919/agent-skills --skill data-cleaninggit clone --depth 1 https://github.com/magnus919/agent-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/magnus919/agent-skills/data-cleaning)<a href="https://agentmods.dev/skills/magnus919/agent-skills/data-cleaning"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/data-cleaning/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/magnus919/agent-skills/data-cleaning"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/data-cleaning.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 | $0.00088 | $0.01645 |
| Opus 5 | $0.00044 | $0.00822 |
| Sonnet 5 | $0.00018 | $0.00329 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade A, and why
data-cleaning 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data cleaning
Treat cleaning as a controlled transformation of an observed dataset, not cosmetic editing. Preserve raw input, state the target use and grain, make every lossy decision explicit, and prove that the cleaned output satisfies a contract.
Route by task
| Need | Read next |
|---|---|
| End-to-end method, scope, and stopping rules | references/methodology.md |
| Choose a library or platform | references/tool-selection.md |
| Missingness, duplicates, types, ranges, categories, dates, joins | references/operations.md |
| Text, identifiers, Unicode, and entity resolution | references/text-and-entity.md |
| Schemas, contracts, validation, drift, scale | references/validation-and-scale.md |
| CLI, OpenRefine, monitoring, and interactive remediation | references/cli-and-interactive-tools.md |
| Source claims and version-sensitive caveats | references/sources.md |
| Plan, logs, exceptions, contracts, or reports | templates/cleaning-plan.md, templates/transformation-log.jsonl, templates/exception-register.csv, templates/schema-contract.yml, templates/quality-report.md |
| Lightweight profile or reconciliation | Run python3 scripts/profile_dataset.py --help or python3 scripts/reconcile_dataset.py --help |
Available Scripts
| Script | Purpose | Invocation |
|---|---|---|
scripts/profile_dataset.py |
Dependency-free first-pass profiling of a CSV, TSV, or JSONL input without modifying it: missingness, cardinality, type candidates, duplicates, ranges, and value anomalies. Run it at workflow step 3 (Profile before changing) as the evidence-gathering pass before designing any cleaning decision. | python3 scripts/profile_dataset.py data.csv --output profile.json |
scripts/reconcile_dataset.py |
Reconciliation between a before and after delimited dataset: row counts, key uniqueness/overlap, and per-column sums (--sum), keyed by --key, writing a machine-readable report. Run it during Validate twice / Review to prove grain preservation and quantify exactly what a transformation changed. |
python3 scripts/reconcile_dataset.py raw.csv cleaned.csv --key id --sum amount --output reconciliation.json |
scripts/test_profile_dataset.py |
Pytest suite covering the profiler's behavior on representative inputs. Run it after modifying the profiler or when auditing its output; CI discovers it automatically. | python3 -m pytest scripts/test_profile_dataset.py |
scripts/test_reconcile_dataset.py |
Pytest suite covering the reconciler's keying, summing, and reporting behavior. Run it after modifying the reconciler or when auditing its output; CI discovers it automatically. | python3 -m pytest scripts/test_reconcile_dataset.py |
What ships with it
20 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.
- evals/evals.json 5.7 KB
- evals/trigger-cases.json 414 B
- README.md 2.1 KB
- references/cli-and-interactive-tools.md 1.4 KB
- references/methodology.md 2.0 KB
- references/operations.md 2.0 KB
- references/sources.md 2.6 KB
- references/text-and-entity.md 1.8 KB
- references/tool-selection.md 1.5 KB
- references/validation-and-scale.md 1.2 KB
- scripts/profile_dataset.py 5.2 KB runs code
- scripts/reconcile_dataset.py 3.6 KB runs code
- scripts/test_profile_dataset.py 1.6 KB runs code
- scripts/test_reconcile_dataset.py 1.9 KB runs code
- templates/cleaning-plan.md 1.0 KB
- templates/decision-log.csv 183 B
- templates/exception-register.csv 148 B
- templates/quality-report.md 783 B
- templates/schema-contract.yml 943 B
- templates/transformation-log.jsonl 237 B
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.
- 10d ago First seen · 85 lines · 88 tokens per session scan A 23c89b41b25d
data-cleaning is a skill published in the GitHub repository magnus919/agent-skills (75 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,645 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…