writing-data-skills

writing-data-skills is a skill for Claude Code from zpower426/datapowers. It costs 34 tokens per session (1,470 once invoked), scanned A, original, MIT.

A quality guide for creating new skills in the Datapowers data-analysis library. It defines the required structure, testing process, and checks for making a skill precise and reliable.

In plain words
What is it for?
Writing, reviewing, and adversarially testing Datapowers skills before they are added to the library.
Why use it?
It helps prevent new analysis skills from being too vague, too restrictive, or untested.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the datapowers plugin — 20 skills, 3 commands, 3 agents, 1 hook shipped together

Good fit Writing, reviewing, and adversarially testing Datapowers skills before they are added to the library.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zpower426/datapowers/writing-data-skills
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.

Any agent
npx skills add zpower426/datapowers --skill writing-data-skills
Clone the repo
git clone --depth 1 https://github.com/zpower426/datapowers

Made for: Claude Code.

Or install datapowers, the plugin that ships this one along with the rest of its 20 skills, 3 commands, 3 agents, 1 hook.

Wrote 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.

agentmods badge for writing-data-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/zpower426/datapowers/writing-data-skills/github.svg)](https://agentmods.dev/skills/zpower426/datapowers/writing-data-skills)
Your own site
<a href="https://agentmods.dev/skills/zpower426/datapowers/writing-data-skills"><img src="https://agentmods.dev/badge/skills/zpower426/datapowers/writing-data-skills/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.

agentmods 80×15 button for writing-data-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/zpower426/datapowers/writing-data-skills"><img src="https://agentmods.dev/badge/skills/zpower426/datapowers/writing-data-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,470 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00034 $0.01470
Opus 5 $0.00017 $0.00735
Sonnet 5 $0.00007 $0.00294
Haiku 4.5 $0.00003 $0.00147

Measured 12d ago against content hash b380ad93eb82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

writing-data-skills 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 12d 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.

skills/writing-data-skills/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Data Skills

Every new datapowers skill must meet the quality bar defined here before it is merged. This skill is the quality gate for the skills library itself.

Why a meta-skill: Skills shape agent behavior at scale. A poorly written skill either fails to enforce discipline (too vague) or breaks legitimate workflows (too rigid). This skill ensures every contribution is tested adversarially, not just on the happy path.

Required Skill Structure

Every SKILL.md must contain these sections in this order:

---
name: <skill-name>
description: "<trigger condition> — <what the skill does>"
---

# Skill Title

One-paragraph statement of purpose and why this matters.

## Iron Law(s)        ← at least one; see format rules below
## When to Use       ← dot graph or bullet list of trigger conditions
## [HARD-GATE]       ← if the skill has a mandatory pre-condition
## Step-by-Step Procedure   ← numbered, specific, with code where needed
## Output            ← table of artifacts produced
## Self-Review Checklist    ← checkbox list agent runs before reporting DONE
## Anti-Patterns     ← "Never:" list of specific failure modes

Sections may be omitted only if genuinely not applicable (e.g., a meta-skill with no code artifacts). Missing sections without justification → skill rejected.

Iron Law Format Rules

An Iron Law is not a principle. It is a specific, violable prohibition that an agent can check mechanically.

Valid Iron Law:

**NO TRANSFORMER MAY BE FIT ON THE FULL DATASET BEFORE TRAIN/TEST SPLIT.**
  • Specific: names the operation (transformer fit)
  • Violable: an agent could accidentally do this
  • Checkable: can be verified by reading code

Invalid Iron Law (too vague):

**ALWAYS USE GOOD STATISTICAL PRACTICES.**
  • Cannot be violated in a specific way
  • Cannot be verified
  • Provides no actionable constraint

Every Iron Law must be followed by a <HARD-GATE> block if violating it would silently corrupt downstream results:

Read the full file on GitHub · 142 lines

Files

What ships with it

3 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. 12d ago First seen · 142 lines · 34 tokens per session scan A b380ad93eb82

Subscribe to this mod's changes

writing-data-skills is a skill published in the GitHub repository zpower426/datapowers (1 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,470 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 2026-08-31.