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 zpower426/datapowers --skill writing-data-skillsgit clone --depth 1 https://github.com/zpower426/datapowersWrote 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/zpower426/datapowers/writing-data-skills)<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.
<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>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 | $0.00034 | $0.01470 |
| Opus 5 | $0.00017 | $0.00735 |
| Sonnet 5 | $0.00007 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
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.
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:
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.
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.
- 12d ago First seen · 142 lines · 34 tokens per session scan A b380ad93eb82
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.
Other skills, from other repositories
peer-conversation
A structured, multi-turn discussion between the main coding agent and one or more other AI assistants about a task.
kimi-peer-writer
A peer-work session in which Kimi writes and Claude acts as a second participant. It supports repeated turns, escalation, review, checking, and a decision about whether to record or implement a result.
archgate
An architecture review method that evaluates a proposed system design or technology change across seven qualities.
pack-new
Create a new Pack — guided flow through SPF: choose domain, name Pack, scaffold structure, fill roadmap.
apply-captures
A review process for extraction reports marked as waiting for review. It lets a person accept, reject, or defer each proposed item and records the decision.
bottleneck-pick
A constraint-analysis skill that finds the main bottleneck, the part of a workflow limiting overall progress, for a specific project or work plan.