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 thuong-nc/perlytics-skill --skill experiment-readoutgit clone --depth 1 https://github.com/thuong-nc/perlytics-skillWrote 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/thuong-nc/perlytics-skill/experiment-readout)<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/experiment-readout"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/experiment-readout.svg" alt="Measured on agentmods" 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 | $0.00477 |
| Opus 5 | $0.00017 | $0.00238 |
| Sonnet 5 | $0.00007 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
experiment-readout 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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Readout
Purpose
Turn test results into a disciplined decision memo rather than a celebratory summary.
When to use
Use this skill when:
- reading out an A/B test
- summarizing a quasi-experiment
- deciding whether to ship, hold, or investigate further
When not to use
Do not use this skill when:
- the metric definitions are still unresolved
- the available evidence is too weak to call the result a test readout
Required thinking discipline
- State the primary metric first.
- Separate observed lift from business impact interpretation.
- Include guardrails and negative signals.
- Be honest about uncertainty, power, and external validity.
- Evidence constraint: Every conclusion must cite specific data — a number, a rate, a segment, or a timeframe. Do not speculate without evidential basis. If data is insufficient, state what is missing rather than asserting an unsupported inference.
Workflow
- Define the test, population, and decision question.
- Summarize the primary metric result.
- Summarize important guardrails.
- Note sample size, duration, and material limitations.
- State the practical decision recommendation.
- Call out what remains uncertain.
Output format
- Decision question
- Primary metric result
- Guardrail summary
- Confidence and limitations
- Recommendation
- Follow-up actions
Good example
Primary metric improved +3.8%, guardrails were neutral, but the test only covered mobile web and ran during a promotion period. Recommendation: ship to mobile web, hold broader rollout until desktop validation.
Bad example
The experiment won, so we should launch everywhere.
Why this is bad:
- uncertainty is missing
- rollout scope is not considered
- guardrails are ignored
Practical notes
- Include absolute baseline and relative lift where possible.
- Avoid treating "not significant" as evidence of no effect.
Optional variants
- Product tests: include user-experience or trust guardrails.
- Pricing tests: include revenue quality and fairness risks.
What ships with it
2 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.
- 8d ago First seen · 78 lines · 34 tokens per session scan A bf3bb7b3e43a
experiment-readout is a skill published in the GitHub repository thuong-nc/perlytics-skill (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 477 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
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.