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 metric-definitiongit 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/metric-definition)<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/metric-definition"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/metric-definition/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/thuong-nc/perlytics-skill/metric-definition"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/metric-definition.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 | $0.00038 | $0.00638 |
| Opus 5 | $0.00019 | $0.00319 |
| Sonnet 5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
metric-definition 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metric Definition
Purpose
Force precise metric definitions before interpretation, reporting, or comparison.
When to use
Use this skill when:
- a metric name could mean several things
- a file, chart, or dashboard contains labels like revenue, usage, activation, churn, or cost that are not yet formally defined
- the user asks for analysis of a dataset but the main KPI could be interpreted in multiple valid ways
- teams are debating a KPI
- an answer depends on denominator choice
- a dashboard label is too vague to trust
When not to use
Do not use this skill when:
- the metric has an agreed canonical definition already documented and confirmed
- the task is pure arithmetic on an already defined metric
Required thinking discipline
- Never treat a metric label as a definition.
- Identify numerator and denominator clearly.
- Specify the entity, grain, timeframe, and filters.
- Surface definition risks that could change interpretation.
- 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
- Restate the metric name.
- Define what is counted.
- Define what is excluded.
- Define denominator logic if the metric is a rate or ratio.
- Specify grain, timeframe, and segment rules.
- Note data source or implementation assumptions.
- Produce a metric spec before any narrative interpretation.
Output format
- Metric name
- Business intent
- Formal definition
- Numerator
- Denominator
- Entity and grain
- Timeframe logic
- Filters and exclusions
- Known ambiguities
Good example
Metric:
Activation rate
Good response:
Activation rate = share of new signups who complete project creation within 7 days of signup.
Numerator: distinct new users who create at least one project within 7 days.
Denominator: distinct new signups in the cohort.
Exclude internal accounts and spam-flagged users.
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.
- 10d ago First seen · 97 lines · 38 tokens per session scan A dc61774b9dd2
metric-definition is a skill published in the GitHub repository thuong-nc/perlytics-skill (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 638 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.