refine-prompt SKILL.md skillA

refine-prompt from coupler-io/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add coupler-io/skills/refine-prompt@git:20261021.e36545f

Pins git:20261021.e36545f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
coupler-io/skills
Path
capability/refine-prompt/SKILL.md
Versions recorded
5
Latest version
git:20261021.e36545f, committed Oct 21, 2026
First version recorded
Jul 23, 2026
Size
4,653 bytes
Repository stars
40
License
MIT

Use this skill when the user's request is vague, incomplete, or poorly structured and needs to be sharpened into a detailed, actionable analytics prompt before analysis. Triggers include underspecified asks like 'how's my marketing doing', 'show me sales data', 'what campaigns performed best' — requests missing a time period, explicit metrics, data sources, comparison criteria, or output format.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Refine an Analytics Question

Turns a vague question like 'how is marketing doing' into a precise one, with the time period, metrics and comparison spelled out. Refine an Analytics Question is a Coupler.io AI agent skill.

You are a specialized prompt refinement agent for Coupler.io's multi-agent AI system.
Your sole purpose is to transform vague, incomplete, or poorly structured user requests into detailed, actionable prompts that generate high-quality data analysis.

## TASK

Take the user's original prompt and enhance it by adding missing critical details while preserving their core intent.

## GOOD PROMPT INCLUDES THE FOLLOWING

1. **Time period**: Specific date ranges or relative periods (last 30 days, Q4 2024, year-over-year).
2. **Metrics**: Explicit KPIs to analyze (CTR, conversion rate, revenue, ROI, engagement rate, etc).
3. **Data sources**: Which platforms/data flows to examine.
4. **Comparison criteria**: What to compare against (previous period, benchmarks, goals, channels).
5. **Output format**: How results should be presented (summary, detailed breakdown, tables, recommendations).
6. **Business context**: Why this analysis matters or what decision it informs.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add coupler-io/skills/refine-prompt@sha256:fa2bcb2616ecf75b

The line at the top of this page pins the label git:20261021.e36545f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_jgz5scgzijye3rnq.svg)](https://markdownregistry.com/a/art_jgz5scgzijye3rnq)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jul 23, 2026 and Oct 21, 2026, about one every 22 days.

versioncommittedcommitsizeaudit
git:20261021.e36545f latest2026-10-21 e36545f 4,653 BA view · diff
git:20261013.e5eb5e82026-10-13 e5eb5e8 4,460 BA view · diff
git:20261012.3a5f5c72026-10-12 3a5f5c7 4,445 BA view · diff
git:20260826.260c8c02026-08-26 260c8c0 4,251 BA view · diff
git:20260723.58d81012026-07-23 58d8101 4,204 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4653 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

coupler-io/skills · 40 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jgz5scgzijye3rnq
GET https://markdownregistry.com/api/v1/resolve?ref=coupler-io/skills/refine-prompt
GET https://markdownregistry.com/api/v1/blob/fa2bcb2616ecf75b682d09976124835f91dda4fdb6e530e2ffef051826895db4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from coupler-io/skills

platform-rules SKILL.md skill
coupler-io/skills · .agents/skills/platform-rules/SKILL.md · Use this skill to keep the platform rules that Coupler.io skills state as fact current: budget flexibility…
v1.0.0 · audit A · 40 stars
skill-review SKILL.md skill
coupler-io/skills · .agents/skills/skill-review/SKILL.md · Use this skill when reviewing a Coupler.io skill before merge, auditing an existing one, or checking a pack of skills…
v1.2.0 · audit A · 40 stars
create-dataflow SKILL.md skill
coupler-io/skills · capability/create-dataflow/SKILL.md · Use this skill when the user wants to create a new dataflow, set up a new data import, connect a new data source to a…
git:20261021.e36545f · audit A · 40 stars
generate-data-set-context SKILL.md skill
coupler-io/skills · capability/generate-data-set-context/SKILL.md · Use this skill when the user wants to explore a dataset's context, or write or update documentation for the data it…
git:20261021.e36545f · audit A · 40 stars
get-started SKILL.md skill
coupler-io/skills · capability/get-started/SKILL.md · Use this skill when the user's Coupler.io workspace is NEW or EMPTY — no datasets, no credentials — and they want their…
v0.2.0 · audit A · 40 stars
google-ads-custom-gaql SKILL.md skill
coupler-io/skills · capability/google-ads-custom-gaql/SKILL.md · Use this skill when the user needs Google Ads data that no packaged report type carries, or asks for a Custom GAQL…
git:20261021.e36545f · audit A · 40 stars
report-generation SKILL.md skill
coupler-io/skills · capability/report-generation/SKILL.md · Use this skill to produce a structured business report from analysis output and validate it before delivery — turning…
git:20261021.e36545f · audit A · 40 stars
cin7-reorder-point-and-stock-cover SKILL.md skill
coupler-io/skills · ecommerce/cin7/cin7-reorder-point-and-stock-cover/SKILL.md · Use for "when should we reorder in Cin7", "what's our reorder point for each SKU", "how many weeks of stock do we have…
v1.0.0 · audit A · 40 stars
ecom-analytics SKILL.md skill
coupler-io/skills · ecommerce/ecom-analytics/SKILL.md · Use this skill when the user wants to analyze e-commerce performance, review funnel conversion, investigate AOV or…
git:20261021.e36545f · audit A · 40 stars
gorgias-support-tickets-per-order SKILL.md skill
coupler-io/skills · ecommerce/gorgias/gorgias-support-tickets-per-order/SKILL.md · Use for "how many support tickets per order do we get", "why is our Gorgias volume up", "what are customers contacting…
v1.0.0 · audit B · 40 stars
klaviyo-email-deliverability-check SKILL.md skill
coupler-io/skills · ecommerce/klaviyo/klaviyo-email-deliverability-check/SKILL.md · Use for "is our Klaviyo sending healthy", "are our emails going to spam", "why is our Klaviyo bounce rate up", "which…
v1.0.0 · audit A · 40 stars
klaviyo-flow-performance-vs-benchmarks SKILL.md skill
coupler-io/skills · ecommerce/klaviyo/klaviyo-flow-performance-vs-benchmarks/SKILL.md · Use for "how are our Klaviyo flows doing", "is our abandoned cart flow good", "which Klaviyo flow underperforms", "how…
v1.0.0 · audit B · 40 stars

Every file in coupler-io/skills

Other files named refine-prompt

refine-prompt SKILL.md skill
iliaal/whetstone · distillery/generated-skills/refine-prompt/SKILL.md · Transforms vague or rough prompts into precise, structured AI instructions. Use when asked to "refine prompt", "improve…
git:20260227.215f429 · audit A · 35 stars

Browse by kind, by grade A, or by owner.