work-item-refinement SKILL.md skillA

work-item-refinement from kaddo-kdd/kaddo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kaddo-kdd/kaddo/work-item-refinement@git:20261006.5f27edc

Pins git:20261006.5f27edc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kaddo-kdd/kaddo
Path
kaddo-power/skills/work-item-refinement/SKILL.md
Versions recorded
2
Latest version
git:20261006.5f27edc, committed Oct 6, 2026
First version recorded
Sep 24, 2026
Size
3,848 bytes
Repository stars
67
License
MIT

Standardize how a Work Item is sharpened from a rough idea into a ready, implementable item. Use when: When improving a draft Work Item, or turning a backlog idea / roadmap candidate into a ready item.

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

<!-- Generated from packages/cli/src/skills/skills.ts. Run `pnpm agent-plugin:sync`; do not edit directly. -->

# Work Item Refinement Skill

## Purpose

Standardize how a Work Item is sharpened from a rough idea into a ready, implementable item.

## When to use

When improving a draft Work Item, or turning a backlog idea / roadmap candidate into a ready item.

## Inputs

The context pack and the Work Item (draft or candidate).

## Output

An improved Work Item with: actor and outcome, current behavior, target behavior, entry points,
end-to-end flow, impact analysis, module coverage, scope unknowns, scope confidence, problem,
expected result, scope, out of scope, acceptance criteria (including end-to-end criteria for
user-facing changes), validation (how to test it), definition of done, open questions and
dependencies.

## Steps

1. **Outcome framing** — identify actor, current behavior, target behavior, observable completion.
2. **Journey reconstruction** — map entry point, interaction, service/API, state change, response,
   final outcome.
3. **Surface review** — evaluate: product/UI, frontend, backend, database, configuration, feature
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kaddo-kdd/kaddo/work-item-refinement@sha256:b97b2358eb1bdd2e

The line at the top of this page pins the label git:20261006.5f27edc, 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_srv5xcvuyip524cm.svg)](https://markdownregistry.com/a/art_srv5xcvuyip524cm)

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

Versions

The registry has recorded 2 versions of this file, between Sep 24, 2026 and Oct 6, 2026, about one every 13 days.

versioncommittedcommitsizeaudit
git:20261006.5f27edc latest2026-10-06 5f27edc 3,848 BA view · diff
git:20260924.7de86822026-09-24 7de8682 3,120 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 (3848 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

kaddo-kdd/kaddo · 67 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_srv5xcvuyip524cm
GET https://markdownregistry.com/api/v1/resolve?ref=kaddo-kdd/kaddo/work-item-refinement
GET https://markdownregistry.com/api/v1/blob/b97b2358eb1bdd2e6317039e15ff0570d2d8b707f7ada1c63a8074e7284f587c

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 kaddo-kdd/kaddo

CLAUDE.md CLAUDE.md file
kaddo-kdd/kaddo · CLAUDE.md
git:20260929.f66137d · audit A · 67 stars
adr-writing SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/adr-writing/SKILL.md · Standardize how Architecture Decision Records are written so every decision is captured the same way and stays…
git:20260924.7de8682 · audit A · 67 stars
capsule-writing SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/capsule-writing/SKILL.md · Standardize how a Knowledge Capsule is written/reviewed so external consumers get safe, useful context. Use when: When…
git:20260924.7de8682 · audit A · 67 stars
evidence-verification SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/evidence-verification/SKILL.md · Estandarizar la recolección de evidencia de implementación y la verificación de Criterios de Aceptación antes de…
git:20260928.2632ac1 · audit A · 67 stars
graph-metadata-review SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/graph-metadata-review/SKILL.md · Standardize how `kaddo graph export` hints become precise relationship front matter. Use when: When relationship…
git:20260924.7de8682 · audit A · 67 stars
implementation-planning SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/implementation-planning/SKILL.md · Standardize the plan produced before implementation starts and ensure design deliberation is explicit before coding…
git:20260928.2632ac1 · audit A · 67 stars
learning-capture SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/learning-capture/SKILL.md · Standardize how a Work Item's learning is captured when it closes. Use when: When finishing a Work Item, after…
git:20260924.7de8682 · audit A · 67 stars
legacy-risk-assessment SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/legacy-risk-assessment/SKILL.md · Evaluate a planned change against known legacy risks, unknowns and modernization candidates to identify which findings…
git:20260929.f89fb49 · audit A · 67 stars
module-context-refinement SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/module-context-refinement/SKILL.md · Standardize how a multirepo module's context is refined without duplicating global knowledge. Use when: When refining…
git:20260924.7de8682 · audit A · 67 stars
ownership-suggestion SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/ownership-suggestion/SKILL.md · Standardize how precise `code:` ownership globs are proposed so Guard can relate code changes to the right knowledge…
git:20260924.7de8682 · audit A · 67 stars
poc-report-writing SKILL.md skill
kaddo-kdd/kaddo · kaddo-power/skills/poc-report-writing/SKILL.md · Turn a supplied deterministic POC report context into a concise, traceable final report. Use when: After a POC has a…
git:20261009.2d71d9c · audit A · 67 stars

Every file in kaddo-kdd/kaddo

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