feature-slicing SKILL.md skillA

feature-slicing from hamza-ali-shahjahan/hamzaish is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hamza-ali-shahjahan/hamzaish/feature-slicing@git:20260721.96f6808

Pins git:20260721.96f6808 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hamza-ali-shahjahan/hamzaish
Path
factory/skills/feature-slicing/SKILL.md
Versions recorded
2
Latest version
git:20260721.96f6808, committed Jul 21, 2026
First version recorded
Jun 28, 2026
Size
3,871 bytes
Repository stars
10
License
MIT

Slice a goal into the smallest feature slices that can each be PROVEN — every slice ships with a named eval and an end-to-end test, and a slice you can't evaluate or test doesn't get selected. Use after the goal is set and before the spec, so only provable features make the build.

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

# /feature-slicing

Usage: `/feature-slicing <the goal, or what "done" looks like>`

A feature you can't evaluate is a guess. A feature you can't test end-to-end is a hope. This skill turns a goal into a short list of **vertical slices** — each a thin, shippable piece of the goal — and **keeps only the slices that come with a way to prove them.** It runs after the goal is pinned (`/write-a-goal`, or a one-line acceptance) and before `/spec`, so the spec describes provable features, not a wishlist.

## The rule

> If you can't name the eval and the end-to-end test for a slice, it doesn't get built yet.

That's the whole discipline. A slice with no eval is either too vague (sharpen it) or not actually part of the goal (drop it). The selection gate is **provability**, not enthusiasm.

## The method

1. **Cut vertically, not by layer.** A slice is a thin end-to-end thing a user can actually do — not "the database layer." Aim for the smallest slice that moves the goal's metric.
2. **For each candidate slice, write three things up front:**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hamza-ali-shahjahan/hamzaish/feature-slicing@sha256:7b783ef20c0cf5b7

The line at the top of this page pins the label git:20260721.96f6808, 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_ii2v2yyojx4tdrpk.svg)](https://markdownregistry.com/a/art_ii2v2yyojx4tdrpk)

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

Versions

The registry has recorded 2 versions of this file, between Jun 28, 2026 and Jul 21, 2026, about one every 23 days.

versioncommittedcommitsizeaudit
git:20260721.96f6808 latest2026-07-21 96f6808 3,871 BA view · diff
git:20260628.4d346922026-06-28 4d34692 3,335 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 (3871 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

hamza-ali-shahjahan/hamzaish · 10 stars · license MIT · pushed 2026-10-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ii2v2yyojx4tdrpk
GET https://markdownregistry.com/api/v1/resolve?ref=hamza-ali-shahjahan/hamzaish/feature-slicing
GET https://markdownregistry.com/api/v1/blob/7b783ef20c0cf5b7d9e1989ba5310ebf937a9bcf75d71cd56cc04ddf3309b497

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 hamza-ali-shahjahan/hamzaish

hamzaish Cursor rule
hamza-ali-shahjahan/hamzaish · .cursor/rules/hamzaish.mdc · Hamzaish factory — universal operating context for any agent working in this repo
git:20260614.1c0c7ab · audit A · 10 stars
AGENTS.md AGENTS.md file
hamza-ali-shahjahan/hamzaish · AGENTS.md
git:20260921.82b1475 · audit A · 10 stars
CLAUDE.md CLAUDE.md file
hamza-ali-shahjahan/hamzaish · CLAUDE.md
git:20261007.6b62766 · audit A · 10 stars
CLAUDE.md@_archive/v0 CLAUDE.md file
hamza-ali-shahjahan/hamzaish · _archive/v0/CLAUDE.md
git:20260528.a4e7dfe · audit A · 10 stars
hamzaish-orchestrator SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/_orchestrator/SKILL.md · Top-level routing brain. Given any user request, identifies the product + stage + intent, then routes to the right…
git:20260528.a4e7dfe · audit A · 10 stars
competitor-mapper SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/competitor-mapper/SKILL.md · Map the competitive landscape by tier (direct/indirect/acquirer/adjacent) and argue why each could win. Antidote to…
git:20260528.a4e7dfe · audit A · 10 stars
customer-discovery SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/customer-discovery/SKILL.md · Plan customer discovery — define target profile, build prospect list, draft interview script, set up outreach +…
git:20260528.a4e7dfe · audit A · 10 stars
devils-advocate SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/devils-advocate/SKILL.md · Stress-test an idea or hypothesis. Build the strongest possible case AGAINST it, find disconfirming evidence, and…
git:20260528.a4e7dfe · audit A · 10 stars
idea-generator SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/idea-generator/SKILL.md · Generate startup ideas grounded in Hamza's existing patterns, current trends, and validated demand signals. Never just…
git:20260528.a4e7dfe · audit A · 10 stars
interview-synthesizer SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/interview-synthesizer/SKILL.md · Synthesize a batch of customer interviews into evidence-for + evidence-against the hypothesis, with pattern surfacing…
git:20260528.a4e7dfe · audit A · 10 stars
market-researcher SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/market-researcher/SKILL.md · Build TAM/SAM/SOM, market trends, buyer landscape — anchored in citable public data, not vibes.
git:20260528.a4e7dfe · audit A · 10 stars
problem-sharpener SKILL.md skill
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/problem-sharpener/SKILL.md · Turn vague problem observations into testable hypothesis statements with specific who/when/severity/current-workaround…
git:20260528.a4e7dfe · audit A · 10 stars

Every file in hamza-ali-shahjahan/hamzaish

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