slice SKILL.md skillA

slice from thoughtbot/rails-consultant is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add thoughtbot/rails-consultant/slice@git:20261106.7724c75

Pins git:20261106.7724c75 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
thoughtbot/rails-consultant
Path
skills/slice/SKILL.md
Versions recorded
7
Latest version
git:20261106.7724c75, committed Nov 6, 2026
First version recorded
Mar 13, 2026
Size
16,544 bytes
Repository stars
29
License
MIT

Cut a feature or idea down to one full-stack slice.

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

# Full-stack slice SPEC

A full-stack slice cuts vertically through every layer a feature needs: storage, logic, interface, integration. It ships on its own, and a user gets something they couldn't get before. The opposite is a horizontal slice ("add the schema", "build the API", "design the UI"), which ships nothing anyone can use and hides the integration pain until the end.

Full stack means whatever this project's fullest stack is. For a web app, storage through to screen. For a CLI, argument parsing through to printed output. Let the repo tell you its layers instead of assuming.

The job is finding the version that costs a fraction of the work and is still worth shipping. The SPEC goes to a session that has none of this conversation, so it has to stand alone.

## Workflow

Arguments start with `--auto`? Nobody will answer. Read [Autonomous mode](#autonomous-mode) first; it replaces the interview and both gates below.

1. Capture the raw idea in the user's words.
2. Recon the codebase with subagents. Wait for them; the interview depends on what they find.
3. Run the interview to cut scope.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add thoughtbot/rails-consultant/slice@sha256:af15c4fb76bedab6

The line at the top of this page pins the label git:20261106.7724c75, 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_cfox4j7op5vqgi5t.svg)](https://markdownregistry.com/a/art_cfox4j7op5vqgi5t)

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

Versions

The registry has recorded 7 versions of this file, between Mar 13, 2026 and Nov 6, 2026, about one every 40 days.

versioncommittedcommitsizeaudit
git:20261106.7724c75 latest2026-11-06 7724c75 16,544 BA view · diff
git:20261106.ce8ab682026-11-06 ce8ab68 16,264 BA view · diff
git:20260730.98073062026-07-30 9807306 9,493 BA view · diff
git:20260730.4e2addb2026-07-30 4e2addb 9,585 BA view · diff
git:20260321.313cfaa2026-03-21 313cfaa 7,268 BA view · diff
git:20260320.77739d32026-03-20 77739d3 6,306 BA view · diff
git:20260313.e2ed4a02026-03-13 e2ed4a0 4,567 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 (16544 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

thoughtbot/rails-consultant · 29 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cfox4j7op5vqgi5t
GET https://markdownregistry.com/api/v1/resolve?ref=thoughtbot/rails-consultant/slice
GET https://markdownregistry.com/api/v1/blob/af15c4fb76bedab63c745069408fc438aca1577f57c10625dcb796217a8f9387

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 thoughtbot/rails-consultant

ask-claude SKILL.md skill
thoughtbot/rails-consultant · skills/ask-claude/SKILL.md · Recommend the best way to have Claude do something, checked against Anthropic's current docs, then write the prompt and…
git:20261106.ce8ab68 · audit A · 29 stars
commit SKILL.md skill
thoughtbot/rails-consultant · skills/commit/SKILL.md · Commit the current changes as atomic commits, recording risks, tradeoffs, and alternatives considered.
git:20261106.7724c75 · audit A · 29 stars
diff-explainer SKILL.md skill
thoughtbot/rails-consultant · skills/diff-explainer/SKILL.md · Builds a shareable HTML walkthrough of the current changes, highlighting risks, tradeoffs, and alternatives considered.
git:20261106.5b1536c · audit A · 29 stars
domain-model SKILL.md skill
thoughtbot/rails-consultant · skills/domain-model/SKILL.md · Turn a described business process into a domain model.
git:20261106.ce8ab68 · audit A · 29 stars
eli5 SKILL.md skill
thoughtbot/rails-consultant · skills/eli5/SKILL.md · Explain something to someone who knows nothing about it.
git:20261106.ce8ab68 · audit A · 29 stars
implement-with-tdd SKILL.md skill
thoughtbot/rails-consultant · skills/implement-with-tdd/SKILL.md · Implement a SPEC, plan, or feature outside-in, with TDD.
git:20261106.ce8ab68 · audit A · 29 stars
multi-lens-review SKILL.md skill
thoughtbot/rails-consultant · skills/multi-lens-review/SKILL.md · Review a change for defects, then against its spec, its codebase's conventions, the domains trying to emerge from it…
git:20261106.ce8ab68 · audit A · 29 stars
pr SKILL.md skill
thoughtbot/rails-consultant · skills/pr/SKILL.md · Open a pull request whose description you write yourself, with a suggested title and a light proofread.
git:20261106.7724c75 · audit A · 29 stars
preparatory-refactor SKILL.md skill
thoughtbot/rails-consultant · skills/preparatory-refactor/SKILL.md · Identify opportunities to introduce a refactor that would make a feature easy to implement.
git:20261106.ce8ab68 · audit A · 29 stars
risk-score SKILL.md skill
thoughtbot/rails-consultant · skills/risk-score/SKILL.md · Score how risky a pull request or branch is with fixed rules, and reply with the result as JSON. Use when asked how…
git:20261106.ce8ab68 · audit A · 29 stars
rubber-duck SKILL.md skill
thoughtbot/rails-consultant · skills/rubber-duck/SKILL.md · Start a rubber duck session.
git:20261106.ce8ab68 · audit A · 29 stars
ship SKILL.md skill
thoughtbot/rails-consultant · skills/ship/SKILL.md · Implement, verify and review a feature based on its SPEC, then open a draft PR.
git:20261106.ce8ab68 · audit A · 29 stars

Every file in thoughtbot/rails-consultant

Other files named slice

slice SKILL.md skill
stevepolitodesign/skills · slice/SKILL.md · Cut a feature or idea down to one full-stack slice.
git:20261105.0b5f9f2 · audit A · 10 stars

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