Home / stempeck / agentfactory · internal/cmd/install_skills/six-sigma-challenge/SKILL.md · GitHub

six-sigma-challenge skillA

six-sigma-challenge is agent-read markdown (skill) from stempeck/agentfactory: Challenges the quality of any completed review or assessment to determine what would achieve six-sigma (99.9999%) quality outcome. Works with scored reviews (X/10), qualitative reviews (PASS/FAIL), or unstructured assessments. Identifies gaps, independently discovers missed issues, stress-tests each proposed improvement for feasibility including logical impossibilities, and appends a "Six-Sigma Caveats" section. Use when a review is less than perfect, when the user asks "what would make this per.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Six-Sigma Challenge

Challenge any quality assessment to find the gap between current outcome and perfection.

## Inputs

| Input | Required | Source |
|-------|----------|--------|
| Review file | Yes | First argument, or `todos/ultra-implement/blind_review.md` |
| Target document | Yes | Second argument, or auto-detected (see below) |

**Invocation**: `/six-sigma-challenge <review-file> <target-document>`
**Default**: `/six-sigma-challenge` (uses ultra-implement defaults)

**Auto-detection for target document** (when no second argument):
1. Read `todos/ultra-implement/investigation_report.md` and extract the `Problem File:` path
2. If that file exists, use it as the target document
3. Fallback: `todos/ultra-implement/COMPLETION.md`

This ensures the caveats append to the original problem file regardless of what `/ultra-implement` was invoked with.

## Phase 1: Extract Quality Gaps

Read the review file. Identify every area where the outcome falls short of perfection.

**For scored reviews** (X/10 criteria): Record each criterion below 10/10, the deficit, and the reviewer's reasoning. Rank by deficit size.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add stempeck/agentfactory/six-sigma-challenge@git:20260628.34d8187
Exact content
mdr add stempeck/agentfactory/six-sigma-challenge@sha256:33eadc246b0c0d08

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_oplohvgoxzbgo7fi.svg)](https://markdownregistry.com/a/art_oplohvgoxzbgo7fi)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260628.34d8187 latest2026-06-28 34d8187 8,059 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (8059 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

stempeck/agentfactory · 3 stars · license AGPL-3.0 · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_oplohvgoxzbgo7fi
GET https://markdownregistry.com/api/v1/resolve?ref=stempeck/agentfactory/six-sigma-challenge
GET https://markdownregistry.com/api/v1/blob/33eadc246b0c0d08b72f1e47baa070abff1e6f25d3ed09da42d8f3b2d931953f

Your agent 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.

More from stempeck/agentfactory

CLAUDE.md@.agentfactory/agents/design-plan-impl claude
stempeck/agentfactory · .agentfactory/agents/design-plan-impl/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/design-v3 claude
stempeck/agentfactory · .agentfactory/agents/design-v3/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/design-v7 claude
stempeck/agentfactory · .agentfactory/agents/design-v7/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/design claude
stempeck/agentfactory · .agentfactory/agents/design/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/fable-implement claude
stempeck/agentfactory · .agentfactory/agents/fable-implement/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/fable-increment claude
stempeck/agentfactory · .agentfactory/agents/fable-increment/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/fable-review claude
stempeck/agentfactory · .agentfactory/agents/fable-review/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/fable-secure claude
stempeck/agentfactory · .agentfactory/agents/fable-secure/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/factoryworker claude
stempeck/agentfactory · .agentfactory/agents/factoryworker/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/gherkin-breakdown claude
stempeck/agentfactory · .agentfactory/agents/gherkin-breakdown/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/github-issue claude
stempeck/agentfactory · .agentfactory/agents/github-issue/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars
CLAUDE.md@.agentfactory/agents/gpt-fable-review claude
stempeck/agentfactory · .agentfactory/agents/gpt-fable-review/CLAUDE.md
git:20260916.8d1a006 · audit A · 3 stars

Every file in stempeck/agentfactory

Other files named six-sigma-challenge

six-sigma-challenge skill
stempeck/agentfactory · .claude/skills/six-sigma-challenge/SKILL.md · Challenges the quality of any completed review or assessment to determine what would achieve six-sigma (99.9999%)…
git:20260628.34d8187 · audit A · 3 stars

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