skill-tdd SKILL.md skillA

skill-tdd from nyldn/claude-octopus is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add nyldn/claude-octopus/skill-tdd@git:20260907.4febbb1

Pins git:20260907.4febbb1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
nyldn/claude-octopus
Path
.claude/skills/skill-tdd/SKILL.md
Versions recorded
6
Latest version
git:20260907.4febbb1, committed Sep 7, 2026
First version recorded
May 19, 2026
Size
3,233 bytes
Repository stars
4,409
License
MIT

Build a behavior change with observed red, minimal green, and measured test consolidation.

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

# Test-driven development

Read `skills/blocks/engineering-method-selection.md` from the installed plugin
for review admission. Natural-language requests and `--peer-review` share that
policy. Honor host-only requests; risk alone does not authorize paid usage.

Run the red, green, and refactor cycle on the current host. Routine TDD makes
zero additional provider dispatches. Use one external reviewer only when the
user passes `--peer-review`, explicitly requests independent review, or an
existing risk policy requires it. Explicit debate, council, and multi-model
commands retain their own execution contracts.

<HARD-GATE>
NO PRODUCTION BEHAVIOR CHANGE WITHOUT AN OBSERVED, EXPECTED FAILING TEST FIRST.
</HARD-GATE>

## The rule

Do not change production behavior until a focused test fails for the expected
reason. Existing implementation outside the requested change remains intact.

1. Name the observable behavior and the smallest public boundary that proves it.
2. Write one focused test. Directly test an internal invariant only when the
   public boundary cannot isolate its failure mode.
3. Run it and record the expected failure, command, and exit status.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add nyldn/claude-octopus/skill-tdd@sha256:fb6141e03082ae1d

The line at the top of this page pins the label git:20260907.4febbb1, 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_4tvdbgyzza64kmka.svg)](https://markdownregistry.com/a/art_4tvdbgyzza64kmka)

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

Versions

The registry has recorded 6 versions of this file, between May 19, 2026 and Sep 7, 2026, about one every 22 days.

versioncommittedcommitsizeaudit
git:20260907.4febbb1 latest2026-09-07 4febbb1 3,233 BA view · diff
git:20260906.89d2d352026-09-06 89d2d35 2,998 BA view · diff
git:20260813.14437ae2026-08-13 14437ae 9,274 BA view · diff
git:20260810.44070172026-08-10 4407017 9,228 BA view · diff
git:20260615.cf8410b2026-06-15 cf8410b 9,321 BA view · diff
git:20260519.8e7e2512026-05-19 8e7e251 8,709 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 (3233 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

nyldn/claude-octopus · 4,409 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4tvdbgyzza64kmka
GET https://markdownregistry.com/api/v1/resolve?ref=nyldn/claude-octopus/skill-tdd
GET https://markdownregistry.com/api/v1/blob/fb6141e03082ae1d4a0800157a20825d487f73578e142fc67176269a12474773

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 nyldn/claude-octopus

skill-extract SKILL.md skill
nyldn/claude-octopus · .claude/skills/extract-skill/SKILL.md · Reverse-engineer design systems, tokens, and components from live products or screenshots
git:20260813.14437ae · audit A · 4,409 stars
flow-define SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-define/SKILL.md · Multi-AI requirements scoping using available external providers (Double Diamond Define phase). Priority triggers: octo…
git:20260929.dbf6863 · audit A · 4,409 stars
flow-deliver SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-deliver/SKILL.md · Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)
git:20261108.8380d65 · audit A · 4,409 stars
flow-develop SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-develop/SKILL.md · Multi-AI implementation using available external providers (Double Diamond Develop phase). DO NOT use for simple code…
git:20261002.5c257fc · audit A · 4,409 stars
flow-discover SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-discover/SKILL.md · Multi-AI research using available external providers (Double Diamond Discover phase)
git:20260929.dbf6863 · audit A · 4,409 stars
flow-parallel SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-parallel/SKILL.md · Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
git:20261007.9f7aada · audit A · 4,409 stars
flow-spec SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-spec/SKILL.md · NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
git:20261002.5c257fc · audit A · 4,409 stars
skill-agent-topology SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-agent-topology/SKILL.md · Audit whether a multi-agent setup earns its coordination cost — use before adding an agent, or when a workflow feels…
git:20260813.14437ae · audit A · 4,409 stars
octopus-architecture SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-architecture/SKILL.md · Review system architecture, simplify boundaries, or compare interface designs from repository evidence
git:20260907.4febbb1 · audit A · 4,409 stars
skill-audit SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-audit/SKILL.md · Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
git:20260907.4febbb1 · audit A · 4,409 stars
skill-authoring SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-authoring/SKILL.md · Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in…
git:20261108.8380d65 · audit A · 4,409 stars
skill-code-review SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-code-review/SKILL.md · Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
git:20261108.8380d65 · audit A · 4,409 stars

Every file in nyldn/claude-octopus

Other files named skill-tdd

skill-tdd SKILL.md skill
nyldn/claude-octopus · skills/skill-tdd/SKILL.md · Build a behavior change with observed red, minimal green, and measured test consolidation
git:20260907.4febbb1 · audit A · 4,409 stars

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