Home / shinpr / claude-code-workflows · skills/recipe-diagnose/SKILL.md · GitHub

recipe-diagnose skillA

recipe-diagnose is agent-read markdown (skill) from shinpr/claude-code-workflows: Investigate problem, verify findings, and derive solutions.

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

**Explicit User Instruction**: The user explicitly instructs and authorizes every subagent call named in this recipe. Execute each applicable call when its prerequisites are met.

Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts.
Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.

**Context**: Diagnosis flow to identify root cause and present solutions

Target problem: $ARGUMENTS

## Orchestrator Definition

**Core Identity**: "I am an orchestrator."

**Local authority gate**: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist.

**Execution Method**:
- Investigation → performed by investigator
- Verification → performed by verifier
- Solution derivation → performed by solver

Orchestrator invokes sub-agents and passes structured JSON between them.

At each Agent invocation below, build the prompt as a mechanical extraction: copy the named source values into the exact fields, apply only the declared serialization, then invoke immediately.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add shinpr/claude-code-workflows/recipe-diagnose@git:20260912.9d2129b
Exact content
mdr add shinpr/claude-code-workflows/recipe-diagnose@sha256:d5f1af29dc0fc48f

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_3qw7xqhhwglwv55o.svg)](https://markdownregistry.com/a/art_3qw7xqhhwglwv55o)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260912.9d2129b latest2026-09-12 9d2129b 10,871 BA view · diff
git:20260912.597a4122026-09-12 597a412 11,989 BA view · diff
git:20260827.75012a32026-08-27 75012a3 12,689 BA view · diff
git:20260818.ca7ff692026-08-18 ca7ff69 12,766 BA view · diff
git:20260809.61960dc2026-08-09 61960dc 12,462 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 (10871 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

shinpr/claude-code-workflows · 684 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3qw7xqhhwglwv55o
GET https://markdownregistry.com/api/v1/resolve?ref=shinpr/claude-code-workflows/recipe-diagnose
GET https://markdownregistry.com/api/v1/blob/d5f1af29dc0fc48f69c6f8e3501e93243827411751927506b0e31ca2a558b530

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 shinpr/claude-code-workflows

ai-development-guide skill
shinpr/claude-code-workflows · dev-skills/skills/ai-development-guide/SKILL.md · Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality…
git:20260827.75012a3 · audit A · 684 stars
coding-principles skill
shinpr/claude-code-workflows · dev-skills/skills/coding-principles/SKILL.md · Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features…
git:20260922.7c4e3a7 · audit A · 684 stars
documentation-criteria skill
shinpr/claude-code-workflows · dev-skills/skills/documentation-criteria/SKILL.md · Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when…
git:20260915.b4b5611 · audit A · 684 stars
external-resource-context skill
shinpr/claude-code-workflows · dev-skills/skills/external-resource-context/SKILL.md · Records where resources outside the repository live (design source, design system, API schema, IaC source, secret…
git:20260809.6130272 · audit A · 684 stars
frontend-ai-guide skill
shinpr/claude-code-workflows · dev-skills/skills/frontend-ai-guide/SKILL.md · Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality…
git:20260906.fbff90d · audit A · 684 stars
implementation-approach skill
shinpr/claude-code-workflows · dev-skills/skills/implementation-approach/SKILL.md · Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach…
git:20260827.75012a3 · audit A · 684 stars
integration-e2e-testing skill
shinpr/claude-code-workflows · dev-skills/skills/integration-e2e-testing/SKILL.md · Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when…
git:20260905.82cde5e · audit A · 684 stars
llm-friendly-context skill
shinpr/claude-code-workflows · dev-skills/skills/llm-friendly-context/SKILL.md · Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute…
git:20260917.73d4471 · audit A · 684 stars
requirement-convergence skill
shinpr/claude-code-workflows · dev-skills/skills/requirement-convergence/SKILL.md · Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded…
git:20260917.c5b7fa6 · audit A · 684 stars
test-implement skill
shinpr/claude-code-workflows · dev-skills/skills/test-implement/SKILL.md · Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks…
git:20260806.d8a29d4 · audit A · 684 stars
testing-principles skill
shinpr/claude-code-workflows · dev-skills/skills/testing-principles/SKILL.md · Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use…
git:20260809.6130272 · audit A · 684 stars
typescript-rules skill
shinpr/claude-code-workflows · dev-skills/skills/typescript-rules/SKILL.md · React/TypeScript frontend development rules including type safety, component design, state management, and error…
git:20260728.e9e235b · audit A · 684 stars

Every file in shinpr/claude-code-workflows

Other files named recipe-diagnose

recipe-diagnose skill
shinpr/claude-code-workflows · dev-workflows-frontend/skills/recipe-diagnose/SKILL.md · Investigate problem, verify findings, and derive solutions
git:20260912.9d2129b · audit A · 684 stars
recipe-diagnose skill
shinpr/claude-code-workflows · dev-workflows-fullstack/skills/recipe-diagnose/SKILL.md · Investigate problem, verify findings, and derive solutions
git:20260912.9d2129b · audit A · 684 stars
recipe-diagnose skill
shinpr/claude-code-workflows · dev-workflows/skills/recipe-diagnose/SKILL.md · Investigate problem, verify findings, and derive solutions
git:20260912.9d2129b · audit A · 684 stars
recipe-diagnose skill
shinpr/codex-workflows · .agents/skills/recipe-diagnose/SKILL.md · Investigate problem, verify findings, and derive solutions through structured diagnosis.
git:20260915.0c8f517 · audit A · 38 stars

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