Skip to main content Accueil Créateurs forceinjection domain-driven-design-skills literate-tests
literate-tests This skill should be used when the user asks to "create literate tests", "generate markdown tests", "specification-as-tests", "TDD with markdown", "agent-driven testing", or mentions test suites where markdown IS the test format. NOT for pytest/jest/unittest. Creates .md test files with inline assertions and uses a bundled custom test runner.
Aller à l'installation Skills Marketplace Découvrez et explorez les compétences IA créées par la communauté.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Afficher les détails du prompt Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
npx skills add https://github.com/ForceInjection/domain-driven-design-skills --skill literate-testsLa commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.
Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.
Télécharger Zip Téléchargement... Plus depuis ce dépôt Conduct deep academic research for philosophy, neuroscience, cognitive science, and theoretical computer science (computability, complexity, AI theory, logic). Use when user asks to: research academic topics, find scholarly papers, conduct literature reviews, analyze citations, synthesize research findings, explore philosophical arguments, investigate consciousness/cognition, study computability/decidability/Turing machines, or analyze academic debates. Triggers on: 'research papers', 'literature review', 'academic sources', 'scholarly articles', 'philosophy of mind', 'computability theory', 'neuroscience studies', 'find papers on', 'what does the research say'.
Create clear action plans with steps, success criteria, and risk awareness. Use before implementing features, making changes, starting projects, or anytime you need a roadmap to success. Triggers on "plan this", "how should we approach", "what's the strategy", "steps to complete", or when facing complex multi-step work.
Add keyboard navigation to a feature using CommandRegistryService. Use when implementing keyboard shortcuts, vim-style navigation, or hotkeys for a page or component.
Explorateur de fichiers
2 fichiers Métiers associés SOC
Basé sur la classification professionnelle SOC
name literate-tests description This skill should be used when the user asks to "create literate tests", "generate markdown tests", "specification-as-tests", "TDD with markdown", "agent-driven testing", or mentions test suites where markdown IS the test format. NOT for pytest/jest/unittest. Creates .md test files with inline assertions and uses a bundled custom test runner.
license MIT metadata {"author":"Ian","version":"2.3"}
Literate Test Suite Generator
Create a test suite for [DOMAIN] that an agent can run autonomously.
What This Pattern Produces
CRITICAL: This is NOT pytest/jest/unittest/etc. This creates a CUSTOM test format.
Generate two artifacts :
1. Markdown Test Files (tests/<feature>.md)
# Feature Name
Prose explaining what this tests and why.
## Test Group
### Specific Behavior
\`\` \`py
result = do_thing("input")
result.value # expect: 42
\`\`\`
### Error Case
\`\`\`py
do_ thing(None) # error: [null-input]
\`\` \`
The markdown file IS the test. Code blocks contain executable code. Comments are assertions.
2. Test Runner (language-specific)
Copy the appropriate bundled runner for your language:
Language Runner Copy Command Python run_tests.pycp "${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.py" tests/JavaScript run_tests.jscp "${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.js" tests/TypeScript run_tests.tscp "${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.ts" tests/Bash/Shell run_tests.shcp "${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.sh" tests/PowerShell run_tests.ps1cp "${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.ps1" tests/Rust run_tests.rscp "${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.rs" tests/C# RunTests.cscp "${CLAUDE_PLUGIN_ROOT}/scripts/RunTests.cs" tests/
Parse markdown files for TOML frontmatter
Extract language-specific code blocks
Validate # expect: / // expect: and # error: / // error: assertions
Support matchers: approx(), contains()
Report pass/fail with colored output
Do NOT use pytest, jest, xunit, or any standard test framework.
Why This Format Tests are the oracle for agent-driven development:
Agent runs python run_tests.py
Sees which assertions fail
Fixes the code
Repeats until green
Documentation humans can read (it's markdown!)Executable specification agents verify against This pattern enabled Simon Willison to port an entire HTML5 parser in 4.5 hours—the agent ran 9,200 tests autonomously.
File Structure project/
├── src/
│ └── <module>.<ext> # Code under test
└── tests/
├── <feature>.md # Markdown test files
└── run_tests.<ext> # Language-specific runner (copied from skill)
Markdown Test File Format
Frontmatter (Required) Must be the FIRST thing in the file:
module = "mypackage.validator"
import = ["validate" , "normalize" , "ValidationError" ]
isolation = "per-block"
Error Code Index (Required) List ALL error codes at the top, before any tests:
**Error codes:**
- `[empty-input]` — User provided empty string
- `[null-input]` — User provided null/None
- `[invalid-format]` — String doesn't match expected pattern
Test Sections Headers create test groups. Prose explains intent. Code blocks are tests:
## Input Validation
Users paste data from spreadsheets which may contain invisible whitespace.
The validator normalizes input before checking length.
### Accepts Valid Input
\`\` \`py
validate("hello") # expect: True
\`\` \`
### Rejects Empty String
Empty means "user submitted nothing" — distinct from whitespace-only:
\`\` \`py
validate("") # error: [empty-input]
\`\` \`
Assertion Syntax
Value Assertions The line before # expect: must be an evaluable expression , not a statement.
result = calculate(10 )
result.value
Error Assertions statement
statement
statement
Matchers For non-exact comparisons:
CLI/Shell Tests
Using the Bundled Runners
Python Runner cp "${CLAUDE_PLUGIN_ROOT} /scripts/run_tests.py" tests/
python tests/run_tests.py
Code blocks: ```py or ```python
Assertions: # expect:, # error:
JavaScript Runner cp "${CLAUDE_PLUGIN_ROOT} /scripts/run_tests.js" tests/
node tests/run_tests.js
Code blocks: ```js or ```javascript
Assertions: // expect:, // error:, // throws:
TypeScript Runner Requires: npm install -D tsx
cp "${CLAUDE_PLUGIN_ROOT} /scripts/run_tests.ts" tests/
npx tsx tests/run_tests.ts
Code blocks: ```ts or ```typescript
Assertions: // expect:, // error:, // throws:
Bash Runner cp "${CLAUDE_PLUGIN_ROOT} /scripts/run_tests.sh" tests/
bash tests/run_tests.sh
Code blocks: ```sh or ```bash
Assertions: # exit:, # stdout:, # stderr:
PowerShell Runner cp "${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.ps1" tests/
pwsh tests/run_tests.ps1
Code blocks: ```ps1 or ```powershell
Assertions: # exit:, # stdout:, # stderr:, # throws:
Rust Runner Requires: cargo install rust-script
cp "${CLAUDE_PLUGIN_ROOT} /scripts/run_tests.rs" tests/
rust-script tests/run_tests.rs
Code blocks: ```rs or ```rust
Assertions: // expect:, // error:, // compiles, // compile_fails:
C# Runner Requires: dotnet tool install -g dotnet-script
cp "${CLAUDE_PLUGIN_ROOT} /scripts/RunTests.cs" tests/
dotnet script tests/RunTests.cs
Code blocks: ```cs or ```csharp
Assertions: // expect:, // error:
Error Identity (Critical) Every error must have a stable code the runner can match:
Language How to Expose Code Python Exception with .code property Rust Error enum variant CLI [code] in stderr + exit codeC# Exception type name
Example Python exception:
class ValidationError (Exception ):
def __init__ (self, code: str , message: str ):
self .code = code
super ().__init__(message)
raise ValidationError("empty-input" , "Input cannot be empty" )
The runner matches # error: [empty-input] against exception.code.
Example: Complete Test File
module = "temperature"
import = ["celsius_to_fahrenheit" , "TemperatureError" ]
isolation = "per-block"
Temperature Conversion Converts between Celsius and Fahrenheit with validation.
Problem: Users need temperature conversion, but invalid inputs (below
absolute zero) must fail clearly—not return nonsense values.
[below-absolute-zero] — Temperature violates laws of physics
Celsius to Fahrenheit Standard formula: F = (C × 9/5) + 32
Converts Freezing Point
Converts Boiling Point celsius_to_fahrenheit(100 )
Rejects Below Absolute Zero -273.15°C is the physical limit. Below that is impossible:
celsius_to_fahrenheit(-300 )
Checklist Before Generating When asked to create literate tests:
Domain Spec Template
What it does: [DESCRIPTION]What problem it solves: [USER PAIN]Language: [LANGUAGE]Code block tag: [py/rs/sh/etc]Comment prefix: [#/////--]Error codes: [EXHAUSTIVE LIST]Public API: [FUNCTIONS TO TEST]Happy paths: [LIST]Error cases: [LIST + WHY]Edge cases: [LIST + WHY] 