Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

resolving-stack-commands

Étoiles3

Forks2

Mis à jour2 juin 2026 à 20:50

Use whenever an agent must run a toolchain command (build, test, mutation) and needs the concrete invocation. Resolves build/test/mutation commands from the detected stack so no agent hardcodes `dotnet test`, `dotnet build`, or any toolchain command. Loaded by acceptance-designer and software-engineer.

Installation

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.

Exécuter dans Manus

Source

SebastienDegodez

SebastienDegodez/meetup-coding-with-ai

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

Plus depuis ce dépôt

même dépôt

mutation-testing

SebastienDegodez/meetup-coding-with-ai

Use when running mutation testing, killing mutants, verifying test quality, checking mutation score, or analyzing survivors after the test baseline is green

2026-06-033

architecture-patterns

SebastienDegodez/meetup-coding-with-ai

Use when selecting architecture patterns for a new feature, performing Event Modeling, defining bounded contexts, choosing DDD tactical patterns, evaluating pattern fitness, or understanding how patterns compose. Covers Event Modeling methodology, DDD strategic design, DDD tactical patterns, Clean Architecture, CQRS, and Event Sourcing.

2026-06-023

architecture-review-criteria

SebastienDegodez/meetup-coding-with-ai

Use when reviewing DESIGN artefacts (event models, ADRs, component diagrams, context maps, interface contracts) for quality, DDD compliance, architectural correctness, and prohibition of negative or baseline-restating ADRs. Contains gate definitions and scoring rubric for the solution-architect-reviewer lenses.

2026-06-023

genesis

SebastienDegodez/meetup-coding-with-ai

Use this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file, orchestrator workflow) or when refactoring an existing one. Activate whenever the task asks to design, restructure, or critique an agentic module across any agent harness (Claude Code, Copilot, Cursor, OpenCode, Codex). This skill drives an 8-step disciplined design process whose output is mermaid diagrams + an interface sketch + a persisted plan that the calling thread (or a coder persona it loads) then turns into natural-language modules. Do not skip to natural-language drafting before the design artifacts exist.

2026-06-023

architecture-decisions

SebastienDegodez/meetup-coding-with-ai

Use when documenting architecture decisions as ADRs, evaluating trade-offs between alternatives, or managing the lifecycle of existing decisions. Covers ADR template, status transitions, consequence analysis, and quality criteria.

2026-05-303

test-design-mandates

SebastienDegodez/meetup-coding-with-ai

Use when designing test coverage matrices, assigning tests to Clean Architecture layers, planning the outside-in implementation order, or applying the Walking Skeleton strategy. Ensures every behaviour is tested at the right level with no redundancy. Load after writing Gherkin scenarios.

2026-05-303

name	resolving-stack-commands
description	Use whenever an agent must run a toolchain command (build, test, mutation) and needs the concrete invocation. Resolves build/test/mutation commands from the detected stack so no agent hardcodes `dotnet test`, `dotnet build`, or any toolchain command. Loaded by acceptance-designer and software-engineer.

Resolving Stack Commands (stack-agnostic)

The single place that maps a repository's stack to its concrete toolchain commands (build, test, mutation). No agent and no workflow step may hardcode a command (dotnet test, dotnet build, mvn test, pytest, ...). They resolve it here instead.

Why this exists

The pipeline must run with .NET today and other stacks tomorrow (Java planned, not yet supported). If each agent embeds dotnet test, swapping or adding a stack means editing every agent. Centralizing the mapping keeps agents tech-agnostic: they say "build the solution" / "run the test suite" / "run mutation", this skill says how.

Detection → commands

Detect the stack from markers at the repo root, then use its commands:

Stack	Detection markers	Build	Test	Mutation	Status
.NET	`.sln`, `.slnx`, `*/.csproj`, `Directory.Packages.props`	`dotnet build`	`dotnet test`	`dotnet stryker`	supported
Java	`pom.xml`, `build.gradle`, `build.gradle.kts`	(not yet provided)	(not yet provided)	(not yet provided)	NOT SUPPORTED

If multiple stacks coexist, run each supported stack's commands and aggregate results.

Unsupported stack → stop, never guess

If the detected stack has no supported command, STOP and emit a structured blocker. Never invent a command:

status: blocked
type: unsupported_stack
message: No command mapping for the detected stack
context:
  stack: java
  markers:
    - pom.xml
  needed: test

Contract for callers

Resolve the command (build / test / mutation) from the table above; do not embed it in workflow steps.
Run it, then assert on its output (build succeeds, RED on a business assertion, GREEN gate, mutation score, etc.).
Adding a stack = add a row here (or its quality-gates-<tech> adapter), with zero edits to agents.