Collections
Collection workflow

outils pour construire des workflows d’agents | AI Agent Skills

Collection de AI Agent Skills installables pour les workflows développeur workflows développeur dans Claude Code, Cursor et Windsurf.

Cette collection met en avant les briques de workflow utilisées dans les architectures d’agents modernes. Vous y trouverez des outils pour le routage, les handoffs contextuels, les checkpoints de validation et des patterns multi-étapes réutilisables. Certaines options proposent une connectivité MCP, mais l’objectif principal reste la conception pratique de workflows pour les skills d’agents IA et le développement orienté IDE.

Primary Install Bridge

Pick One Skill, Then Take the Install Path

This collection should not trap users in comparison mode or pretend to install the whole collection. Its job is to narrow the shortlist to one skill, then send the next click into installation, validation, and rollout. Installation happens on the skill path.

Step 1 / Primary Path

Step 1: Open the installation docs

Move from workflow discovery into the install flow, validation checklist, and first command path before comparing anything else.

Open the Install Path
Best-Fit Next Paths

The Next Click Should Keep Narrowing, Not Reset Back To A Generic Directory

Once the install path is clear, move into the solution, CLI, or editorial surface that best matches this collection. That keeps platform, framework, and operations demand narrowing into a more verifiable high-intent journey.

Editorial Proof & Trust Signals

Why This Collection Deserves Priority Attention

Reviewed on 2026-04-17 against workflow fit, installation clarity, operator handoff, and repeatable execution value. This page is now positioned as an install-first workflow gateway instead of a generic tooling roundup.

We prioritize this page because workflow-intent users should move from comparison into installation, validation, and team rollout quickly. That recovery path is stronger than keeping them inside another broad repo crawl.

Trust Signals

  • - Entries are selected because they solve a concrete workflow role such as routing, approvals, handoff, or execution scaffolding.
  • - Included tools still connect cleanly to operator-facing setup docs, installation paths, or trusted workflow guidance.
  • - Selection favors repeatable delivery value over generic repository popularity or trend-driven tool lists.

Grouping Logic

  • - Lead with workflow tools that can turn routing, approvals, handoff, and execution scaffolding into one installable path.
  • - Keep the shortlist compact enough for fast comparison while still covering orchestration, reusable scaffolds, and operator checkpoints.
  • - Use installation as the bridge from workflow discovery into validated multi-step execution.

Maintenance & Review

Last Reviewed
2026-04-17
Cadence
Review monthly and whenever a workflow entry changes setup complexity, maintenance ownership, or production positioning.
Maintained By
Killer-Skills editorial review with authority-surface recovery priorities.
Verification
Each entry must still represent a concrete workflow role, remain installable, and connect cleanly to operator-facing docs or setup guidance.
Execution Examples

How These Skills Work Together In Practice

Install one workflow lane before standardizing it

Use this page when you need to shortlist one workflow stack, validate it quickly, and only then roll it out to more contributors or agents.

  1. 1. Open the installation docs before evaluating more workflow repositories.
  2. 2. Pick one scaffold or orchestration tool that matches the execution path you need now.
  3. 3. Install it and verify the CLI write path, handoff behavior, and first checkpoint.
  4. 4. Only after the base lane works, standardize it across the team.

Approval-gated automation loop

Pair automation builders with approval-aware tooling when a workflow can trigger external actions, publishing, or destructive changes.

  1. 1. Use an automation builder to connect triggers, data, and downstream actions.
  2. 2. Insert a review or approval gate before irreversible changes happen.
  3. 3. Document the validation path so operators know what to confirm after each run.

Context-rich handoff between tools

A workflow stack is most useful when handoffs preserve project state, not just payload text.

  1. 1. Define which tool owns planning, which tool executes, and which step verifies outputs.
  2. 2. Keep shared context in docs, prompts, or memory artifacts that survive handoff.
  3. 3. Send users into installation or CLI docs when the next step requires concrete environment setup.
After Installation

Supporting Moves After The Install Path Is Clear

backend-code-review

[ En vedette ]
Logo of langgenius
langgenius

The backend-code-review skill reviews Python code for quality, security, and maintainability, providing actionable fixes and suggestions. It benefits developers by improving their code and workflow.

component-refactoring

[ En vedette ]
Logo of langgenius
langgenius

La réorganisation de composants est une technique pour simplifier et optimiser les composants de logiciel complexes.

frontend-testing

[ En vedette ]
Logo of langgenius
langgenius

Cette compétence d'agent d'intelligence artificielle permet à Cursor de générer des tests de frontend de haute qualité pour le projet Dify

orpc-contract-first

[ En vedette ]
Logo of langgenius
langgenius

Guide for implementing oRPC contract-first API patterns in Dify frontend. Trigger when creating or updating contracts in web/contract, wiring router composition, integrating TanStack Query with typed contracts, migrating legacy service calls to oRPC, or deciding whether to call queryOptions directly vs extracting a helper or use-* hook in web/service.

frontend-code-review

[ En vedette ]
Logo of langgenius
langgenius

This frontend-code-review skill reviews frontend files, such as .tsx, .ts, and .js, and applies a checklist to ensure code quality, performance, and business logic, helping developers and teams maintain high standards.

frontend-query-mutation

[ En vedette ]
Logo of langgenius
langgenius

Un modèle de requête et de mutation frontend qui utilise TanStack Query et oRPC pour créer des contrats dans web/contract

create-skill

Logo of n8n-io
n8n-io

The create-skill AI agent skill automates workflows and integrates APIs for Claude Code, enhancing developer productivity. It teaches the agent focused workflows, leveraging markdown and optional scripts.

create-pr

Logo of n8n-io
n8n-io

La compétence d'agent IA 'create-pr' crée des demandes d'extraction de GitHub avec des titres formatés correctement qui passent la validation de CI

loom-transcript

Logo of n8n-io
n8n-io

Fetch and display the full transcript from a Loom video URL. Use when the user wants to get or read a Loom transcript.

reproduce-bug

Logo of n8n-io
n8n-io

Reproduce a bug from a Linear ticket with a failing test. Expects the full ticket context (title, description, comments) to be provided as input.

linear-issue

Logo of n8n-io
n8n-io

Used to download images/attachments. Typically pre-installed.

create-issue

Logo of n8n-io
n8n-io

Required for creating GitHub issues. Must be authenticated (gh auth login)

n8n-conventions

Logo of n8n-io
n8n-io

Quick reference for n8n patterns. Full docs /AGENTS.md

content-design

Logo of n8n-io
n8n-io

>

spec-driven-development

Logo of n8n-io
n8n-io

Le développement basé sur des spécifications permet une intégration plus efficace des API et des flux de données

write-docs

Logo of inkeep
inkeep

Write or update documentation for the Inkeep docs site (agents-docs package). Use when: creating new docs, modifying existing docs, introducing features that need documentation, touching MDX files in agents-docs/content/. Triggers on: docs, documentation, MDX, agents-docs, write docs, update docs, add page, new tutorial, API reference, integration guide.

ai-development-guide

Logo of shinpr
shinpr

Detects code smells, anti-patterns, and debugging issues. Use when: fixing bugs, reviewing code quality, or refactoring.

34
0
Productivité

documentation-criteria

Logo of shinpr
shinpr

Guides PRD, ADR, Design Doc, and Work Plan creation. Use when: planning features, writing specs, or creating technical documents.

35
0
Productivité

testing

Logo of shinpr
shinpr

Applies TDD process, test quality criteria, and mock guidelines. Use when: writing unit tests, using mocks, or reviewing test quality.

0
0
Développeur

worklog

Logo of tae0y
tae0y

Project template for Claude Python Vibecoding workflow

13
0
Développeur
Related Authority Collections

If This Page Is Close, Keep Narrowing With Adjacent Authority Pages

Do not reset back to the generic directory. Move sideways through these adjacent high-intent collections to narrow the shortlist toward the install path that best matches your team.

Installation Questions

Answer These Three Questions Before You Install

This collection should not keep users browsing forever. These three questions explain how to shortlist, install, and validate the next step.

Pour quels flux de travail ces collections sont-elles conçues ?

Ces collections sont conçues autour de l'automatisation de flux, processus, documents, données et piles de compétences réutilisables.

Quelle est la différence entre une collection et le répertoire principal ?

Le répertoire est meilleur pour la recherche directe, tandis que les collections regroupent des compétences complémentaires autour d'un flux complet.

Puis-je installer ces collections pour Claude Code ou Cursor ?

Oui. Les compétences de ces collections fonctionnent généralement dans Claude Code, Cursor, Windsurf et d'autres environnements via un flux d'installation unifié.

Additional Recovery Paths

Use These Additional Paths If You Need One More Step To Narrow The Decision

These are the supporting surfaces for this collection after the install direction is clear and the primary next paths have already narrowed the decision.