Gestion des workflows DeepWork

VérifiéSûr

Crée et gère des workflows IA multi-étapes en définissant des spécifications de tâches, en les révisant, en générant des instructions d'étape et en apprenant des exécutions passées. Aide à structurer des tâches complexes nécessitant plusieurs étapes IA, comme les pipelines de traitement de données ou de génération de contenu.

Spar Skills Guide Bot
DeveloppementIntermédiaire
10002/06/2026
Claude Code
#workflow#automation#multi-step#jobs#deepwork

Recommandé pour

Notre avis

Crée et gère des workflows multi-étapes pour l'IA en définissant, implémentant et améliorant des jobs DeepWork.

Points forts

  • Automatisation de processus complexes via des étapes enchaînées
  • Génération interactive de spécifications de job
  • Apprentissage automatique des conversations pour améliorer les instructions
  • Invocation via outil Skill pour éviter les erreurs de copier-coller

Limites

  • Nécessite une compréhension préalable des workflows DeepWork
  • Dépend de l'outil Skill pour l'exécution correcte
  • Peut être rigide si les étapes doivent être ordonnées
Quand l'utiliser

Utilisez ce skill lorsque vous devez définir un nouveau workflow multi-étapes ou améliorer un job existant à partir de retours d'exécution.

Quand l'éviter

Ne l'utilisez pas pour des tâches simples en une étape ou lorsque vous voulez exécuter une commande isolée sans structure de workflow.

Analyse de sécurité

Sûr
Score qualité88/100

The skill orchestrates workflow management through a defined Skill tool, with no direct execution of dangerous commands or external system access. It does not instruct destructive actions, exfiltration, or obfuscation. The risk is minimal as it only guides users through creating and improving job specifications.

Aucun point d'attention détecté

Exemples

Define a new job
/deepwork_jobs define I need a workflow that first scans a codebase for TODOs, then generates a report, and finally creates issues in a tracker.
Learn from a job run
/deepwork_jobs learn Review the last conversation where we ran the 'report_gen' job and improve its instructions.
Implement from spec
/deepwork_jobs implement Generate the step instruction files for the job spec I just defined.

name: deepwork_jobs description: "Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs."

deepwork_jobs

Multi-step workflow: Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs.

CRITICAL: Always invoke steps using the Skill tool. Never copy/paste step instructions directly.

Core commands for managing DeepWork jobs. These commands help you define new multi-step workflows and learn from running them.

The define command guides you through an interactive process to create a new job by asking structured questions about your workflow, understanding each step's inputs and outputs, and generating all necessary files.

The learn command reflects on conversations where DeepWork jobs were run, identifies confusion or inefficiencies, and improves job instructions. It also captures bespoke learnings specific to the current run into AGENTS.md files in the working folder.

Available Steps

  1. define - Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow.
  2. review_job_spec - Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification. (requires: define)
  3. implement - Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes. (requires: review_job_spec)
  4. learn - Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.

Execution Instructions

Step 1: Analyze Intent

Parse any text following /deepwork_jobs to determine user intent:

  • "define" or related terms → start at deepwork_jobs.define
  • "review_job_spec" or related terms → start at deepwork_jobs.review_job_spec
  • "implement" or related terms → start at deepwork_jobs.implement
  • "learn" or related terms → start at deepwork_jobs.learn

Step 2: Invoke Starting Step

Use the Skill tool to invoke the identified starting step:

Skill tool: deepwork_jobs.define

Step 3: Continue Workflow Automatically

After each step completes:

  1. Check if there's a next step in the sequence
  2. Invoke the next step using the Skill tool
  3. Repeat until workflow is complete or user intervenes

Handling Ambiguous Intent

If user intent is unclear, use AskUserQuestion to clarify:

  • Present available steps as numbered options
  • Let user select the starting point

Guardrails

  • Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps
  • Do NOT skip steps in the workflow unless the user explicitly requests it
  • Do NOT proceed to the next step if the current step's outputs are incomplete
  • Do NOT make assumptions about user intent; ask for clarification when ambiguous

Context Files

  • Job definition: .deepwork/jobs/deepwork_jobs/job.yml
Skills similaires