/workflow

name: workflow
description: "Structured multi-phase workflows: review, debug, refactor (tidy, clean up, untangle messy code without behaviour change), deploy, create, research."
user-invocable: false
context: fork
routing:
  category: meta-tooling
  not_for: "3D game asset generation or Meshy API (use game-asset-generator skill) — this skill orchestrates multi-step ad-hoc workflows"
  pairs_with:
    - planning
    - feature-lifecycle
    - verification-before-completion
  triggers:
    - "workflow"
    - "multi-phase task"
    - "structured pipeline"
    - "phased execution"
    - "orchestrated workflow"
    - "tidy up"
    - "tidy it"
    - "tidy into one place"
    - "clean up"
    - "messy"
    - "messy code"
    - "structure is messy"
    - "reorganize"
    - "reorganize without changing behaviour"
    - "reorganize without changing behavior"
    - "untangle"
    - "consolidate duplicated"
    - "duplicated everywhere"
    - "repeated everywhere"
allowed-tools:
  - Read
  - Edit
  - Write
  - Bash
  - Glob
  - Grep
  - Agent
  - Skill

Workflow

Umbrella skill for all structured multi-phase workflows. Load the appropriate workflow reference based on the task.

**Terminology:** "workflow" is the canonical term for these flows. "pipeline" is the retained legacy alias — kept for back-compat. Routing keys, `meta.name` exports, and `pipeline-index.json` keep their existing "pipeline" identifiers unchanged; do not rename them. Use "workflow" in new prose.

Available Workflows

| Category | Workflow | Reference | |----------|----------|-----------| | **Code Review** | Comprehensive multi-wave review | `references/comprehensive-review.md` | | **Code Review** | Systematic code review | `skills/review/systematic-code-review/SKILL.md` | | **Debugging** | Evidence-based debugging pipeline | `references/systematic-debugging.md` | | **Refactoring** | Safe refactoring with test gates | `references/systematic-refactoring.md` | | **Features** | End-to-end feature lifecycle | `skills/process/feature-lifecycle/references/pipeline.md` | | **PR Workflow** | PR creation pipeline | `skills/process/pr-workflow/references/pipeline.md` | | **Research** | Formal research with source gates | `references/research-pipeline.md` | | **Research** | Research to article pipeline | `references/research-to-article.md` | | **Content** | Voice content generation | `references/voice-writer.md` | | **Content** | Article evaluation | `references/article-evaluation-pipeline.md` | | **Content** | De-AI content pipeline | `references/de-ai-pipeline.md` | | **Content** | Documentation pipeline | `references/doc-pipeline.md` | | **Exploration** | Codebase exploration | `references/explore-pipeline.md` | | **Exploration** | Multi-perspective analysis | `references/do-perspectives.md` | | **Creation** | Skill creation pipeline | `references/skill-creation-pipeline.md` | | **Creation** | Hook development pipeline | `references/hook-development-pipeline.md` | | **Creation** | MCP server pipeline | `references/mcp-pipeline-builder.md` | | **Creation** | Pipeline scaffolding | `references/pipeline-scaffolder.md` | | **Creation** | Domain research for pipelines | `references/domain-research.md` | | **Creation** | Chain composition | `references/chain-composer.md` | | **Creation** | Auto-pipeline generation | `references/auto-pipeline.md` | | **Upgrade** | Agent/skill upgrade | `references/agent-upgrade.md` | | **Upgrade** | System upgrade | `references/system-upgrade.md` | | **Upgrade** | Toolkit improvement | `references/toolkit-improvement.md` | | **Testing** | Pipeline test runner | `references/pipeline-test-runner.md` | | **Testing** | Pipeline retro | `references/pipeline-retro.md` | | **GitHub** | Profile rules extraction | `references/github-profile-rules.md` | | **Orchestration** | Task orchestration | `references/workflow-orchestrator.md` | | **Patterns** | Composable-pattern + failure-mode + cost-gate catalog | `references/workflow-patterns.md` | | **Patterns** | Tournament (pairwise-comparison) template | `references/tournament-workflow.md` | | **Patterns** | Quarantine (untrusted-source triage isolation) | `references/quarantine-pattern.md` | | **Orchestration** | DAG-based multi-skill composition patterns | `references/dag-composition-patterns.md` | | **Orchestration** | Skill compatibility matrix for chaining | `references/dag-compatibility-matrix.md` | | **Orchestration** | Common DAG skill patterns | `references/dag-skill-patterns.md` | | **Orchestration** | DAG orchestration worked examples (standard sequential/parallel compositions) | `references/dag-orchestration-examples.md` | | **Orchestration** | Error recovery, circular-dependency detection, adaptive/nested composition, performance metrics | `references/dag-orchestration-advanced.md` |

How to Use (MANDATORY)

**You MUST load the named target before executing any workflow phase.** The table above is a routing index — the actual methodology, phases, gates, and instructions are in its references or standalone skills.

1. **Identify** the workflow category from the user's task using the table above 2. **Load** the matching target. `references/...` paths resolve under `${CLAUDE_SKILL_DIR}`; `skills/.../SKILL.md` paths are standalone public skills rooted at the repository. 3. **Follow** the phases and gates defined in that reference exactly — do not improvise phases 4. **Report** using the output format specified in the loaded reference

If the task spans multiple workflows (e.g., research then write), load each reference in sequence and follow them in order.

**Workflow rule**: Load the named target before executing a workflow phase. The table shows names only; the target contains the actual instructions, gates, artifact requirements, and quality criteria.

Reference Loading Table

| Signal | Load These Files | Why | |---|---|---| | **Code Review** | `comprehensive-review.md` | Comprehensive multi-wave review | | **Code Review** | `skills/review/sy