跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs

shinpr · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add shinpr/claude-code-workflows --skill recipe-add-integration-tests

技能说明


name: recipe-add-integration-tests description: Add integration/E2E tests to existing codebase using Design Docs disable-model-invocation: true

Explicit User Instruction: The user explicitly instructs and authorizes every subagent call named in this recipe. Execute each applicable call when its prerequisites are met.

Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.

Context: Test addition workflow for existing implementations (backend, frontend, or fullstack)

Orchestrator Definition

Core Identity: "I am an orchestrator."

Local authority gate: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist.

Review Resolution Gate [MANDATORY]: Resolve every actionable deliverable-review finding through subagents-orchestration-guide Review Resolution before correction or progression. Before the first finding disposition, read references/review-resolution.md from the loaded subagents-orchestration-guide skill.

Execution Gate: Complete Steps 1-7 in order for each generated layer. Advance only through the current step's stated output or response gate; skip work only when its stated condition is false. Report completion after every layer has completed its review, quality, commit, and retained-limitation retry.

Why Delegate: Orchestrator's context is shared across all steps. Direct implementation consumes context needed for review and quality check phases. Subagents work in isolated context.

Execution Method:

  • Skeleton generation → delegate to acceptance-test-generator
  • Test implementation → delegate to task-executor
  • Test review → delegate to integration-test-reviewer
  • Quality checks → delegate to quality-fixer

At each Agent invocation below, build the prompt as a mechanical extraction: copy the named source values into the exact fields, apply only the declared serialization, then invoke immediately.

Document paths: $ARGUMENTS

Prerequisites

  • At least one Design Doc must exist (created manually or via reverse-engineer)
  • Existing implementation to test

Execution Flow

Step 1: Discover and Validate Documents

Resolve the documents named by $ARGUMENTS; when a supplied path is stale, use repository evidence to locate its intended artifact. Use the requested feature and layers as the discovery boundary. Resolve applicable Design Docs and UI Specs/PRDs within that boundary, including same-feature frontend/backend counterparts when fullstack work is requested, even when the named document does not link them. Use feature identity, governing requirements, and implementation ownership to establish relevance; stop once the requested layers and proof boundaries are covered. An explicitly single-layer request remains single-layer. Classify documents from their content and references; filenames are hints. Report an exact missing prerequisite when no applicable Design Doc can be resolved.

Step 2: Skeleton Generation

Invoke acceptance-test-generator using Agent tool:

  • subagent_type: "dev-workflows-fullstack:acceptance-test-generator"
  • description: "Generate test skeletons"
  • design_docs: Existing backend, frontend, or single-layer Design Doc paths from Step 1
  • ui_spec: Existing UI Spec path when present
  • requirement_context: Approved PRD path or unchanged Design Doc Requirement Convergence record

Follow subagents-orchestration-guide HC-06 to verify generated paths and coverage of empty lanes before Step 3.

Expected output: generatedFiles containing integration and e2e paths

Step 3: Test Implementation

For each layer with generated skeletons, record the current HEAD as diffBase, then invoke the layer's task-executor:

  • Backend or single-layer → subagent_type: "dev-workflows-fullstack:task-executor"
  • Frontend → subagent_type: "dev-workflows-fullstack:task-executor-frontend"
  • description: "Implement integration tests"
  • direct_scope: Implement every test defined by the layer-specific generated skeletons
  • governing_sources: Layer-specific Design Doc, applicable UI Spec, and generated skeleton paths
  • target_paths: Generated test paths plus the existing setup or fixture paths explicitly identified before invocation
  • observable_verification: Execute the implemented tests and verify every skeleton claim at its declared boundary

Execute one layer at a time through Steps 3→4→5→6→7 before starting the next.

Expected output: status, testsAdded, mutationEvidence

Apply this response gate after every task-executor invocation in Steps 3 and 5:

  • At least one changed integration/E2E test file and its implementation evidence are confirmed from the response and repository state → Proceed to Step 4
  • Required implementation remains incomplete → Apply Specialist Result Acceptance and continue Step 3 while repository evidence supplies an advancing action
  • Other result variations → Apply subagents-orchestration-guide Specialist Result Acceptance

Step 4: Test Review

Invoke integration-test-reviewer using Agent tool:

  • subagent_type: "dev-workflows-fullstack:integration-test-reviewer"
  • description: "Review test quality"
  • prompt: "Review test quality. changedTestFiles: [confirmed changed integration/E2E test paths]. diffBase: [revision recorded before Step 3]. skeletonFiles: [layer-specific paths from Step 2 generatedFiles]. mutationEvidence: [Step 3 mutationEvidence]."

Expected output: status (pass/needs_revision/blocked), testFiles, reviewBasis, qualityIssues; correction re-review also returns prior_feedback_reconciliation

Step 5: Apply Review Fixes

Check Step 4 result:

  • status: pass → Mark complete, proceed to Step 6
  • status: blocked → Apply Specialist Result Acceptance
  • status: needs_revision → P
阅读完整来源 ↗