메뉴
Implement features from task specifications using Test-Driven Development (TDD) with bmad-commands for file operations and testing. This skill should be used when implementing new functionality from approved task specs.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/adolfoaranaes12/BMAD-ENHANCED --skill implement-feature명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Comprehensive brownfield architecture analysis for existing codebases. Discovers structure, identifies patterns, assesses quality, calculates production readiness, and provides actionable recommendations. Use when analyzing existing codebases to understand architecture, assess quality, or prepare for modernization.
Systematically consume QA quality gate outputs and apply prioritized fixes for high-severity issues, NFR failures, and test coverage gaps. Use when quality review identifies issues requiring remediation.
Peer review architecture for quality, risks, and optimization opportunities. Analyzes scalability bottlenecks, security vulnerabilities, performance optimization, technology fit, and provides prioritized recommendations. Use when reviewing proposed architecture documents for quality assurance, risk identification, or architectural decision validation.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | implement-feature |
| description | Implement features from task specifications using Test-Driven Development (TDD) with bmad-commands for file operations and testing. This skill should be used when implementing new functionality from approved task specs. |
| acceptance | [{"tests_passing":"All tests must pass"},{"coverage_threshold":"Test coverage >= 80%"},{"no_syntax_errors":"Code must have no syntax errors"},{"task_spec_loaded":"Task specification successfully loaded"},{"requirements_met":"All acceptance criteria from task spec addressed"}] |
| inputs | {"task_id":{"type":"string","required":true,"description":"Task identifier (e.g., task-auth-002-login)","validation":"Must match pattern: task-{component}-{number}-{slug}"},"subtask_id":{"type":"string","required":false,"description":"Optional subtask identifier to implement only a specific subtask (e.g., subtask-1, subtask-2)","validation":"Must match pattern: subtask-{number} if provided"}} |
| outputs | {"implementation_complete":{"type":"boolean","description":"Whether implementation is complete and meets all criteria"},"test_coverage_percent":{"type":"number","description":"Test coverage percentage achieved"},"files_modified":{"type":"array","description":"List of files created or modified"},"tests_passed":{"type":"boolean","description":"Whether all tests passed"}} |
| telemetry | {"emit":"skill.implement-feature.completed","track":["task_id","test_coverage_percent","duration_ms","files_modified_count","tests_total","tests_passed","tests_failed"]} |
Implement features from task specifications or user stories using Test-Driven Development (TDD). This skill writes tests first, implements code to make tests pass, and validates the implementation meets all acceptance criteria.
Core Principles:
.claude/skills/bmad-commands/Action: Use bmad-commands to load task spec.
Execute:
python .claude/skills/bmad-commands/scripts/read_file.py \
--path workspace/tasks/{task_id}.md \
--output json
Parse Response:
success == trueoutputs.content for task specificationIf task spec not found:
file_not_found in errors arraycreate-task-spec skillIf subtask_id is provided:
See: references/templates.md for required task spec format
Action: Break down acceptance criteria into test cases.
For each acceptance criterion:
AC-1: User can log in with valid credentials
Test Cases:
- [Unit] Should return user object when credentials valid
- [Unit] Should return null when email not found
- [Unit] Should return null when password incorrect
- [Integration] Should create session when login successful
- [Integration] Should return 401 when login fails
Identify Files:
See: references/requirement-analysis-guide.md for detailed analysis patterns
Action: Write failing tests that cover all acceptance criteria.
Run Tests:
python .claude/skills/bmad-commands/scripts/run_tests.py \
--path . \
--framework auto \
--output json
Verify RED Phase:
outputs.passed == falseIf tests pass in RED phase:
See: references/test-examples.md for comprehensive test patterns and structure
Action: Write minimum code to make tests pass.
Implementation Strategy:
Run Tests:
python .claude/skills/bmad-commands/scripts/run_tests.py \
--path . \
--framework auto \
--output json
Verify GREEN Phase:
outputs.passed == trueoutputs.coverage_percent >= 80outputs.failed_tests == 0If tests still failing:
outputs.failuresSee: references/implementation-examples.md for implementation patterns
Action: Improve code quality while keeping tests green.
Refactoring Targets:
After Each Refactor:
python .claude/skills/bmad-commands/scripts/run_tests.py \
--path . \
--framework auto \
--output json
Verify tests stay green:
outputs.passed == true after each refactorSee: references/refactoring-patterns.md for common refactoring techniques
Action: Check that all acceptance criteria from task spec are met.
For each acceptance criterion:
Automated Verification:
# Run full test suite
python .claude/skills/bmad-commands/scripts/run_tests.py \
--path . \
--framework auto \
--output json
Check:
outputs.passed == trueoutputs.coverage_percent >= 80outputs.total_tests >= expected_countManual Verification:
Action: Run comprehensive checks before completion.
Validation Checks:
Run Final Tests:
python .claude/skills/bmad-commands/scripts/run_tests.py \
--path . \
--framework auto \
--output json
Acceptance Criteria Verification:
tests_passing: outputs.passed == truecoverage_threshold: outputs.coverage_percent >= 80no_syntax_errors: No syntax errors in outputtask_spec_loaded: Task spec was successfully loaded in Step 0requirements_met: All acceptance criteria verified in Step 5See: references/validation-guide.md for complete validation procedures
Return structured output with implementation status, test results, and telemetry.
See: references/templates.md for complete output format and examples
If any step fails:
create-task-spec skillSee: references/error-scenarios.md for detailed error handling strategies
If acceptance criteria are unclear or not testable:
refine-story skillIf implementation requires files that don't exist:
If tests break during refactoring:
If a task has multiple independent subtasks that can be implemented separately:
--subtask flag to implement one subtask at a time/implement-feature workspace/tasks/task-auth-002.md --subtask subtask-1See: references/best-practices.md for detailed TDD best practices
Use this skill when:
Use alternative when:
implement-with-discovery skillComplexity Assessment:
implement-with-discoveryreferences/requirement-analysis-guide.md - Analyze acceptance criteria, plan testsreferences/test-examples.md - Complete test patterns (unit, integration, e2e)references/implementation-examples.md - Code implementation patternsreferences/refactoring-patterns.md - Common refactoring techniquesreferences/validation-guide.md - Complete validation proceduresreferences/error-scenarios.md - Error handling strategiesreferences/best-practices.md - TDD and testing best practicesreferences/templates.md - Task spec format, output format, commit templatesInvoked by James subagent with routing, or called directly with task_id input.
Part of BMAD Enhanced Development Suite