Best fit
- 평가 주도 개발(EDD) 원칙을 구현하는 Claude Code 세션용 공식 평가 프레임워크
affaan-m/ECC
평가 주도 개발(EDD) 원칙을 구현하는 Claude Code 세션용 공식 평가 프레임워크
npx skills add https://github.com/affaan-m/ECC --skill "docs/ko-KR/skills/eval-harness"Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
According to the pinned SKILL.md from affaan-m/ECC: Claude Code 세션을 위한 공식 평가 프레임워크로, 평가 주도 개발(EDD) 원칙을 구현합니다.
npx skills add https://github.com/affaan-m/ECC --skill "docs/ko-KR/skills/eval-harness"Best fit
Bring this context
Expected outputs
Key source sections
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
Capability Evals: - [ ] User can register with email/password - [ ] User can login with valid credentials - [ ] Invalid credentials rejected with proper error - [ ] Sessions persist across page reloads - [ ] Logout clears session
Review the “Phase 2: 구현 (가변)” section in the pinned source before continuing.
Run: /eval check add-authentication
EVAL REPORT: add-authentication ============================== Capability: 5/5 passed (pass@3: 100%) Regression: 3/3 passed (pass^3: 100%) Status: SHIP IT
AI 지원 워크플로우에 평가 주도 개발(EDD) 설정 시
SkillSignal prompt templates
These prompts were written by SkillSignal from the source structure; they are not upstream text.
Task-start prompt
Confirm source fit, inputs, and outputs before acting.
Use eval-harness to help me with: [specific task]. Context: [files, data, or background]. Constraints: [environment, scope, and prohibited actions]. Before acting, check the pinned SKILL.md and explain which sections apply, what inputs are still missing, and what you will deliver.
Source-guided execution
Make the Agent explicitly follow the key extracted sections.
Apply the pinned eval-harness source to [task]. Pay particular attention to these source sections: “Phase 1: 정의 (10분)”, “Phase 2: 구현 (가변)”, “Phase 3: 평가”, “Phase 4: 보고서”, “활성화 시점”. Preserve the important decision at each step. Mark facts not covered by the source as “needs confirmation” instead of inventing them. Then verify the result against my acceptance criteria: [criteria].
Result-review prompt
Check omissions, permissions, and source drift before delivery.
Review the current eval-harness result: (1) does it satisfy the original task; (2) were any applicable steps or limits in the pinned SKILL.md missed; (3) did it perform any unauthorized file, command, network, or data action; and (4) which conclusions remain unverified? List issues first, then fix only what the source or user authorization supports.
Output checklist
The task matches the purpose documented in the SKILL.md.
The source section “Phase 1: 정의 (10분)” has been checked.
The source section “Phase 2: 구현 (가변)” has been checked.
The source section “Phase 3: 평가” has been checked.
The source section “Phase 4: 보고서” has been checked.
Inputs, constraints, and acceptance criteria are explicit.
Unverified facts, compatibility, and outcome claims are clearly marked.
Any file, command, network, or data action has been reviewed.
Choose a different workflow
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailFramework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
Claude Code 세션을 위한 공식 평가 프레임워크로, 평가 주도 개발(EDD) 원칙을 구현합니다.
The catalog detected this source-specific install command: npx skills add https://github.com/affaan-m/ECC --skill "docs/ko-KR/skills/eval-harness". Inspect the command and pinned source before running it.
claude code
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Compare before choosing
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)
Eval-driven development (EDD) ilkelerini uygulayan Claude Code oturumları için formal değerlendirme çerçevesi
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
Claude Code 세션을 위한 공식 평가 프레임워크로, 평가 주도 개발(EDD) 원칙을 구현합니다.
평가 주도 개발은 평가를 "AI 개발의 단위 테스트"로 취급합니다:
Claude가 이전에 할 수 없었던 것을 할 수 있는지 테스트:
[CAPABILITY EVAL: feature-name]
Task: Description of what Claude should accomplish
Success Criteria:
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3
Expected Output: Description of expected result
변경 사항이 기존 기능을 손상시키지 않는지 확인:
[REGRESSION EVAL: feature-name]
Baseline: SHA or checkpoint name
Tests:
- existing-test-1: PASS/FAIL
- existing-test-2: PASS/FAIL
- existing-test-3: PASS/FAIL
Result: X/Y passed (previously Y/Y)
코드를 사용한 결정론적 검사:
# Check if file contains expected pattern
grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"
# Check if tests pass
npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL"
# Check if build succeeds
npm run build && echo "PASS" || echo "FAIL"
Claude를 사용하여 개방형 출력 평가:
[MODEL GRADER PROMPT]
Evaluate the following code change:
1. Does it solve the stated problem?
2. Is it well-structured?
3. Are edge cases handled?
4. Is error handling appropriate?
Score: 1-5 (1=poor, 5=excellent)
Reasoning: [explanation]
수동 검토 플래그:
[HUMAN REVIEW REQUIRED]
Change: Description of what changed
Reason: Why human review is needed
Risk Level: LOW/MEDIUM/HIGH
"k번 시도 중 최소 한 번 성공"
"k번 시행 모두 성공"
## EVAL DEFINITION: feature-xyz
### Capability Evals
1. Can create new user account
2. Can validate email format
3. Can hash password securely
### Regression Evals
1. Existing login still works
2. Session management unchanged
3. Logout flow intact
### Success Metrics
- pass@3 > 90% for capability evals
- pass^3 = 100% for regression evals
정의된 평가를 통과하기 위한 코드 작성.
# Run capability evals
[Run each capability eval, record PASS/FAIL]
# Run regression evals
npm test -- --testPathPattern="existing"
# Generate report
EVAL REPORT: feature-xyz
========================
Capability Evals:
create-user: PASS (pass@1)
validate-email: PASS (pass@2)
hash-password: PASS (pass@1)
Overall: 3/3 passed
Regression Evals:
login-flow: PASS
session-mgmt: PASS
logout-flow: PASS
Overall: 3/3 passed
Metrics:
pass@1: 67% (2/3)
pass@3: 100% (3/3)
Status: READY FOR REVIEW
/eval define feature-name
.claude/evals/feature-name.md에 평가 정의 파일 생성
/eval check feature-name
현재 평가를 실행하고 상태 보고
/eval report feature-name
전체 평가 보고서 생성
프로젝트에 평가 저장:
.claude/
evals/
feature-xyz.md # 평가 정의
feature-xyz.log # 평가 실행 이력
baseline.json # 회귀 베이스라인
## EVAL: add-authentication
### Phase 1: 정의 (10분)
Capability Evals:
- [ ] User can register with email/password
- [ ] User can login with valid credentials
- [ ] Invalid credentials rejected with proper error
- [ ] Sessions persist across page reloads
- [ ] Logout clears session
Regression Evals:
- [ ] Public routes still accessible
- [ ] API responses unchanged
- [ ] Database schema compatible
### Phase 2: 구현 (가변)
[Write code]
### Phase 3: 평가
Run: /eval check add-authentication
### Phase 4: 보고서
EVAL REPORT: add-authentication
==============================
Capability: 5/5 passed (pass@3: 100%)
Regression: 3/3 passed (pass^3: 100%)
Status: SHIP IT
행동 품질을 단위 테스트만으로 포착할 수 없을 때 제품 평가를 사용하세요.
pass@1: 직접 신뢰성pass@3: 제어된 재시도 하에서의 실용적 신뢰성pass^3: 안정성 테스트 (3회 모두 통과해야 함)권장 임계값:
.claude/evals/<feature>.md 정의.claude/evals/<feature>.log 실행 이력docs/releases/<version>/eval-summary.md 릴리스 스냅샷