chore: update .gitignore and improve coding standards documentation

- Added .cursor/sessions/* to .gitignore to prevent session files from being tracked. - Enhanced coding standards in SKILL.md by adding semicolons to TypeScript examples for consistency. - Improved formatting in continuous learning, detail layout, and other SKILL.md files for better readability. These changes aim to streamline development processes and maintain code quality across the project.
2026-08-25 17:50:17 +07:00
parent ff6814d038
commit f2f0be111a
48 changed files with 962 additions and 742 deletions
@@ -5,6 +5,7 @@ A formal evaluation framework for Claude Code sessions, implementing eval-driven
 ## Philosophy

 Eval-Driven Development treats evals as the "unit tests of AI development":
+
 - Define expected behavior BEFORE implementation
 - Run evals continuously during development
 - Track regressions with each change
@@ -13,33 +14,41 @@ Eval-Driven Development treats evals as the "unit tests of AI development":
 ## Eval Types

 ### Capability Evals
+
 Test if Claude can do something it couldn't before:
+
 ```markdown
 [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
+
+- [ ] Criterion 1
+- [ ] Criterion 2
+- [ ] Criterion 3
+      Expected Output: Description of expected result
 ```

 ### Regression Evals
+
 Ensure changes don't break existing functionality:
+
 ```markdown
 [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)
+
+- existing-test-1: PASS/FAIL
+- existing-test-2: PASS/FAIL
+- existing-test-3: PASS/FAIL
+  Result: X/Y passed (previously Y/Y)
 ```

 ## Grader Types

 ### 1. Code-Based Grader
+
 Deterministic checks using code:
+
 ```bash
 # Check if file contains expected pattern
 grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"
@@ -52,10 +61,13 @@ npm run build && echo "PASS" || echo "FAIL"
 ```

 ### 2. Model-Based Grader
+
 Use Claude to evaluate open-ended outputs:
+
 ```markdown
 [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?
@@ -66,7 +78,9 @@ Reasoning: [explanation]
 ```

 ### 3. Human Grader
+
 Flag for manual review:
+
 ```markdown
 [HUMAN REVIEW REQUIRED]
 Change: Description of what changed
@@ -77,13 +91,17 @@ Risk Level: LOW/MEDIUM/HIGH
 ## Metrics

 ### pass@k
+
 "At least one success in k attempts"
+
 - pass@1: First attempt success rate
 - pass@3: Success within 3 attempts
 - Typical target: pass@3 > 90%

 ### pass^k
+
 "All k trials succeed"
+
 - Higher bar for reliability
 - pass^3: 3 consecutive successes
 - Use for critical paths
@@ -91,28 +109,34 @@ Risk Level: LOW/MEDIUM/HIGH
 ## Eval Workflow

 ### 1. Define (Before Coding)
+
 ```markdown
 ## 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
 ```

 ### 2. Implement
+
 Write code to pass the defined evals.

 ### 3. Evaluate
+
 ```bash
 # Run capability evals
 [Run each capability eval, record PASS/FAIL]
@@ -124,25 +148,25 @@ npm test -- --testPathPattern="existing"
 ```

 ### 4. Report
+
 ```markdown
-EVAL REPORT: feature-xyz
-========================
+# 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
+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
+login-flow: PASS
+session-mgmt: PASS
+logout-flow: PASS
+Overall: 3/3 passed

 Metrics:
-  pass@1: 67% (2/3)
-  pass@3: 100% (3/3)
+pass@1: 67% (2/3)
+pass@3: 100% (3/3)

 Status: READY FOR REVIEW
 ```
@@ -150,26 +174,33 @@ Status: READY FOR REVIEW
 ## Integration Patterns

 ### Pre-Implementation
+
 ```
 /eval define feature-name
 ```
+
 Creates eval definition file at `.cursor/evals/feature-name.md`

 ### During Implementation
+
 ```
 /eval check feature-name
 ```
+
 Runs current evals and reports status

 ### Post-Implementation
+
 ```
 /eval report feature-name
 ```
+
 Generates full eval report

 ## Eval Storage

 Store evals in project:
+
 ```
 .cursor/
  evals/
@@ -194,7 +225,9 @@ Store evals in project:
 ## EVAL: add-authentication

 ### Phase 1: Define (10 min)
+
 Capability Evals:
+
 - [ ] User can register with email/password
 - [ ] User can login with valid credentials
 - [ ] Invalid credentials rejected with proper error
@@ -202,19 +235,23 @@ Capability Evals:
 - [ ] Logout clears session

 Regression Evals:
+
 - [ ] Public routes still accessible
 - [ ] API responses unchanged
 - [ ] Database schema compatible

 ### Phase 2: Implement (varies)
+
 [Write code]

 ### Phase 3: Evaluate
+
 Run: /eval check add-authentication

 ### Phase 4: Report
-EVAL REPORT: add-authentication
-==============================
+
+# EVAL REPORT: add-authentication
+
 Capability: 5/5 passed (pass@3: 100%)
 Regression: 3/3 passed (pass^3: 100%)
 Status: SHIP IT