@adityaaria/agent-os 1.0.0

package/skills/new-page/report-template.md

@@ -0,0 +1,39 @@
+# Executive Summary
+* **Trigger Detected**: N/A. Reason: Populated during skill execution.
+* **Purpose**: N/A. Reason: Populated during skill execution.
+
+# Scope
+* **Target**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Confidence
+* **Score**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Classification
+* **Classification**: N/A. Reason: Populated during skill execution.
+
+# Traceability Matrix
+| Layer | File | Function | Notes |
+| ----- | ---- | -------- | ----- |
+| Framework | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. |
+
+# Evidence
+* N/A. Reason: Populated during skill execution.
+
+# Root Cause
+* N/A. Reason: Populated during skill execution.
+
+# Impact
+* N/A. Reason: Populated during skill execution.
+
+# Recommendation
+* **Quick Win**: N/A. Reason: Populated during skill execution.
+* **Long Term Improvement**: N/A. Reason: Populated during skill execution.
+
+# Quality Gate
+* N/A. Reason: Populated during skill execution.
+
+# Enterprise Readiness
+* N/A. Reason: Populated during skill execution.
+
+# Final Decision
+N/A. Reason: Populated during skill execution.

package/skills/new-page/workflow.md

@@ -0,0 +1,10 @@
+# New Page Workflow
+
+1. **Pre-flight Check**: Parse the new page request and verify scope.
+2. **Knowledge Retrieval**: Load applicable `.agent-os/knowledge/` (Business Rules, Workflows, Technical).
+3. **Traceability Mapping**: Trace the new requirement across the unified 10-layer chain.
+4. **Design**: Plan the page structure and API integrations.
+5. **Implementation**: Build the page.
+6. **Knowledge Impact Assessment**: Explicitly determine if Business Rules, Workflows, APIs, DTOs, Entities, Database, or User Journeys changed.
+7. **Execution Validation**: Verify the page via testing.
+8. **Final Reporting**: Generate the standard Report Template.

package/skills/project-onboarding/SKILL.md

@@ -0,0 +1,27 @@
+# PROJECT-ONBOARDING SKILL
+
+## Purpose
+To autonomously analyze a new or existing repository, deeply detecting the Tech Stack, Architecture, FE-BE mappings, and database structures, generating rich foundational knowledge for all other skills.
+
+## Responsibilities
+- Detect Architecture (Monolith, Microservice, Hybrid).
+- Detect Tech Stack (Frontend, Backend, Database).
+- Identify Business Modules/Domains.
+- Map high-level FE-BE relationships.
+- Establish `.agent-os/project/` knowledge files.
+
+## Workflow
+Follow the detailed workflow in `workflow.md` for this skill.
+
+## Required Inputs
+Minimal Prompting: `ONBOARD` or automatically triggered when joining a new workspace.
+
+## Expected Outputs
+Project Knowledge Report and a fully populated `.agent-os/project` directory.
+
+## Execution Rules
+- Never rely solely on folder names; inspect source code for frameworks (e.g., `package.json`, `pom.xml`, `build.gradle`).
+- Collect explicit evidence of architecture (e.g., API Gateway configurations, monolith routing).
+
+## Minimal Prompting Target
+- Agent automatically scans the current directory and parent directories to find project boundaries.

package/skills/project-onboarding/checklist.md

@@ -0,0 +1,18 @@
+# PROJECT-ONBOARDING CHECKLIST
+
+## Entry Criteria
+- [ ] Workspace directory is accessible.
+
+## Execution
+- [ ] Repository Scan complete.
+- [ ] Architecture detected.
+- [ ] Tech Stack detected.
+- [ ] Module list generated.
+- [ ] FE-BE Mapping generated.
+- [ ] Database mapped.
+- [ ] `.agent-os/project/` knowledge files populated.
+
+## Exit Criteria / Definition of Done
+- [ ] Project Knowledge Report generated.
+- [ ] Enterprise Readiness Score calculated.
+- [ ] Quality Gate set to PASS.

package/skills/project-onboarding/examples.md

@@ -0,0 +1,26 @@
+# PROJECT-ONBOARDING EXAMPLES
+
+### Example 1
+```txt
+ANALYZE PROJECT: Initialize this repository.
+```
+
+### Example 2
+```txt
+ANALYZE PROJECT: Re-scan after moving to Monorepo.
+```
+
+### Example 3
+```txt
+ANALYZE PROJECT: Update database rules.
+```
+
+### Example 4
+```txt
+ANALYZE PROJECT: Document the new Auth flow.
+```
+
+### Example 5
+```txt
+ANALYZE PROJECT: Generate Module Catalog.
+```

package/skills/project-onboarding/report-template.md

@@ -0,0 +1,39 @@
+# Executive Summary
+* **Trigger Detected**: N/A. Reason: Populated during skill execution.
+* **Purpose**: N/A. Reason: Populated during skill execution.
+
+# Scope
+* **Target**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Confidence
+* **Score**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Classification
+* **Classification**: N/A. Reason: Populated during skill execution.
+
+# Traceability Matrix
+| Layer | File | Function | Notes |
+| ----- | ---- | -------- | ----- |
+| Framework | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. |
+
+# Evidence
+* N/A. Reason: Populated during skill execution.
+
+# Root Cause
+* N/A. Reason: Populated during skill execution.
+
+# Impact
+* N/A. Reason: Populated during skill execution.
+
+# Recommendation
+* **Quick Win**: N/A. Reason: Populated during skill execution.
+* **Long Term Improvement**: N/A. Reason: Populated during skill execution.
+
+# Quality Gate
+* N/A. Reason: Populated during skill execution.
+
+# Enterprise Readiness
+* N/A. Reason: Populated during skill execution.
+
+# Final Decision
+N/A. Reason: Populated during skill execution.

package/skills/project-onboarding/workflow.md

@@ -0,0 +1,9 @@
+# Project Onboarding Workflow
+
+1. **Pre-flight Check**: Parse the onboarding request and root repository context.
+2. **Technical Knowledge Generation**: Scan the repository structure and define the architecture, dependencies, and code standards in `.agent-os/knowledge/technical/`.
+3. **Business Rules Generation**: Extract explicit business constraints and document them using the standard template in `.agent-os/knowledge/business-rules/`.
+4. **Workflow Knowledge Generation**: Extract step-by-step user/system flows and document them in `.agent-os/knowledge/workflows/`.
+5. **Traceability Knowledge Generation**: Generate the unified 10-layer traceability mapping across the repository inside `.agent-os/knowledge/traceability/`.
+6. **Repository Summary Generation**: Aggregate the high-level metrics and health of the project.
+7. **Final Reporting**: Generate the standard Project Onboarding Report Template to present all findings.

package/skills/release-readiness/SKILL.md

@@ -0,0 +1,27 @@
+# RELEASE-READINESS SKILL
+
+## Purpose
+To audit the overall readiness of the system for production deployment by evaluating Deployment, Regression, Performance, and Security risks.
+
+## Responsibilities
+- Audit Deployment Risk.
+- Audit Regression Risk.
+- Audit Performance Risk.
+- Audit Security Risk.
+- Assess Rollback Readiness.
+
+## Workflow
+Follow the detailed workflow in `workflow.md` for this skill.
+
+## Required Inputs
+Minimal Prompting: `AUDIT: Release Readiness`
+
+## Expected Outputs
+Release Readiness Report with a final Readiness Score (0-100).
+
+## Execution Rules
+- Compile signals from existing automated tests, pipeline status, and code audits.
+- Output a strict PASS/FAIL based on the final Score.
+
+## Minimal Prompting Target
+- Agent autonomously assesses the main branch or current state without needing explicit parameters.

package/skills/release-readiness/checklist.md

@@ -0,0 +1,16 @@
+# RELEASE-READINESS CHECKLIST
+
+## Entry Criteria
+- [ ] Release candidate or environment is identified.
+
+## Execution
+- [ ] Deployment risk audited.
+- [ ] Regression risk audited.
+- [ ] Performance risk audited.
+- [ ] Security risk audited.
+- [ ] Rollback readiness verified.
+
+## Exit Criteria / Definition of Done
+- [ ] Release Readiness Report generated.
+- [ ] Enterprise Readiness Score calculated.
+- [ ] Quality Gate set to PASS.

package/skills/release-readiness/examples.md

@@ -0,0 +1,3 @@
+# EXAMPLES
+
+To be populated by Agent OS automatically based on project context.

package/skills/release-readiness/report-template.md

@@ -0,0 +1,39 @@
+# Executive Summary
+* **Trigger Detected**: N/A. Reason: Populated during skill execution.
+* **Purpose**: N/A. Reason: Populated during skill execution.
+
+# Scope
+* **Target**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Confidence
+* **Score**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Classification
+* **Classification**: N/A. Reason: Populated during skill execution.
+
+# Traceability Matrix
+| Layer | File | Function | Notes |
+| ----- | ---- | -------- | ----- |
+| Framework | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. |
+
+# Evidence
+* N/A. Reason: Populated during skill execution.
+
+# Root Cause
+* N/A. Reason: Populated during skill execution.
+
+# Impact
+* N/A. Reason: Populated during skill execution.
+
+# Recommendation
+* **Quick Win**: N/A. Reason: Populated during skill execution.
+* **Long Term Improvement**: N/A. Reason: Populated during skill execution.
+
+# Quality Gate
+* N/A. Reason: Populated during skill execution.
+
+# Enterprise Readiness
+* N/A. Reason: Populated during skill execution.
+
+# Final Decision
+N/A. Reason: Populated during skill execution.

package/skills/release-readiness/workflow.md

@@ -0,0 +1,14 @@
+# RELEASE-READINESS WORKFLOW
+
+You MUST execute these explicit steps sequentially:
+
+1. **Pre Validation** (Verify all Execution Reports and dependency artifacts exist)
+2. **Deployment Audit** (Check CI/CD pipelines, env vars, build status)
+3. **Regression Audit** (Check test coverage, E2E test results)
+4. **Performance Audit** (Assess bundle sizes, N+1 query risks)
+5. **Security Audit** (Assess exposed secrets, package vulnerabilities)
+6. **Rollback Assessment** (Check database migration reversibility)
+7. **Execution Validation** (Ensure all metrics collected)
+8. **Generate Readiness Score**
+9. **Generate Assessment Report**
+10. **Post Validation** (Verify report conforms to Enterprise Standard)

package/skills/repository-health/SKILL.md

@@ -0,0 +1,26 @@
+# REPOSITORY-HEALTH SKILL
+
+## Purpose
+To autonomously audit and score the holistic health of the repository, providing a top-level classification of enterprise readiness based on documentation, coverage, and debt metrics.
+
+## Responsibilities
+- Audit Documentation Coverage.
+- Audit Knowledge Coverage.
+- Audit Test Coverage.
+- Audit Traceability Coverage.
+- Assess Dependency Risk.
+- Assess Technical Debt.
+- Audit Architecture Consistency.
+
+## Workflow
+Follow the detailed workflow in `workflow.md` for this skill.
+
+## Required Inputs
+Minimal Prompting: `AUDIT: Repository Health`
+
+## Expected Outputs
+Repository Health Report containing a final score (0-100) and Classification (Excellent, Good, Fair, Poor, Critical).
+
+## Execution Rules
+- Must strictly validate findings against the Anti-Assumption Framework.
+- If test coverage cannot be detected, it must be marked as ASSUMED and heavily penalized.

package/skills/repository-health/checklist.md

@@ -0,0 +1,20 @@
+# REPOSITORY-HEALTH CHECKLIST
+
+## Entry Criteria
+- [ ] Pre Validation complete.
+
+## Execution
+- [ ] Documentation Coverage audited.
+- [ ] Knowledge Coverage audited.
+- [ ] Test Coverage audited.
+- [ ] Traceability Coverage audited.
+- [ ] Dependency Risk audited.
+- [ ] Technical Debt assessed.
+- [ ] Architecture Consistency audited.
+- [ ] Execution Validation complete.
+
+## Exit Criteria / Definition of Done
+- [ ] Post Validation complete.
+- [ ] Repository Health Report generated.
+- [ ] Score and Classification (Excellent to Critical) assigned.
+- [ ] Quality Gate set to PASS.

package/skills/repository-health/report-template.md

@@ -0,0 +1,39 @@
+# Executive Summary
+* **Trigger Detected**: N/A. Reason: Populated during skill execution.
+* **Purpose**: N/A. Reason: Populated during skill execution.
+
+# Scope
+* **Target**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Confidence
+* **Score**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Classification
+* **Classification**: N/A. Reason: Populated during skill execution.
+
+# Traceability Matrix
+| Layer | File | Function | Notes |
+| ----- | ---- | -------- | ----- |
+| Framework | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. |
+
+# Evidence
+* N/A. Reason: Populated during skill execution.
+
+# Root Cause
+* N/A. Reason: Populated during skill execution.
+
+# Impact
+* N/A. Reason: Populated during skill execution.
+
+# Recommendation
+* **Quick Win**: N/A. Reason: Populated during skill execution.
+* **Long Term Improvement**: N/A. Reason: Populated during skill execution.
+
+# Quality Gate
+* N/A. Reason: Populated during skill execution.
+
+# Enterprise Readiness
+* N/A. Reason: Populated during skill execution.
+
+# Final Decision
+N/A. Reason: Populated during skill execution.

package/skills/repository-health/workflow.md

@@ -0,0 +1,14 @@
+# REPOSITORY-HEALTH WORKFLOW
+
+You MUST execute these explicit steps sequentially:
+
+1. **Pre Validation** (Check if Knowledge exists)
+2. **Scan Documentation** (Check Readme, Swagger, internal wikis)
+3. **Scan Knowledge Coverage** (Check `.agent-os/project` integrity)
+4. **Scan Test Coverage** (Check Jest/Cypress coverage reports)
+5. **Scan Traceability** (Check missing links in `traceability-analysis`)
+6. **Scan Dependencies** (Check for CVEs or outdated packages)
+7. **Scan Architecture** (Check for monolith/microservice consistency)
+8. **Execution Validation** (Ensure all metrics collected)
+9. **Generate Repository Health Report**
+10. **Post Validation** (Verify report conforms to Enterprise standard)

package/skills/selenium-e2e/SKILL.md

@@ -0,0 +1,83 @@
+# SELENIUM-E2E SKILL
+
+## Purpose
+To execute enterprise-grade automated End-to-End browser tests, capable of autonomously generating comprehensive scenarios from simple user prompts without requiring prior setup by the user.
+
+## Responsibilities
+- Conduct strict Environment Readiness Audits before execution.
+- Perform deep Frontend (FE) Analysis (routes, components, validation).
+- Enforce strict FE-BE Traceability (UI Action -> Component -> API -> DTO -> Entity).
+- Automatically generate robust test scenarios (Happy Path, Validation, Negative Testing, Edge Case).
+- Validate selectors and wait strategies against enterprise standards.
+- Produce standardized, audit-ready Execution Reports.
+
+## Workflow
+Follow the detailed workflow in `workflow.md` for this skill.
+
+## Required Inputs
+A simple prompt indicating the target scope, e.g.:
+```txt
+TEST: Halaman Request Leave
+- tambah data
+- edit data
+- hapus data
+```
+
+## Expected Outputs
+Comprehensive execution report covering Test Scenarios, Traceability Matrix, Technical Debt, Root Cause Analysis, and Enterprise Readiness Score.
+
+## Execution Rules
+
+### 1. Environment Detection (MANDATORY)
+**Before any testing**, you MUST audit the environment.
+- **Dependencies**: Check `package.json` for `selenium-webdriver` and `chromedriver`/`geckodriver`. If missing, abort and report:
+  ```txt
+  STATUS: ENVIRONMENT_NOT_READY
+  MISSING:
+  - selenium-webdriver
+  - chromedriver
+  INSTALLATION GUIDE:
+  npm install selenium-webdriver
+  npm install chromedriver --save-dev
+  ```
+- **Browsers**: Verify availability of Google Chrome, Chromium, or Microsoft Edge. Report as blocker if none found.
+- **Test Folder**: Check for `tests/`, `tests/e2e/`, `automation/`, or `e2e/`. Recommend standard structure if missing.
+- **CI/CD**: Check for GitHub Actions, GitLab CI, or Jenkins. Report readiness.
+
+### 2. FE Analysis
+Do not generate tests solely based on UI appearance. You MUST read:
+- Routes and Views
+- Components and Modals
+- Forms (identify required/optional fields)
+- Tables (pagination, search, filter)
+- Validation Rules
+
+### 3. FE-BE Traceability
+You MUST trace the execution flow back to the database layer.
+**Trace Pattern**: `UI Action -> FE Component -> API Client -> Backend Controller -> Service -> DTO -> Entity`.
+
+### 4. Scenario Generation
+You MUST automatically generate the following scenarios:
+- **Happy Path**: View Page, Search, Filter, Create, Edit, Delete.
+- **Validation**: Required Fields, Invalid Formats, Max Length, Duplicate Data.
+- **Negative Testing**: API Errors, Unauthorized, Forbidden, Network Failures.
+- **Edge Case**: Empty Data, Large Data, Slow Responses.
+
+### 5. Selector Validation
+**Audit selectors prioritizing:**
+1. `data-testid`
+2. `id`
+3. `name`
+4. `aria-label`
+**Forbidden**: Long XPaths, brittle CSS selectors, `nth-child`. Report these as Technical Debt.
+
+### 6. Wait Strategy Validation
+**Audit wait commands:**
+- **Forbidden**: `sleep()`, `setTimeout()`. Report if found.
+- **Required**: Explicit Waits and Expected Conditions.
+
+## Quality Gates
+- Environment Audit passed.
+- Traceability Matrix completed.
+- Scenario Matrix executed.
+- Report generated matching standard template.

package/skills/selenium-e2e/checklist.md

@@ -0,0 +1,29 @@
+# SELENIUM-E2E CHECKLIST
+
+Before concluding the task, ensure all items are complete:
+
+## 1. Environment Readiness
+- [ ] Checked `package.json` for Selenium dependencies.
+- [ ] Checked for target browsers.
+- [ ] Checked/established standard test folder structure.
+- [ ] Verified CI/CD integration status.
+
+## 2. Analysis & Planning
+- [ ] Conducted FE Analysis (Routes, Components, Validation).
+- [ ] Mapped FE-BE Traceability (UI Action -> Component -> API -> DTO -> Entity).
+- [ ] Generated comprehensive Scenario Matrix (Happy Path, Validation, Negative, Edge Case).
+
+## 3. Scripting & Validation
+- [ ] Wrote scripts using standard structures.
+- [ ] Validated Selectors: Eliminated long XPaths, CSS selectors, `nth-child` in favor of `data-testid`, `id`, `name`.
+- [ ] Validated Waits: Eliminated `sleep()`, `setTimeout()` in favor of explicit waits/expected conditions.
+
+## 4. Execution & Root Cause
+- [ ] Executed tests locally.
+- [ ] Collected Evidence (Screenshots, Console Logs, Network Logs).
+- [ ] Performed deep Root Cause Analysis on failures (FE, BE, API, Data, Env).
+
+## 5. Reporting
+- [ ] Generated standardized `report-template.md`.
+- [ ] Calculated Enterprise Readiness Score (0-100).
+- [ ] Provided Actionable Recommendations (Quick Win, Medium, Long Term).

package/skills/selenium-e2e/examples.md

@@ -0,0 +1,26 @@
+# SELENIUM-E2E EXAMPLES
+
+### Example 1
+```txt
+TEST: E2E for User Login.
+```
+
+### Example 2
+```txt
+TEST: E2E for Checkout process.
+```
+
+### Example 3
+```txt
+TEST: Verify 404 page.
+```
+
+### Example 4
+```txt
+TEST: Test form validation errors.
+```
+
+### Example 5
+```txt
+TEST: E2E for multi-language toggle.
+```

package/skills/selenium-e2e/report-template.md

@@ -0,0 +1,39 @@
+# Executive Summary
+* **Trigger Detected**: N/A. Reason: Populated during skill execution.
+* **Purpose**: N/A. Reason: Populated during skill execution.
+
+# Scope
+* **Target**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Confidence
+* **Score**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Classification
+* **Classification**: N/A. Reason: Populated during skill execution.
+
+# Traceability Matrix
+| Layer | File | Function | Notes |
+| ----- | ---- | -------- | ----- |
+| Framework | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. |
+
+# Evidence
+* N/A. Reason: Populated during skill execution.
+
+# Root Cause
+* N/A. Reason: Populated during skill execution.
+
+# Impact
+* N/A. Reason: Populated during skill execution.
+
+# Recommendation
+* **Quick Win**: N/A. Reason: Populated during skill execution.
+* **Long Term Improvement**: N/A. Reason: Populated during skill execution.
+
+# Quality Gate
+* N/A. Reason: Populated during skill execution.
+
+# Enterprise Readiness
+* N/A. Reason: Populated during skill execution.
+
+# Final Decision
+N/A. Reason: Populated during skill execution.

package/skills/selenium-e2e/workflow.md

@@ -0,0 +1,9 @@
+# Selenium E2E Workflow
+
+1. **Environment Check**: Verify `selenium-webdriver` and `chromedriver` are installed. Verify browser availability. Verify test directory exists. If missing, generate a Setup Guide (`npm install selenium-webdriver chromedriver --save-dev`).
+2. **Knowledge Retrieval**: Load applicable `.agent-os/knowledge/` (Business Rules, Workflows, Technical).
+3. **Traceability Mapping**: Trace the test coverage across the unified 10-layer chain.
+4. **Scenario Generation**: Plan the E2E test scenarios based on business logic.
+5. **Implementation**: Write the Selenium tests.
+6. **Execution Validation**: Run the tests and capture failures/screenshots.
+7. **Final Reporting**: Generate the standard E2E Report Template incorporating Environment Status, Results, and Failures.

package/skills/self-audit/SKILL.md

@@ -0,0 +1,19 @@
+# SELF-AUDIT SKILL
+
+## Purpose
+To continuously audit Agent OS internal structure against the Enterprise Certification Framework. This skill is responsible for preventing quality regressions.
+
+## Responsibilities
+- Execute all 5 Validators in `.agent-os/validators/`.
+- Verify the Enterprise Traceability Chain.
+- Output the 100-point Enterprise Scorecard.
+- Enforce the "Non Negotiable Rule" for framework regression.
+
+## Workflow
+Follow the detailed workflow in `workflow.md` for this skill.
+
+## Required Inputs
+Minimal Prompting: `AUDIT: Agent OS`
+
+## Expected Outputs
+Agent OS Health Report (incorporating the Enterprise Scorecard).

package/skills/self-audit/checklist.md

@@ -0,0 +1,14 @@
+# SELF-AUDIT CHECKLIST
+
+## Entry Criteria
+- [ ] Self Audit trigger detected.
+
+## Execution
+- [ ] All 5 Validator checks executed and PASSED.
+- [ ] Registry Audit PASSED.
+- [ ] README Consistency Validation PASSED.
+- [ ] Enterprise Scorecard calculated.
+
+## Exit Criteria / Definition of Done
+- [ ] Agent OS Health Report generated.
+- [ ] Quality Gate set to PASS.

package/skills/self-audit/report-template.md

@@ -0,0 +1,39 @@
+# Executive Summary
+* **Trigger Detected**: N/A. Reason: Populated during skill execution.
+* **Purpose**: N/A. Reason: Populated during skill execution.
+
+# Scope
+* **Target**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Confidence
+* **Score**: N/A. Reason: Populated during skill execution.
+
+# Knowledge Classification
+* **Classification**: N/A. Reason: Populated during skill execution.
+
+# Traceability Matrix
+| Layer | File | Function | Notes |
+| ----- | ---- | -------- | ----- |
+| Framework | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. | N/A. Reason: Populated during skill execution. |
+
+# Evidence
+* N/A. Reason: Populated during skill execution.
+
+# Root Cause
+* N/A. Reason: Populated during skill execution.
+
+# Impact
+* N/A. Reason: Populated during skill execution.
+
+# Recommendation
+* **Quick Win**: N/A. Reason: Populated during skill execution.
+* **Long Term Improvement**: N/A. Reason: Populated during skill execution.
+
+# Quality Gate
+* N/A. Reason: Populated during skill execution.
+
+# Enterprise Readiness
+* N/A. Reason: Populated during skill execution.
+
+# Final Decision
+N/A. Reason: Populated during skill execution.

package/skills/self-audit/workflow.md

@@ -0,0 +1,11 @@
+# Self Audit Workflow
+
+1. **Pre-flight Check**: Parse the self audit request.
+2. **Validator Execution**: Execute all 5 Validator checks from `.agent-os/validators/`.
+3. **Skill Coverage Check**: Validate existence of the 6 core V1.0 skills (`project-onboarding`, `audit`, `bug-fix`, `enhancement`, `new-page`, `selenium-e2e`, plus `knowledge-evolution` and `self-audit`).
+4. **Knowledge Coverage Check**: Evaluate existence of data within `.agent-os/knowledge/`.
+5. **Template Quality Check**: Sweep all `report-template.md` and `workflow.md` files for legacy placeholders or deviations from the 11-section standard.
+6. **Traceability Coverage Check**: Verify the 10-layer Traceability Matrix is strictly enforced.
+7. **Knowledge Structure Check**: Verify `business-rules`, `workflows`, `technical`, and `traceability` folders exist and use the new templates.
+8. **Report Quality Check**: Validate structure of recent execution reports.
+9. **Final Reporting**: Generate the Agent OS Health Report and calculate the Readiness Score.