@teevee98/synapse-hub 4.1.3 → 4.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (206) hide show
  1. package/.agents/rules/git-push-protocol.md +2 -2
  2. package/.agents/skills/01-web-automation/auth-session-and-cookie-manager/SKILL.md +6 -1
  3. package/.agents/skills/01-web-automation/bats-testing-patterns/SKILL.md +6 -1
  4. package/.agents/skills/01-web-automation/clean-pom-crafter/SKILL.md +8 -3
  5. package/.agents/skills/01-web-automation/clean-pom-crafter/examples/standard_test_case.groovy +3 -0
  6. package/.agents/skills/01-web-automation/clean-pom-crafter/references/pom_patterns.groovy +3 -0
  7. package/.agents/skills/01-web-automation/e2e-testing-patterns/SKILL.md +6 -1
  8. package/.agents/skills/01-web-automation/e2e-testing-patterns/examples/playwright_sharded_config.ts +3 -0
  9. package/.agents/skills/01-web-automation/katalon-cli-runner/SKILL.md +6 -1
  10. package/.agents/skills/01-web-automation/lam-script-generator/SKILL.md +6 -1
  11. package/.agents/skills/01-web-automation/mobile-appium-som/SKILL.md +6 -1
  12. package/.agents/skills/01-web-automation/mobile-appium-som/examples/BaseScreen.java +2 -2
  13. package/.agents/skills/01-web-automation/mobile-appium-som/examples/LoginScreen.java +2 -2
  14. package/.agents/skills/01-web-automation/mobile-appium-som/examples/TC_MobileLogin.java +2 -2
  15. package/.agents/skills/01-web-automation/playwright-live-interaction/SKILL.md +7 -2
  16. package/.agents/skills/01-web-automation/playwright-webapp-testing/SKILL.md +6 -1
  17. package/.agents/skills/01-web-automation/playwright-webapp-testing/examples/server_lifecycle_playwright.py +3 -0
  18. package/.agents/skills/01-web-automation/web-agent-gym-benchmarking/SKILL.md +6 -1
  19. package/.agents/skills/02-test-design/architecture-decision-records/SKILL.md +6 -1
  20. package/.agents/skills/02-test-design/gherkin-to-suite/SKILL.md +6 -1
  21. package/.agents/skills/02-test-design/rbt-manual-testing/SKILL.md +6 -1
  22. package/.agents/skills/02-test-design/review-spec/SKILL.md +4 -1
  23. package/.agents/skills/02-test-design/tot-exploratory-testing/SKILL.md +6 -1
  24. package/.agents/skills/03-api-and-contracts/api-network-mocking-interception/SKILL.md +6 -1
  25. package/.agents/skills/03-api-and-contracts/api-spec-to-e2e-matrix/SKILL.md +6 -1
  26. package/.agents/skills/03-api-and-contracts/consumer-driven-contract-testing/SKILL.md +7 -2
  27. package/.agents/skills/04-performance-and-load/backend-load-and-stress-patterns/SKILL.md +7 -2
  28. package/.agents/skills/04-performance-and-load/lean-impact-scoreboard/SKILL.md +4 -1
  29. package/.agents/skills/04-performance-and-load/web-vitals-and-performance-profiler/SKILL.md +6 -1
  30. package/.agents/skills/04-performance-and-load/web-vitals-and-performance-profiler/examples/playwright_cwv_profiler_fixture.ts +3 -0
  31. package/.agents/skills/05-security-and-compliance/security-dast-sentinel/SKILL.md +6 -1
  32. package/.agents/skills/05-security-and-compliance/security-dast-sentinel/references/dast_recipes.ts +3 -0
  33. package/.agents/skills/05-security-and-compliance/skillspector-security-guard/SKILL.md +6 -1
  34. package/.agents/skills/05-security-and-compliance/wcag-audit-patterns/SKILL.md +6 -1
  35. package/.agents/skills/06-healing-and-resilience/agentless-qa-repair/SKILL.md +6 -1
  36. package/.agents/skills/06-healing-and-resilience/antigravity-test-sentinel/SKILL.md +6 -1
  37. package/.agents/skills/06-healing-and-resilience/failure-autopsy-and-healing/SKILL.md +7 -2
  38. package/.agents/skills/06-healing-and-resilience/flaky-test-sentinel-and-quarantine/SKILL.md +6 -1
  39. package/.agents/skills/06-healing-and-resilience/self-healing-locator/SKILL.md +6 -1
  40. package/.agents/skills/06-healing-and-resilience/systematic-debugging/SKILL.md +6 -1
  41. package/.agents/skills/06-healing-and-resilience/test-driven-development/SKILL.md +6 -1
  42. package/.agents/skills/06-healing-and-resilience/verification-before-completion/SKILL.md +6 -1
  43. package/.agents/skills/06-healing-and-resilience/visual-regression-sentinel/SKILL.md +6 -1
  44. package/.agents/skills/07-data-and-state/db-state-verifier-and-seeder/SKILL.md +6 -1
  45. package/.agents/skills/07-data-and-state/file-and-report-validator/SKILL.md +6 -1
  46. package/.agents/skills/07-data-and-state/synthetic-test-data-generator/SKILL.md +6 -1
  47. package/.agents/skills/08-code-quality/code-refactoring-refactor-clean/SKILL.md +6 -1
  48. package/.agents/skills/08-code-quality/code-refactoring-refactor-clean/examples/refactored_page_sample.groovy +3 -0
  49. package/.agents/skills/08-code-quality/code-refactoring-refactor-clean/examples/refactored_playwright_pom.ts +3 -0
  50. package/.agents/skills/08-code-quality/graphify-impact-analyzer/SKILL.md +6 -1
  51. package/.agents/skills/08-code-quality/lean-code-ladder/SKILL.md +6 -1
  52. package/.agents/skills/08-code-quality/repo-quality-audit/SKILL.md +4 -1
  53. package/.agents/skills/08-code-quality/senior-code-review/SKILL.md +4 -1
  54. package/.agents/skills/08-code-quality/surgical-coding-principles/SKILL.md +6 -1
  55. package/.agents/skills/08-code-quality/technical-debt-harvester/SKILL.md +4 -1
  56. package/.agents/skills/09-ci-and-devops/github-actions-templates/SKILL.md +6 -1
  57. package/.agents/skills/10-agent-orchestration/actor-qa-swarm/SKILL.md +6 -1
  58. package/.agents/skills/10-agent-orchestration/agent-orchestration-multi-agent-optimize/SKILL.md +6 -1
  59. package/.agents/skills/10-agent-orchestration/event-stream-qa-orchestrator/SKILL.md +6 -1
  60. package/.agents/skills/10-agent-orchestration/persistent-planning-files/SKILL.md +6 -1
  61. package/.agents/skills/10-agent-orchestration/qa-memory-os/SKILL.md +6 -1
  62. package/.agents/skills/11-ai-and-prompting/meta-prompt-crafter/SKILL.md +6 -1
  63. package/.agents/skills/11-ai-and-prompting/mipro-prompt-compiler/SKILL.md +6 -1
  64. package/.agents/skills/11-ai-and-prompting/qa-aci-interface/SKILL.md +6 -1
  65. package/.agents/skills/11-ai-and-prompting/qa-aci-interface/examples/surgical_code_window_walkthrough.md +1 -1
  66. package/.agents/skills/11-ai-and-prompting/token-and-context-optimizer/SKILL.md +6 -1
  67. package/AGENTS.md +7 -1
  68. package/LICENSE +5 -5
  69. package/NOTICE +1 -1
  70. package/README.en.md +4 -4
  71. package/README.md +4 -4
  72. package/agentskills.json +1 -1
  73. package/docs/ARCHITECTURE.en.md +2 -2
  74. package/docs/ARCHITECTURE.md +11 -2
  75. package/docs/CLI_REFERENCE.en.md +6 -4
  76. package/docs/CLI_REFERENCE.md +1 -1
  77. package/docs/CONTRIBUTING.en.md +1 -1
  78. package/docs/CONTRIBUTING.md +2 -2
  79. package/docs/PERFORMANCE_AUDIT_REPORT.md +2 -2
  80. package/docs/TOOL_CATALOG.md +6 -2
  81. package/docs/research/agent_skill_training_analysis.md +1 -1
  82. package/package.json +1 -1
  83. package/plugin.json +1 -1
  84. package/scripts/generate_skill_examples.py +3 -0
  85. package/scripts/package_dist.py +3 -0
  86. package/skills_manifest.json +320 -55
  87. package/synapse.config.json +1 -1
  88. package/templates/ui/index.html +2 -2
  89. package/tools/.infer_baseline.json +3 -796
  90. package/tools/TOOL_CATALOG.json +63 -3
  91. package/tools/__init__.py +4 -1
  92. package/tools/agent_canary.py +3 -0
  93. package/tools/analyze_project.py +3 -0
  94. package/tools/api_drift_sentinel.py +3 -0
  95. package/tools/api_fuzzer.py +182 -118
  96. package/tools/ast_cache.py +4 -2
  97. package/tools/author_integrity.py +174 -12
  98. package/tools/auto_heal.py +7 -2
  99. package/tools/autogen_qa_broker.py +14 -15
  100. package/tools/benchmark_swarm_context.py +119 -18
  101. package/tools/break_ui_generator.py +233 -0
  102. package/tools/browser_helpers.js +2 -2
  103. package/tools/bug_reporter.py +3 -0
  104. package/tools/build_consolidated_report.py +3 -0
  105. package/tools/bump_version.py +4 -1
  106. package/tools/cache_resolver.py +7 -3
  107. package/tools/check_env.py +3 -0
  108. package/tools/check_version_sync.py +21 -50
  109. package/tools/ci_healing_hook.py +3 -0
  110. package/tools/cli.py +116 -22
  111. package/tools/config_decoupler.py +3 -0
  112. package/tools/core/__init__.py +3 -0
  113. package/tools/core/bm25_retriever.py +218 -0
  114. package/tools/core/file_lock.py +23 -14
  115. package/tools/core/i18n.py +13 -11
  116. package/tools/core/memory_bus.py +6 -3
  117. package/tools/core/process_supervisor.py +28 -18
  118. package/tools/core/provider_usage_adapter.py +317 -0
  119. package/tools/core/token_estimator.py +83 -18
  120. package/tools/count_tokens.py +16 -7
  121. package/tools/coverage_reporter.py +245 -0
  122. package/tools/create_mock_docx.py +3 -0
  123. package/tools/dashboard_generator.py +17 -15
  124. package/tools/db_sandbox.py +150 -5
  125. package/tools/debt_harvester.py +2 -2
  126. package/tools/diagram_architect.py +3 -0
  127. package/tools/distill_log.py +22 -2
  128. package/tools/distill_skill.py +191 -0
  129. package/tools/e2e_flow_prober.py +3 -0
  130. package/tools/export_postman_collection.py +3 -0
  131. package/tools/flaky_detector.py +3 -0
  132. package/tools/fsm_enforcer.py +2 -2
  133. package/tools/fuzz_payloads.py +3 -0
  134. package/tools/generate_allure_report.py +3 -0
  135. package/tools/generate_api_matrix.py +3 -0
  136. package/tools/generate_jmx_plan.py +3 -0
  137. package/tools/generate_tc_from_story.py +3 -0
  138. package/tools/generate_test_reports.py +3 -0
  139. package/tools/git_pre_commit_guard.py +25 -3
  140. package/tools/git_worktree_manager.py +3 -0
  141. package/tools/heal/__init__.py +3 -0
  142. package/tools/heal_pr_automator.py +3 -0
  143. package/tools/heuristic_locator_matcher.py +3 -0
  144. package/tools/hub_publisher.py +3 -3
  145. package/tools/humanize_linter.py +3 -0
  146. package/tools/infer_linter.py +19 -9
  147. package/tools/init_config.py +6 -9
  148. package/tools/jtl_analyzer.py +3 -0
  149. package/tools/lint/__init__.py +3 -0
  150. package/tools/lint_ai_docs.py +3 -0
  151. package/tools/lookup_tc.py +3 -0
  152. package/tools/lookup_xpath.py +3 -0
  153. package/tools/matrix_sharder.py +3 -0
  154. package/tools/mcp/__init__.py +3 -0
  155. package/tools/mcp_docx_server.py +1 -1
  156. package/tools/mcp_excel_server.py +4 -1
  157. package/tools/mcp_server.py +78 -15
  158. package/tools/md_to_xlsx.py +3 -0
  159. package/tools/mechanical_ui_gate.py +3 -0
  160. package/tools/micro_mutator.py +93 -19
  161. package/tools/network_mock_shield.py +3 -0
  162. package/tools/newman_analyzer.py +3 -0
  163. package/tools/omni_emitter.py +3 -0
  164. package/tools/omni_parser.py +3 -0
  165. package/tools/omni_transpiler.py +3 -0
  166. package/tools/output_formatter.py +3 -0
  167. package/tools/package_release.py +6 -6
  168. package/tools/pairwise_generator.py +3 -0
  169. package/tools/pentest_scope_guard.py +401 -58
  170. package/tools/perf/__init__.py +3 -0
  171. package/tools/perf/benchmark_perf_runner.py +42 -0
  172. package/tools/pinpoint_failure.py +3 -0
  173. package/tools/project_state.py +3 -0
  174. package/tools/repo_map.py +3 -0
  175. package/tools/report/__init__.py +3 -0
  176. package/tools/rules_router.py +426 -34
  177. package/tools/runaway_stopper.py +3 -0
  178. package/tools/safety_firewall.py +3 -0
  179. package/tools/security_scanner.py +80 -0
  180. package/tools/senior_code_review.py +14 -0
  181. package/tools/setup_project.py +9 -4
  182. package/tools/skill_canonical_digest.py +244 -0
  183. package/tools/skill_collision_guard.py +2 -2
  184. package/tools/skill_profiles.py +77 -7
  185. package/tools/skillspector.py +2 -1
  186. package/tools/slide_deck_exporter.py +477 -0
  187. package/tools/smart_visual_masker.py +3 -0
  188. package/tools/sync_skills_manifest.py +166 -0
  189. package/tools/task_memory_manager.py +260 -0
  190. package/tools/telemetry_correlator.py +3 -0
  191. package/tools/template_excel_exporter.py +2 -2
  192. package/tools/test_impact.py +3 -0
  193. package/tools/trace_data_flow.py +3 -0
  194. package/tools/traffic_session_converter.py +3 -0
  195. package/tools/ui_server.py +2 -2
  196. package/tools/universal_ir.py +3 -0
  197. package/tools/update_sentinel.py +15 -9
  198. package/tools/validate_groovy_scripts.py +3 -0
  199. package/tools/validate_host_interop.py +485 -0
  200. package/tools/validate_skills_schema.py +282 -0
  201. package/tools/verify_all.py +600 -63
  202. package/tools/visual_diff_canvas.py +3 -0
  203. package/tools/visual_som_helper.py +3 -0
  204. package/tools/watch_mode.py +4 -4
  205. package/tools/wcag_audit.py +3 -0
  206. package/tools/welcome_page.py +2 -2
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: visual-regression-sentinel
3
3
  description: "Run pixel and layout shift visual regression checks with anti-flake masking. Use when comparing screenshots for visual regressions with anti-flake masking."
4
+ category: verification_and_resilience
5
+ version: "2.0.0"
6
+ policies:
7
+ network: localhost-only
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Visual Regression Sentinel Skill
7
12
 
8
13
  > **Target:** Catch unintended UI rendering defects, CSS breakages, alignment shifts, and missing visual assets across viewports without manual visual inspection.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: db-state-verifier-and-seeder
3
3
  description: "Seed isolated test fixtures and assert database mutations across SQL and NoSQL. Use when seeding, verifying, or cleaning database state around tests."
4
+ category: verification_and_resilience
5
+ version: "2.0.0"
6
+ policies:
7
+ network: localhost-only
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Database State Verifier & Seeder Skill
7
12
 
8
13
  > **Target:** Eliminate shallow UI-only validations by asserting exact backend database mutations (PostgreSQL, MySQL, Oracle, MongoDB, Redis) and providing isolated, idempotent fixture seeding.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: file-and-report-validator
3
3
  description: "Validate downloaded and uploaded files (Excel, CSV, PDF) schemas and tabular integrity. Use when validating exported files or reports against a schema."
4
+ category: verification_and_resilience
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: read-only
9
+ filesystem: read-only
4
10
  ---
5
-
6
11
  # File & Report Validator Skill
7
12
 
8
13
  > **Target:** Eliminate superficial testing of file exports and imports by inspecting and asserting exact file contents, schemas, formulas, and values across Excel, CSV, and PDF formats.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: synthetic-test-data-generator
3
3
  description: "Generate idempotent, boundary-value synthetic test data with unique runtime timestamps. Use when generating idempotent, unique test data for creation tests."
4
+ category: verification_and_resilience
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Synthetic Test Data Generator & Edge-Case Fuzzing Skill
7
12
 
8
13
  > **Target:** Eliminate database collisions, race conditions in parallel testing, and stale fixture dependencies by dynamically generating valid, boundary-value, and edge-case fuzzing datasets.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: code-refactoring-refactor-clean
3
3
  description: "Eliminate technical debt and refactor code using SOLID and Clean Code patterns. Use when refactoring legacy test code toward clean, maintainable structures."
4
+ category: architecture_and_analysis
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Refactor, Clean Code & Technical Debt Remediation
7
12
 
8
13
  You are a code refactoring and technical debt expert specializing in clean code principles, SOLID design patterns, tech debt inventory, and modern software engineering best practices. Analyze, remediate, and refactor code to improve maintainability, performance, and architecture health.
@@ -1,3 +1,6 @@
1
+ // SPDX-FileCopyrightText: © 2026 Thế Vị (@TeeVee98) <https://github.com/TeeVee98/Synapse-Hub>
2
+ // SPDX-License-Identifier: MIT
3
+
1
4
  package pages
2
5
 
3
6
  class UserManagementPage extends BasePage {
@@ -1,3 +1,6 @@
1
+ // SPDX-FileCopyrightText: © 2026 Thế Vị (@TeeVee98) <https://github.com/TeeVee98/Synapse-Hub>
2
+ // SPDX-License-Identifier: MIT
3
+
1
4
  /**
2
5
  * Clean POM & Flat Architecture Refactoring Demonstration (Playwright TypeScript)
3
6
  *
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: graphify-impact-analyzer
3
3
  description: "Analyze code change blast radius and scope impacted test cases via AST. Use when analyzing the blast radius of code changes via dependency graphs."
4
+ category: architecture_and_analysis
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Graphify Impact Analyzer — AST Knowledge Graph Navigation & Zero-Waste Impact Analysis
7
12
 
8
13
  Specialized skill for navigating the codebase's AST Knowledge Graph (`graphify-out/graph.json`), executing sub-second dependency queries, and performing **Zero-Waste Test Impact Analysis** to execute only tests affected by code modifications.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: lean-code-ladder
3
3
  description: "Apply a 7-rung reuse-first ladder so every new test-automation code path is the smallest complete change that fully solves the task. Use when adding helpers, Page Class methods, dependencies, or any new code where a shorter existing option might already exist."
4
+ category: architecture_and_analysis
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: read-only
4
10
  ---
5
-
6
11
  # Lean Code Ladder — Enterprise Reuse-First Standard
7
12
 
8
13
  Specialized skill for minimizing newly written code in test automation projects: solve the whole problem with the least new code, then finish the change completely (callers, fixtures, and the small test that proves it).
@@ -3,8 +3,11 @@ name: repo-quality-audit
3
3
  description: "Comprehensive codebase quality audit covering bugs, security, bottlenecks, and bloat. Use when auditing an entire project, evaluating repository health, or prioritizing technical debt."
4
4
  category: architecture_and_analysis
5
5
  version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: read-only
9
+ filesystem: read-only
6
10
  ---
7
-
8
11
  # Repo Quality Audit — Comprehensive Repository Health & Risk Audit
9
12
 
10
13
  Audit an entire repository like the senior engineer who just inherited it and will be paged when it breaks.
@@ -3,8 +3,11 @@ name: senior-code-review
3
3
  description: "Review code changes across logic, security, concurrency, and test coverage. Use when conducting pull request reviews, diff inspections, or auditing commit changes before merge."
4
4
  category: architecture_and_analysis
5
5
  version: "1.1.0"
6
+ policies:
7
+ network: none
8
+ shell: read-only
9
+ filesystem: read-only
6
10
  ---
7
-
8
11
  # Senior Code Review — Enterprise Quality & Lean Diff Review
9
12
 
10
13
  Review code changes like the senior engineer who will be paged at 2 AM when it breaks.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: surgical-coding-principles
3
3
  description: "Enforce four behavioral principles (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution) when writing or modifying test automation code. Use when implementing Page Classes, editing test scripts, or changing hub tools to prevent assumption drift and over-engineering."
4
+ category: architecture_and_analysis
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Surgical Coding Principles — Enterprise Minimal-Diff Discipline
7
12
 
8
13
  Specialized skill for reducing the three classic LLM coding failure modes — silent assumptions, over-engineering, and out-of-scope edits — across Page Classes, test scripts, and `tools/*.py` maintenance.
@@ -3,8 +3,11 @@ name: technical-debt-harvester
3
3
  description: "Harvest shortcut: comments into a tracked technical debt ledger. Use when auditing code compromises, tracking deferred refactorings, or scanning for shortcut markers."
4
4
  category: architecture_and_analysis
5
5
  version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: read-only
9
+ filesystem: read-only
6
10
  ---
7
-
8
11
  # Technical Debt Harvester — Pragmatic Shortcut & Deferral Tracker
9
12
 
10
13
  Harvest deliberate shortcut comments (`shortcut: <limit>, <when to upgrade>`) across the entire repository into a structured Markdown ledger so pragmatic compromises do not silently rot into permanent defects.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: github-actions-templates
3
3
  description: "Create production-ready GitHub Actions workflows for automated test suites and CI/CD. Use when wiring test pipelines, matrix shards, or quality gates into GitHub Actions."
4
+ category: architecture_and_analysis
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # GitHub Actions CI/CD Patterns for Test Automation
7
12
 
8
13
  > **Target:** Author secure, performant, and matrix-sharded GitHub Actions workflows for automated test execution, quality gate validation, and Allure reporting.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: actor-qa-swarm
3
3
  description: "Asynchronous Actor Model message broker and matrix sharding coordinator for multi-agent test execution. Use when distributing parallel test workloads or wiring decoupled subagent event pub/sub."
4
+ category: context_and_optimization
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Actor QA Swarm Skill — Asynchronous Actor Messaging & Matrix Sharding
7
12
 
8
13
  > **Paradigm Attribution:** Inspired by **Microsoft AutoGen v0.4+ (AG2 Actor Framework)**.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: agent-orchestration-multi-agent-optimize
3
3
  description: "Profile, benchmark, and orchestrate multi-agent test workloads and token throughput. Use when orchestrating multi-agent swarms, partitioning workloads, or optimizing agent roles."
4
+ category: context_and_optimization
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: read-only
4
10
  ---
5
-
6
11
  # Multi-Agent Optimization & Orchestration Skill
7
12
 
8
13
  > **Target:** Optimize multi-agent test workloads, reduce context overhead, streamline agent handoffs, and monitor token consumption across autonomous test swarms.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: event-stream-qa-orchestrator
3
3
  description: "Immutable EventStream orchestrator recording deterministic action/observation timelines with SHA-256 hash chains and reversible checkpoint rollbacks. Use when tracing test executions and managing replayable state."
4
+ category: context_and_optimization
5
+ version: "1.0.0"
6
+ policies:
7
+ network: localhost-only
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # QA Event Stream Orchestrator Skill — Immutable Audit & Replay Timeline
7
12
 
8
13
  > **Paradigm Attribution:** Inspired by **All-Hands-AI OpenHands (EventStream & CodeAct Runtime)**.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: persistent-planning-files
3
3
  description: "Persist multi-step task plans, findings, and progress to three markdown files on disk so work survives context resets, compaction, and session crashes. Use when a task needs 5 or more tool calls, spans multiple phases, or must be resumable by another agent."
4
+ category: context_and_optimization
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Persistent Planning Files — Enterprise Disk-Backed Working Memory
7
12
 
8
13
  Specialized skill for running long QA tasks (suite authoring, self-heal campaigns, RCA investigations) with the context window treated as RAM and the filesystem as the only durable state.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: qa-memory-os
3
3
  description: "Hierarchical 3-tier memory operating system for test automation: Core Memory blocks, Recall step logs, and Archival semantic store with AUT version scoping. Use when managing long-term test session state, auth tokens, and preventing context rot."
4
+ category: context_and_optimization
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: read-only
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # QA Test Memory OS Skill — Hierarchical Persistent Memory
7
12
 
8
13
  > **Paradigm Attribution:** Inspired by **Letta AI / UC Berkeley SkyLab (MemGPT & MemFS)**.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: meta-prompt-crafter
3
3
  description: "Meta-prompt engineer transforming rough human requests into high-fidelity, production-grade prompts for ChatGPT, Gemini, Claude, Midjourney, and Coding AIs. Use when the user asks to write, design, refine, or optimize a prompt for another AI."
4
+ category: context_and_optimization
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: read-only
4
10
  ---
5
-
6
11
  # Meta-Prompt Crafter — Production-Grade Prompt Engineering Engine
7
12
 
8
13
  The **Meta-Prompt Crafter** skill transforms unstructured, high-level user ideas into production-ready, highly effective prompts optimized for specific target LLMs and multimodal AI systems (ChatGPT, Gemini, Claude, Midjourney, Cursor, Copilot).
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: mipro-prompt-compiler
3
3
  description: "MIPROv2 Bayesian teleprompter optimizer and few-shot compiler tuning prompt instructions against AST mutation kill scores. Use when optimizing QA prompts or compiling few-shot assertion generators."
4
+ category: architecture_and_analysis
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # MIPROv2 Prompt Compiler Skill — Bayesian Few-Shot & Assertion Optimization
7
12
 
8
13
  > **Paradigm Attribution:** Inspired by **Stanford NLP DSPy v2 (MIPROv2 Teleprompter) & Optuna TPE**.
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: qa-aci-interface
3
3
  description: "Safe Agent-Computer Interface for inspecting code windows (40-50 lines), surgical editing with pre-commit AST checks, and distilled test execution. Use when inspecting, editing, or refactoring code without context blowout."
4
+ category: architecture_and_analysis
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: read-only
9
+ filesystem: read-only
4
10
  ---
5
-
6
11
  # QA Agent-Computer Interface (ACI) Skill — Context-Safe Code Editing
7
12
 
8
13
  > **Paradigm Attribution:** Inspired by **Princeton NLP / Stanford SWE-agent ACI**.
@@ -37,4 +37,4 @@ python tools/infer_linter.py --file pages/OrderPage.py --strict
37
37
  The ACI engine automatically rejects patches that introduce:
38
38
  - Syntax errors or brace mismatches.
39
39
  - Swallowed exception handlers (`except: pass`).
40
- - Hardcoded machine-specific absolute paths (`/Users/admin/...`).
40
+ - Hardcoded machine-specific absolute paths (`/Users/<username>/...`).
@@ -1,8 +1,13 @@
1
1
  ---
2
2
  name: token-and-context-optimizer
3
3
  description: "Optimize prompt context, distill verbose logs, and prevent context rot in Antigravity. Use when optimizing prompts or reducing token and context overhead."
4
+ category: context_and_optimization
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: none
9
+ filesystem: read-only
4
10
  ---
5
-
6
11
  # Token & Context Optimizer — Antigravity Engineering Standard
7
12
 
8
13
  > **Purpose:** Master context engineering and token efficiency. Directs AI Agents to prevent context rot, mitigate Lost-in-the-Middle attention drops, offload large state to filesystem scratchpads, and maintain clean KV-cache alignment across long test automation sessions.
package/AGENTS.md CHANGED
@@ -50,6 +50,12 @@ You are a lazy senior developer. The best code is the code never written. Solve
50
50
  4. **Hard Floor (Never Cut):** Trust-boundary validation, error handling preventing data loss, security checks, accessibility (a11y), Clean POM separation, and anything explicitly requested.
51
51
  5. **End-of-Turn Risk Note:** End every code response with one or two concise lines stating what was skipped or not checked and any risks the user must know.
52
52
 
53
+ ### 2.1 Multi-Agent Handoff & Autonomy Protocols
54
+ 1. **Rulings, Not Stalls (Jesse Vincent Protocol):** Autonomous subagents must never pause execution for trivial decisions. Record every judgment as:
55
+ `Ruling: <what you decided> — <why> — <what it costs if wrong>` and proceed immediately.
56
+ 2. **Self-Contained Task Briefings (Fan-Out Invariant):** When orchestrating subagents, prompts must be fully self-contained (`BRIEFING.md` format). Subagents cannot assume access to parent context.
57
+ 3. **Doubt-Driven Falsification (Addy Osmani DDD):** Before declaring a test or locator verified, explicitly propose 3 falsification scenarios where the test passes while the feature is broken.
58
+
53
59
  ---
54
60
 
55
61
  ## 3. TRUTH ANCHOR & ON-DEMAND AUTONOMY
@@ -72,7 +78,7 @@ You are a lazy senior developer. The best code is the code never written. Solve
72
78
  - Querying / Storing verified PageClass library -> Run `tools/skill_vault.py`.
73
79
  - Vague requirements / story ambiguity -> Autonomously run `tools/interview_story.py`.
74
80
  - Optimizing assertions against surviving mutants -> Run `tools/textgrad_mutation_optimizer.py`.
75
- - User asks to push / release hub ("push lên", "push hub") -> Autonomously bump version based on changes via `tools/bump_version.py <patch|minor|major>` then run `tools/hub_publisher.py` (Push main + Tag + Release + Packages + NPM).
81
+ - User asks to push / release hub ("push lên", "push hub") -> Autonomously bump version based on changes via `tools/bump_version.py <patch|minor|major>` then run `tools/hub_publisher.py -y` (Push main + Tag + Release + Packages + NPM without stalling).
76
82
  - Task progress & compaction anchoring -> Autonomously run `tools/project_state.py`.
77
83
  - Before completing code tasks -> Autonomously run `tools/verify_all.py` (10 Quality Gates DoD). For quick fixes (< 15 lines of code), apply Fast-Track mode; for external target repos lacking `tools/`, gracefully fallback to native test runners (`npm test`, `pytest`, `mvn test`) per `.agents/rules/stack-auto-router.md` and `.agents/rules/systematic-debugging.md`.
78
84
  - Context-aware stack routing -> Strictly adhere to `.agents/rules/stack-auto-router.md` (Web/Mobile/Perf/Security scope) and 5-layer pentest safety gate (`.agents/rules/security_testing_rules.md`).
package/LICENSE CHANGED
@@ -6,8 +6,8 @@
6
6
 
7
7
  ## 🇻🇳 Phiên Bản Tiếng Việt (Tham Khảo & Giải Thích Pháp Lý)
8
8
 
9
- Bản quyền (c) 2026 Thế Vị (@TeeVee998). Toàn quyền bảo lưu.
10
- Kho mã nguồn gốc: https://github.com/TeeVee998/Synapse-Hub
9
+ Bản quyền (c) 2026 Thế Vị (@TeeVee98). Toàn quyền bảo lưu.
10
+ Kho mã nguồn gốc: https://github.com/TeeVee98/Synapse-Hub
11
11
 
12
12
  *(Lưu ý: Phần tiếng Việt dưới đây là bản giải thích tham khảo nhằm giúp cộng đồng nắm bắt rõ quyền và nghĩa vụ; văn bản tiếng Anh phía dưới là văn bản pháp lý chính thức có hiệu lực của Giấy phép MIT).*
13
13
 
@@ -18,7 +18,7 @@ Theo Giấy phép MIT, bạn được cấp quyền miễn phí, không giới h
18
18
  - **Hợp nhất & Đóng gói:** Tích hợp Synapse Hub vào các bộ kiểm thử nội bộ hoặc giải pháp của bạn.
19
19
 
20
20
  ### 2. Nghĩa vụ bắt buộc (Điều kiện tiên quyết)
21
- - **Ghi nhận nguồn tác giả gốc:** Bạn **BẮT BUỘC** phải giữ nguyên thông báo bản quyền ghi nhận tác giả **Thế Vị (@TeeVee998)** cùng liên kết mã nguồn gốc `https://github.com/TeeVee998/Synapse-Hub` trong toàn bộ các bản sao hoặc các phần quan trọng của phần mềm.
21
+ - **Ghi nhận nguồn tác giả gốc:** Bạn **BẮT BUỘC** phải giữ nguyên thông báo bản quyền ghi nhận tác giả **Thế Vị (@TeeVee98)** cùng liên kết mã nguồn gốc `https://github.com/TeeVee98/Synapse-Hub` trong toàn bộ các bản sao hoặc các phần quan trọng của phần mềm.
22
22
  - Nghiêm cấm hành vi xóa bỏ bản quyền hoặc mạo danh quyền tác giả.
23
23
 
24
24
  ### 3. Tuyên bố miễn trừ trách nhiệm
@@ -30,8 +30,8 @@ Phần mềm được cung cấp theo nguyên trạng ("AS IS"), không có bấ
30
30
 
31
31
  MIT License
32
32
 
33
- Copyright (c) 2026 Thế Vị (@TeeVee998). All rights reserved.
34
- Original Repository: https://github.com/TeeVee998/Synapse-Hub
33
+ Copyright (c) 2026 Thế Vị (@TeeVee98). All rights reserved.
34
+ Original Repository: https://github.com/TeeVee98/Synapse-Hub
35
35
 
36
36
  Permission is hereby granted, free of charge, to any person obtaining a copy
37
37
  of this software and associated documentation files (the "Software"), to deal
package/NOTICE CHANGED
@@ -1,5 +1,5 @@
1
1
  Synapse Hub
2
- Copyright (c) 2026 Thế Vị (@TeeVee998). Distributed under the MIT License.
2
+ Copyright (c) 2026 Thế Vị (@TeeVee98). Distributed under the MIT License.
3
3
 
4
4
  This software includes threat vector taxonomy, static rule categories, and security concepts
5
5
  inspired by:
package/README.en.md CHANGED
@@ -6,13 +6,13 @@
6
6
 
7
7
  > **Core Mission:** A standalone linter and guardrail engine (zero external dependencies for core engine & DoD gates) safeguarding automated test suites when AI writes code — Automatically catching "fake-pass" tests (0 assertions, tautologies), eliminating fixed sleeps, compressing 95% of CI/CD log noise, and enforcing Clean POM architecture.
8
8
  > **Author:** Thế Vị ([@TeeVee98](https://github.com/TeeVee98)) | **License:** MIT License
9
- > **Version:** `v4.1.3` | **Scale:** 53 Standardized QA Skills, 9 Specialized AI Agents, 10 DoD Quality Gates.
9
+ > **Version:** `v4.2.0` | **Scale:** 53 Standardized QA Skills, 9 Specialized AI Agents, 10 DoD Quality Gates.
10
10
 
11
11
  [![npm version](https://img.shields.io/npm/v/@teevee98/synapse-hub.svg?style=flat-square&color=blue)](https://www.npmjs.com/package/@teevee98/synapse-hub)
12
12
  [![node version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg?style=flat-square)](https://nodejs.org)
13
13
  [![python version](https://img.shields.io/badge/python-%3E%3D3.10-blue.svg?style=flat-square)](https://python.org)
14
14
  [![Quality Gates](https://img.shields.io/badge/Quality%20Gates-10%2F10%20DoD%20PASS-success.svg?style=flat-square)](docs/QUALITY_GATES.en.md)
15
- [![Tests](https://img.shields.io/badge/tests-880%2B%20passing-brightgreen.svg?style=flat-square)](#)
15
+ [![Tests](https://img.shields.io/badge/tests-passing-brightgreen.svg?style=flat-square)](#)
16
16
  [![license](https://img.shields.io/badge/license-MIT-green.svg?style=flat-square)](https://github.com/TeeVee98/Synapse-Hub/blob/main/LICENSE)
17
17
  [![Ecosystem](https://img.shields.io/badge/AI%20Ecosystem-Antigravity%20%7C%20Cursor%20%7C%20Claude%20%7C%20Copilot%20%7C%20Windsurf-orange.svg?style=flat-square)](#)
18
18
 
@@ -86,7 +86,7 @@ npx @teevee98/synapse-hub verify
86
86
  ```
87
87
 
88
88
  > 💡 **Tip:** Install globally to invoke `synapse-hub <command>` directly without `npx`:
89
- > `npm install -g @teevee98/synapse-hub` (or via Python: `pip install agent-qa`)
89
+ > `npm install -g @teevee98/synapse-hub` (or via Python: `pip install synapse-hub`)
90
90
 
91
91
  > 📦 **Enterprise Reference Test Suites:** Inspect working sample projects adhering to Clean POM & Guardrails in [`examples/`](examples/):
92
92
  > [🎭 Playwright TS](examples/playwright-crm-suite) • [🌲 Cypress E2E](examples/cypress-ecommerce-suite) • [🐍 Pytest API](examples/pytest-api-suite) • [☕ Katalon Studio](examples/katalon-suite) • [🌐 Selenium Java](examples/selenium-suite)
@@ -154,7 +154,7 @@ Every test code change must satisfy all 10 Quality Gates before pull request mer
154
154
  # Pre-commit hook (.pre-commit-config.yaml):
155
155
  repos:
156
156
  - repo: https://github.com/TeeVee98/Synapse-Hub
157
- rev: v4.1.3
157
+ rev: v4.2.0
158
158
  hooks:
159
159
  - id: synapse-lint
160
160
  - id: synapse-verify
package/README.md CHANGED
@@ -6,13 +6,13 @@
6
6
 
7
7
  > **Định vị cốt lõi:** Bộ Linter & Guardrails độc lập (zero external dependencies cho core engine & DoD gates) bảo vệ độ tin cậy của test suite khi AI viết code — Tự động bắt test "pass ảo" (0 assert, tautology), loại bỏ hoàn toàn sleep cố định, nén 95% log CI/CD, và chuẩn hóa cấu trúc Clean POM.
8
8
  > **Tác giả:** Thế Vị ([@TeeVee98](https://github.com/TeeVee98)) | **Giấy phép:** MIT License
9
- > **Phiên bản:** `v4.1.3` | **Quy mô:** 53 Kỹ năng QA, 9 Vai trò AI Agent, 10 Cổng kiểm định DoD.
9
+ > **Phiên bản:** `v4.2.0` | **Quy mô:** 53 Kỹ năng QA, 9 Vai trò AI Agent, 10 Cổng kiểm định DoD.
10
10
 
11
11
  [![npm version](https://img.shields.io/npm/v/@teevee98/synapse-hub.svg?style=flat-square&color=blue)](https://www.npmjs.com/package/@teevee98/synapse-hub)
12
12
  [![node version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg?style=flat-square)](https://nodejs.org)
13
13
  [![python version](https://img.shields.io/badge/python-%3E%3D3.10-blue.svg?style=flat-square)](https://python.org)
14
14
  [![Quality Gates](https://img.shields.io/badge/Quality%20Gates-10%2F10%20DoD%20PASS-success.svg?style=flat-square)](docs/QUALITY_GATES.md)
15
- [![Tests](https://img.shields.io/badge/tests-880%2B%20passing-brightgreen.svg?style=flat-square)](#)
15
+ [![Tests](https://img.shields.io/badge/tests-passing-brightgreen.svg?style=flat-square)](#)
16
16
  [![license](https://img.shields.io/badge/license-MIT-green.svg?style=flat-square)](https://github.com/TeeVee98/Synapse-Hub/blob/main/LICENSE)
17
17
  [![Ecosystem](https://img.shields.io/badge/AI%20Ecosystem-Antigravity%20%7C%20Cursor%20%7C%20Claude%20%7C%20Copilot%20%7C%20Windsurf-orange.svg?style=flat-square)](#)
18
18
 
@@ -86,7 +86,7 @@ npx @teevee98/synapse-hub verify
86
86
  ```
87
87
 
88
88
  > 💡 **Mẹo:** Cài đặt toàn cục để gõ trực tiếp `synapse-hub <lệnh>` không cần tiền tố `npx`:
89
- > `npm install -g @teevee98/synapse-hub` (hoặc qua Python: `pip install agent-qa`)
89
+ > `npm install -g @teevee98/synapse-hub` (hoặc qua Python: `pip install synapse-hub`)
90
90
 
91
91
  > 📦 **Kho Dự Án Mẫu Doanh Nghiệp (Reference Suites):** Xem các dự án mẫu đã chuẩn hóa Clean POM & Guardrails tại [`examples/`](examples/):
92
92
  > [🎭 Playwright TS](examples/playwright-crm-suite) • [🌲 Cypress E2E](examples/cypress-ecommerce-suite) • [🐍 Pytest API](examples/pytest-api-suite) • [☕ Katalon Studio](examples/katalon-suite) • [🌐 Selenium Java](examples/selenium-suite)
@@ -154,7 +154,7 @@ Mọi thay đổi mã nguồn kiểm thử đều được kiểm chứng qua 10
154
154
  # Pre-commit hook (.pre-commit-config.yaml):
155
155
  repos:
156
156
  - repo: https://github.com/TeeVee98/Synapse-Hub
157
- rev: v4.1.3
157
+ rev: v4.2.0
158
158
  hooks:
159
159
  - id: synapse-lint
160
160
  - id: synapse-verify
package/agentskills.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "$schema": "https://agentskills.io/schema/v1.json",
3
3
  "name": "Synapse-Hub",
4
- "version": "4.1.3",
4
+ "version": "4.2.0",
5
5
  "description": "Enterprise QA & Test Automation AI Skills Ecosystem — 53 skills organised across 11 Domain Packages adhering to Clean POM Flat Architecture.",
6
6
  "author": "Thế Vị (@TeeVee98)",
7
7
  "repository": "https://github.com/TeeVee98/Synapse-Hub",
@@ -3,7 +3,7 @@
3
3
  [🇻🇳 Tiếng Việt](ARCHITECTURE.md) | [🇬🇧 English Edition](ARCHITECTURE.en.md)
4
4
 
5
5
  > **Scope:** Enterprise Multi-Agent QA Hub
6
- > **Version:** `4.1.3` | **Status:** Active / Production Standard
6
+ > **Version:** `4.2.0` | **Status:** Active / Production Standard
7
7
 
8
8
  ---
9
9
 
@@ -191,7 +191,7 @@ To maintain strict engineering rigor (**Truth Anchor**), Synapse Hub discloses a
191
191
  1. **Static Heuristic Mutation Testing vs Runtime Mutation Testing:**
192
192
  `tools/micro_mutator.py` in static mode performs fast heuristic assertion reachability analysis (~0.1s) to detect unasserted branches and weak assertions. This is a lexical reachability and dataflow heuristic, **not** a compiler-grade runtime mutation testing engine (such as Stryker or mutmut). To avoid inflated assertion scores and obtain ground-truth mutation kill rates, execute in Dynamic mode (`--test-cmd`) against real test runners.
193
193
  2. **Empirical Benchmarks (Self-Reported Baseline):**
194
- The metrics (25/25 challenges resolved, 76.2 tokens/bug) reflect author-measured internal baselines on curated challenges (`benchmarks/qa_eval`) rather than independent third-party double-blind audits. Metrics may vary on real-world enterprise suites depending on architectural complexity and test coverage.
194
+ The metrics (45/45 challenges resolved across 11 domains, 93.8 tokens/bug) reflect author-measured internal baselines on curated challenges (`benchmarks/qa_eval`) rather than independent third-party double-blind audits. Metrics may vary on real-world enterprise suites depending on architectural complexity and test coverage.
195
195
  3. **Hub-Spoke Version Pinning (Blast-Radius Isolation):**
196
196
  When mounting or referencing Synapse Hub in downstream Spoke projects, downstream repositories should pin a specific Git Submodule commit or release tag (`git checkout v4.1.1`) rather than tracking unpinned `main` HEAD, preventing upstream Hub changes from unexpectedly breaking downstream CI/CD pipelines.
197
197
  4. **Supported Runners:**
@@ -3,7 +3,7 @@
3
3
  [🇻🇳 Tiếng Việt](ARCHITECTURE.md) | [🇬🇧 English Edition](ARCHITECTURE.en.md)
4
4
 
5
5
  > **Phạm vi:** Enterprise Multi-Agent QA Hub
6
- > **Version:** `4.1.3` | **Trạng thái:** Hoạt động / Tiêu chuẩn Sản xuất
6
+ > **Version:** `4.2.0` | **Trạng thái:** Hoạt động / Tiêu chuẩn Sản xuất
7
7
  > **Tác giả:** Thế Vị (@TeeVee98) | **Giấy phép:** MIT License
8
8
 
9
9
  ---
@@ -192,7 +192,7 @@ flowchart TD
192
192
  1. **Quét Nhạy Cảm Assert Tĩnh (Heuristic) vs Đột Biến Runtime:**
193
193
  `tools/micro_mutator.py` ở chế độ tĩnh sử dụng phân tích độ nhạy assert heuristic (~0.1s) để phát hiện nhanh nhánh rẽ thiếu assert hoặc assertion lỏng lẻo. Đây là cơ chế ước tính độ phủ ngữ nghĩa (reachability & dataflow heuristic), **không phải** công cụ mutation testing thực thi mã cấp trình biên dịch (như Stryker hay mutmut). Để có điểm mutation thực tế không bị thổi phồng, cần chạy chế độ Dynamic (`--test-cmd`) để thực thi test suite trực tiếp trên từng mutant.
194
194
  2. **Kết Quả Benchmark Thực Nghiệm (Self-Reported Baseline):**
195
- Các chỉ số 25/25 bài toán (100.0%) và 76.2 token / lỗi là kết quả đo lường nội bộ do tác giả thực hiện trên bộ benchmark curated nội bộ (`benchmarks/qa_eval`), chưa qua kiểm chứng độc lập của bên thứ ba (third-party double-blind benchmark). Khi áp dụng vào dự án thực tế với kiến trúc phức tạp, các chỉ số có thể thay đổi tùy thuộc vào độ bao phủ của bộ test.
195
+ Các chỉ số 45/45 bài toán trên 11 nhóm miền lỗi (100.0%) và 93.8 token / lỗi là kết quả đo lường nội bộ do tác giả thực hiện trên bộ benchmark curated nội bộ (`benchmarks/qa_eval`), chưa qua kiểm chứng độc lập của bên thứ ba (third-party double-blind benchmark). Khi áp dụng vào dự án thực tế với kiến trúc phức tạp, các chỉ số có thể thay đổi tùy thuộc vào độ bao phủ của bộ test.
196
196
  3. **Cơ Chế Pin Version Hub-Spoke (Chống Lỗi Lan Truyền):**
197
197
  Khi tích hợp Synapse Hub vào các dự án Spoke, khuyến nghị bắt buộc pin phiên bản qua Git Submodule commit cụ thể hoặc git release tag (`git checkout v4.1.1`), tránh kéo trực tiếp nhánh `main` tự động để không làm ảnh hưởng pipeline của các Spoke khi Hub có cập nhật chưa kiểm duyệt.
198
198
  4. **Test Framework Được Hỗ Trợ Tốt Nhất:**
@@ -201,3 +201,12 @@ flowchart TD
201
201
  - Node.js >= 18.0.0 (khuyên dùng Node 20 hoặc 22 LTS).
202
202
  - Python >= 3.10 (đã kiểm thử đầy đủ trên 3.10, 3.11, 3.12, 3.13, 3.15).
203
203
  - Trình duyệt headless: Cần cài đặt Playwright Chromium để dùng tính năng dò phần tử DOM và tự sửa locator.
204
+
205
+ ---
206
+
207
+ ## 10. Chuẩn Mực Quản Trị Đa Cấp Monorepo (Hierarchical AGENTS.md & Lowest-Layer Design)
208
+
209
+ Học hỏi từ các monorepo quy mô toàn cầu (Next.js, Cloudflare Workers-SDK, Airflow, Sentry):
210
+ 1. **Phân Tầng Đa Cấp (Hierarchical Scoping):** Thay vì duy trì một tệp quy tắc 4,000 dòng cồng kềnh tại thư mục gốc, hệ thống áp dụng mô hình phân tán: tệp `AGENTS.md` gốc chỉ định các bất biến toàn cục (DoD, Clean POM, UTF-8 No BOM, Zero Secret Leaks). Các package con (`packages/*/AGENTS.md`) chịu trách nhiệm về tooling, runner và phạm vi kiểm thử hẹp tương ứng.
211
+ 2. **Nguyên Lý Thiết Kế Tầng Thấp Nhất (Lowest-Layer Design Axiom):** Khi thực hiện kiểm thử hoặc sửa đổi mã nguồn trong kiến trúc monorepo, quy tắc và test command luôn được kích hoạt tại package thấp nhất có thể (ví dụ: `pnpm test -F <package>` thay vì chạy toàn bộ workspace) nhằm giảm thiểu bán kính rủi ro (blast radius) và bảo vệ lockfile monorepo.
212
+ 3. **Nguồn Chân Lý Duy Nhất (Single Source of Truth):** `AGENTS.md` là nguồn chân lý duy nhất cho toàn bộ AI coding agents (Claude, Cursor, Copilot, Windsurf, Antigravity). Các cấu hình khác (`.cursorrules`, `CLAUDE.md`) chỉ đóng vai trò symlink hoặc con trỏ kế thừa.
@@ -1,16 +1,18 @@
1
- # Agent-QA CLI & Tools Reference Manual
1
+ # Synapse-Hub CLI & Tools Reference Manual
2
2
 
3
3
  [🇻🇳 Tiếng Việt](CLI_REFERENCE.md) | [🇬🇧 English Edition](CLI_REFERENCE.en.md)
4
4
 
5
- The `Synapse Hub` provides a unified CLI utility `agent-qa` (and direct python scripts in `tools/`) to execute quality gates, linting, impact analysis, and log distillation.
5
+ The `Synapse Hub` ecosystem provides a unified CLI utility `synapse-hub` (or legacy `agent-qa`, along with direct Python scripts in `tools/`) to execute quality gates, linting, impact analysis, and log distillation.
6
6
 
7
7
  ---
8
8
 
9
- ## 1. Unified CLI Entrypoint (`agent-qa`)
9
+ ## 1. Unified CLI Entrypoint (`synapse-hub` / `agent-qa`)
10
10
 
11
- When installed via `pip install -e .`, the `agent-qa` command is globally accessible:
11
+ After installing globally via `npm install -g @teevee98/synapse-hub` or via Python `pip install synapse-hub` (or `pip install -e .` for local development), the command is globally accessible:
12
12
 
13
13
  ```bash
14
+ synapse-hub <command> [options]
15
+ # or
14
16
  agent-qa <command> [options]
15
17
  ```
16
18
 
@@ -8,7 +8,7 @@ Hệ sinh thái Synapse Hub cung cấp công cụ dòng lệnh `synapse-hub` (ho
8
8
 
9
9
  ## 1. Điểm Vào Dòng Lệnh Thống Nhất (`synapse-hub` / `agent-qa`)
10
10
 
11
- Sau khi cài đặt qua `npm install -g @teevee98/synapse-hub` hoặc `pip install -e .`, bạn có thể gõ trực tiếp:
11
+ Sau khi cài đặt qua `npm install -g @teevee98/synapse-hub` hoặc qua Python `pip install synapse-hub` (hoặc `pip install -e .`), bạn có thể gõ trực tiếp:
12
12
 
13
13
  ```bash
14
14
  synapse-hub <lệnh> [tùy_chọn]
@@ -28,7 +28,7 @@ Every skill resides in `.agents/skills/<category>/<skill-name>/` (across 11 doma
28
28
  Before submitting a pull request or committing changes:
29
29
 
30
30
  ```bash
31
- # 1. Run regression test suite (770+ tests)
31
+ # 1. Run regression test suite (1,001+ tests)
32
32
  pytest tests -q
33
33
 
34
34
  # 2. Verify all 10 DoD Quality Gates (Gate 1–10)
@@ -28,8 +28,8 @@ Mỗi kỹ năng nằm trong thư mục riêng `.agents/skills/<category>/<ten-k
28
28
  Trước khi mở PR hoặc đẩy code lên nhánh `develop`:
29
29
 
30
30
  ```bash
31
- # 1. Chạy toàn bộ 260+ bài unit test
32
- python3 -m unittest discover tests
31
+ # 1. Chạy toàn bộ 1,001+ bài unit test
32
+ pytest tests -q
33
33
 
34
34
  # 2. Kiểm định toàn vẹn 10 Cổng Chất Lượng DoD (Gate 1–10)
35
35
  python3 tools/verify_all.py