@teevee98/synapse-hub 4.1.4 → 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 (116) 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/e2e-testing-patterns/SKILL.md +6 -1
  6. package/.agents/skills/01-web-automation/katalon-cli-runner/SKILL.md +6 -1
  7. package/.agents/skills/01-web-automation/lam-script-generator/SKILL.md +6 -1
  8. package/.agents/skills/01-web-automation/mobile-appium-som/SKILL.md +6 -1
  9. package/.agents/skills/01-web-automation/mobile-appium-som/examples/BaseScreen.java +2 -2
  10. package/.agents/skills/01-web-automation/mobile-appium-som/examples/LoginScreen.java +2 -2
  11. package/.agents/skills/01-web-automation/mobile-appium-som/examples/TC_MobileLogin.java +2 -2
  12. package/.agents/skills/01-web-automation/playwright-live-interaction/SKILL.md +7 -2
  13. package/.agents/skills/01-web-automation/playwright-webapp-testing/SKILL.md +6 -1
  14. package/.agents/skills/01-web-automation/web-agent-gym-benchmarking/SKILL.md +6 -1
  15. package/.agents/skills/02-test-design/architecture-decision-records/SKILL.md +6 -1
  16. package/.agents/skills/02-test-design/gherkin-to-suite/SKILL.md +6 -1
  17. package/.agents/skills/02-test-design/rbt-manual-testing/SKILL.md +6 -1
  18. package/.agents/skills/02-test-design/review-spec/SKILL.md +4 -1
  19. package/.agents/skills/02-test-design/tot-exploratory-testing/SKILL.md +6 -1
  20. package/.agents/skills/03-api-and-contracts/api-network-mocking-interception/SKILL.md +6 -1
  21. package/.agents/skills/03-api-and-contracts/api-spec-to-e2e-matrix/SKILL.md +6 -1
  22. package/.agents/skills/03-api-and-contracts/consumer-driven-contract-testing/SKILL.md +7 -2
  23. package/.agents/skills/04-performance-and-load/backend-load-and-stress-patterns/SKILL.md +7 -2
  24. package/.agents/skills/04-performance-and-load/lean-impact-scoreboard/SKILL.md +4 -1
  25. package/.agents/skills/04-performance-and-load/web-vitals-and-performance-profiler/SKILL.md +6 -1
  26. package/.agents/skills/05-security-and-compliance/security-dast-sentinel/SKILL.md +6 -1
  27. package/.agents/skills/05-security-and-compliance/skillspector-security-guard/SKILL.md +6 -1
  28. package/.agents/skills/05-security-and-compliance/wcag-audit-patterns/SKILL.md +6 -1
  29. package/.agents/skills/06-healing-and-resilience/agentless-qa-repair/SKILL.md +6 -1
  30. package/.agents/skills/06-healing-and-resilience/antigravity-test-sentinel/SKILL.md +6 -1
  31. package/.agents/skills/06-healing-and-resilience/failure-autopsy-and-healing/SKILL.md +7 -2
  32. package/.agents/skills/06-healing-and-resilience/flaky-test-sentinel-and-quarantine/SKILL.md +6 -1
  33. package/.agents/skills/06-healing-and-resilience/self-healing-locator/SKILL.md +6 -1
  34. package/.agents/skills/06-healing-and-resilience/systematic-debugging/SKILL.md +6 -1
  35. package/.agents/skills/06-healing-and-resilience/test-driven-development/SKILL.md +6 -1
  36. package/.agents/skills/06-healing-and-resilience/verification-before-completion/SKILL.md +6 -1
  37. package/.agents/skills/06-healing-and-resilience/visual-regression-sentinel/SKILL.md +6 -1
  38. package/.agents/skills/07-data-and-state/db-state-verifier-and-seeder/SKILL.md +6 -1
  39. package/.agents/skills/07-data-and-state/file-and-report-validator/SKILL.md +6 -1
  40. package/.agents/skills/07-data-and-state/synthetic-test-data-generator/SKILL.md +6 -1
  41. package/.agents/skills/08-code-quality/code-refactoring-refactor-clean/SKILL.md +6 -1
  42. package/.agents/skills/08-code-quality/graphify-impact-analyzer/SKILL.md +6 -1
  43. package/.agents/skills/08-code-quality/lean-code-ladder/SKILL.md +6 -1
  44. package/.agents/skills/08-code-quality/repo-quality-audit/SKILL.md +4 -1
  45. package/.agents/skills/08-code-quality/senior-code-review/SKILL.md +4 -1
  46. package/.agents/skills/08-code-quality/surgical-coding-principles/SKILL.md +6 -1
  47. package/.agents/skills/08-code-quality/technical-debt-harvester/SKILL.md +4 -1
  48. package/.agents/skills/09-ci-and-devops/github-actions-templates/SKILL.md +6 -1
  49. package/.agents/skills/10-agent-orchestration/actor-qa-swarm/SKILL.md +6 -1
  50. package/.agents/skills/10-agent-orchestration/agent-orchestration-multi-agent-optimize/SKILL.md +6 -1
  51. package/.agents/skills/10-agent-orchestration/event-stream-qa-orchestrator/SKILL.md +6 -1
  52. package/.agents/skills/10-agent-orchestration/persistent-planning-files/SKILL.md +6 -1
  53. package/.agents/skills/10-agent-orchestration/qa-memory-os/SKILL.md +6 -1
  54. package/.agents/skills/11-ai-and-prompting/meta-prompt-crafter/SKILL.md +6 -1
  55. package/.agents/skills/11-ai-and-prompting/mipro-prompt-compiler/SKILL.md +6 -1
  56. package/.agents/skills/11-ai-and-prompting/qa-aci-interface/SKILL.md +6 -1
  57. package/.agents/skills/11-ai-and-prompting/token-and-context-optimizer/SKILL.md +6 -1
  58. package/AGENTS.md +7 -1
  59. package/LICENSE +5 -5
  60. package/NOTICE +1 -1
  61. package/README.en.md +4 -4
  62. package/README.md +4 -4
  63. package/agentskills.json +1 -1
  64. package/docs/ARCHITECTURE.en.md +2 -2
  65. package/docs/ARCHITECTURE.md +11 -2
  66. package/docs/CLI_REFERENCE.en.md +6 -4
  67. package/docs/CLI_REFERENCE.md +1 -1
  68. package/docs/CONTRIBUTING.en.md +1 -1
  69. package/docs/CONTRIBUTING.md +2 -2
  70. package/docs/TOOL_CATALOG.md +6 -2
  71. package/docs/research/agent_skill_training_analysis.md +1 -1
  72. package/package.json +1 -1
  73. package/plugin.json +1 -1
  74. package/skills_manifest.json +320 -55
  75. package/synapse.config.json +1 -1
  76. package/templates/ui/index.html +2 -2
  77. package/tools/TOOL_CATALOG.json +63 -3
  78. package/tools/__init__.py +1 -1
  79. package/tools/api_fuzzer.py +179 -118
  80. package/tools/author_integrity.py +121 -11
  81. package/tools/benchmark_swarm_context.py +119 -18
  82. package/tools/break_ui_generator.py +233 -0
  83. package/tools/browser_helpers.js +2 -2
  84. package/tools/check_version_sync.py +18 -50
  85. package/tools/cli.py +109 -18
  86. package/tools/core/bm25_retriever.py +218 -0
  87. package/tools/core/i18n.py +4 -4
  88. package/tools/core/provider_usage_adapter.py +317 -0
  89. package/tools/core/token_estimator.py +42 -14
  90. package/tools/count_tokens.py +5 -0
  91. package/tools/coverage_reporter.py +245 -0
  92. package/tools/dashboard_generator.py +6 -6
  93. package/tools/db_sandbox.py +146 -4
  94. package/tools/distill_skill.py +191 -0
  95. package/tools/git_pre_commit_guard.py +12 -0
  96. package/tools/humanize_linter.py +3 -0
  97. package/tools/mcp_docx_server.py +1 -1
  98. package/tools/mcp_excel_server.py +1 -1
  99. package/tools/mcp_server.py +75 -15
  100. package/tools/micro_mutator.py +84 -14
  101. package/tools/pentest_scope_guard.py +399 -56
  102. package/tools/perf/benchmark_perf_runner.py +42 -0
  103. package/tools/rules_router.py +401 -41
  104. package/tools/security_scanner.py +80 -0
  105. package/tools/senior_code_review.py +14 -0
  106. package/tools/skill_canonical_digest.py +244 -0
  107. package/tools/skill_profiles.py +77 -7
  108. package/tools/slide_deck_exporter.py +477 -0
  109. package/tools/sync_skills_manifest.py +166 -0
  110. package/tools/task_memory_manager.py +260 -0
  111. package/tools/ui_server.py +1 -1
  112. package/tools/update_sentinel.py +3 -3
  113. package/tools/validate_host_interop.py +485 -0
  114. package/tools/validate_skills_schema.py +282 -0
  115. package/tools/verify_all.py +572 -42
  116. package/tools/welcome_page.py +2 -2
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "$schema": "https://json-schema.org/draft/2020-12/schema",
3
3
  "name": "Synapse-Hub",
4
- "version": "4.1.4",
4
+ "version": "4.2.0",
5
5
  "description": "Unified Catalog of 53 Skills across 11 Domain Packages for Enterprise QA AI Agents.",
6
6
  "totalSkills": 53,
7
7
  "domains": {
@@ -330,7 +330,12 @@
330
330
  "profiles": [
331
331
  "core-web-qa"
332
332
  ],
333
- "description": "Build and refactor Clean POM Page Classes adhering to Flat Architecture standards. Use when designing Clean POM page classes or enforcing zero-locator discipline in scripts."
333
+ "description": "Build and refactor Clean POM Page Classes adhering to Flat Architecture standards. Use when designing Clean POM page classes or enforcing zero-locator discipline in scripts.",
334
+ "policies": {
335
+ "network": "none",
336
+ "shell": "workspace-sandbox",
337
+ "filesystem": "workspace-sandbox"
338
+ }
334
339
  },
335
340
  {
336
341
  "id": "e2e-testing-patterns",
@@ -343,7 +348,12 @@
343
348
  "profiles": [
344
349
  "core-web-qa"
345
350
  ],
346
- "description": "Design robust multi-browser E2E test architectures, parallel sharding, and retry governance. Use when designing end-to-end test suites for web applications."
351
+ "description": "Design robust multi-browser E2E test architectures, parallel sharding, and retry governance. Use when designing end-to-end test suites for web applications.",
352
+ "policies": {
353
+ "network": "none",
354
+ "shell": "workspace-sandbox",
355
+ "filesystem": "workspace-sandbox"
356
+ }
347
357
  },
348
358
  {
349
359
  "id": "playwright-live-interaction",
@@ -356,7 +366,12 @@
356
366
  "profiles": [
357
367
  "core-web-qa"
358
368
  ],
359
- "description": "Probe live web DOM/AOM and verify selectors under 200ms using headless Playwright. Use when probing live DOM/AOM, verifying selectors, or debugging a live browser session."
369
+ "description": "Probe live web DOM/AOM and verify selectors under 200ms using headless Playwright. Use when probing live DOM/AOM, verifying selectors, or debugging a live browser session.",
370
+ "policies": {
371
+ "network": "localhost-only",
372
+ "shell": "workspace-sandbox",
373
+ "filesystem": "workspace-sandbox"
374
+ }
360
375
  },
361
376
  {
362
377
  "id": "playwright-webapp-testing",
@@ -369,7 +384,12 @@
369
384
  "profiles": [
370
385
  "core-web-qa"
371
386
  ],
372
- "description": "Drive Playwright test runs against a local web application with a managed server lifecycle: start, wait for readiness, run automation, and guarantee teardown. Use when verifying frontend functionality or debugging UI behavior of a dynamic webapp that must be started before testing."
387
+ "description": "Drive Playwright test runs against a local web application with a managed server lifecycle: start, wait for readiness, run automation, and guarantee teardown. Use when verifying frontend functionality or debugging UI behavior of a dynamic webapp that must be started before testing.",
388
+ "policies": {
389
+ "network": "localhost-only",
390
+ "shell": "workspace-sandbox",
391
+ "filesystem": "workspace-sandbox"
392
+ }
373
393
  },
374
394
  {
375
395
  "id": "lam-script-generator",
@@ -382,7 +402,12 @@
382
402
  "profiles": [
383
403
  "core-web-qa"
384
404
  ],
385
- "description": "Transform user stories and acceptance criteria into Clean POM automation scripts. Use when the user provides a user story, acceptance criteria, or requirement document that must become a runnable script."
405
+ "description": "Transform user stories and acceptance criteria into Clean POM automation scripts. Use when the user provides a user story, acceptance criteria, or requirement document that must become a runnable script.",
406
+ "policies": {
407
+ "network": "none",
408
+ "shell": "none",
409
+ "filesystem": "workspace-sandbox"
410
+ }
386
411
  },
387
412
  {
388
413
  "id": "auth-session-and-cookie-manager",
@@ -395,7 +420,12 @@
395
420
  "profiles": [
396
421
  "core-web-qa"
397
422
  ],
398
- "description": "Manage browser authentication sessions, storageState, JWT tokens, and multi-role state. Use when managing login sessions, storage state, or cookie reuse across tests."
423
+ "description": "Manage browser authentication sessions, storageState, JWT tokens, and multi-role state. Use when managing login sessions, storage state, or cookie reuse across tests.",
424
+ "policies": {
425
+ "network": "localhost-only",
426
+ "shell": "workspace-sandbox",
427
+ "filesystem": "workspace-sandbox"
428
+ }
399
429
  },
400
430
  {
401
431
  "id": "katalon-cli-runner",
@@ -408,7 +438,12 @@
408
438
  "profiles": [
409
439
  "core-web-qa"
410
440
  ],
411
- "description": "Execute headless Katalon and Gradle test runners with automatic driver cleanup. Use when running Katalon suites headless or integrating KRE into CI/CD."
441
+ "description": "Execute headless Katalon and Gradle test runners with automatic driver cleanup. Use when running Katalon suites headless or integrating KRE into CI/CD.",
442
+ "policies": {
443
+ "network": "localhost-only",
444
+ "shell": "workspace-sandbox",
445
+ "filesystem": "workspace-sandbox"
446
+ }
412
447
  },
413
448
  {
414
449
  "id": "bats-testing-patterns",
@@ -421,7 +456,12 @@
421
456
  "profiles": [
422
457
  "core-web-qa"
423
458
  ],
424
- "description": "Test bash/sh scripts, CLI tools, and CI/CD pipelines with Bats. Use when writing Bash automation tests with the BATS framework."
459
+ "description": "Test bash/sh scripts, CLI tools, and CI/CD pipelines with Bats. Use when writing Bash automation tests with the BATS framework.",
460
+ "policies": {
461
+ "network": "none",
462
+ "shell": "workspace-sandbox",
463
+ "filesystem": "workspace-sandbox"
464
+ }
425
465
  },
426
466
  {
427
467
  "id": "mobile-appium-som",
@@ -434,7 +474,12 @@
434
474
  "profiles": [
435
475
  "core-web-qa"
436
476
  ],
437
- "description": "Enterprise Screen Object Model (SOM) and Appium mobile automation standards for iOS and Android. Use when authoring, refactoring, or executing native or hybrid mobile tests with Appium, UIAutomator2, or XCUITest."
477
+ "description": "Enterprise Screen Object Model (SOM) and Appium mobile automation standards for iOS and Android. Use when authoring, refactoring, or executing native or hybrid mobile tests with Appium, UIAutomator2, or XCUITest.",
478
+ "policies": {
479
+ "network": "localhost-only",
480
+ "shell": "workspace-sandbox",
481
+ "filesystem": "workspace-sandbox"
482
+ }
438
483
  },
439
484
  {
440
485
  "id": "web-agent-gym-benchmarking",
@@ -447,7 +492,12 @@
447
492
  "profiles": [
448
493
  "core-web-qa"
449
494
  ],
450
- "description": "Empirical benchmark harness evaluating web agents and Page Classes against standardized enterprise tasks with headless <200ms latency budgets and ground-truth DB state verification. Use when benchmarking web agents or certifying Page Classes."
495
+ "description": "Empirical benchmark harness evaluating web agents and Page Classes against standardized enterprise tasks with headless <200ms latency budgets and ground-truth DB state verification. Use when benchmarking web agents or certifying Page Classes.",
496
+ "policies": {
497
+ "network": "localhost-only",
498
+ "shell": "workspace-sandbox",
499
+ "filesystem": "workspace-sandbox"
500
+ }
451
501
  },
452
502
  {
453
503
  "id": "rbt-manual-testing",
@@ -460,7 +510,12 @@
460
510
  "profiles": [
461
511
  "enterprise-rbt"
462
512
  ],
463
- "description": "Comprehensive Risk-Based Testing (AI-RBT) 6-stage manual test case generation, Ambiguity Q&A analysis, Traceability Matrix, Field-Level Validation Checklist (15 input field types), Non-Functional scenarios (Double-Submit, Race Conditions), and Excel export formatting. Use when generating risk-based manual test cases and exploratory charters."
513
+ "description": "Comprehensive Risk-Based Testing (AI-RBT) 6-stage manual test case generation, Ambiguity Q&A analysis, Traceability Matrix, Field-Level Validation Checklist (15 input field types), Non-Functional scenarios (Double-Submit, Race Conditions), and Excel export formatting. Use when generating risk-based manual test cases and exploratory charters.",
514
+ "policies": {
515
+ "network": "none",
516
+ "shell": "none",
517
+ "filesystem": "workspace-sandbox"
518
+ }
464
519
  },
465
520
  {
466
521
  "id": "gherkin-to-suite",
@@ -473,7 +528,12 @@
473
528
  "profiles": [
474
529
  "enterprise-rbt"
475
530
  ],
476
- "description": "Compile Gherkin .feature files into an expanded test matrix, hub Universal IR and a proven-vs-owed coverage-gap report with zero LLM tokens. Use when the user supplies BDD .feature specs or wants a BDD suite audited before codification."
531
+ "description": "Compile Gherkin .feature files into an expanded test matrix, hub Universal IR and a proven-vs-owed coverage-gap report with zero LLM tokens. Use when the user supplies BDD .feature specs or wants a BDD suite audited before codification.",
532
+ "policies": {
533
+ "network": "none",
534
+ "shell": "none",
535
+ "filesystem": "workspace-sandbox"
536
+ }
477
537
  },
478
538
  {
479
539
  "id": "tot-exploratory-testing",
@@ -486,7 +546,12 @@
486
546
  "profiles": [
487
547
  "enterprise-rbt"
488
548
  ],
489
- "description": "Non-linear Tree/Graph-of-Thoughts exploratory testing engine exploring Happy Path, Boundary/Race, and Negative/Chaos branches with Beam Search risk scoring and multi-hypothesis RCA. Use when decomposing complex user stories into exploratory test trees or triaging complex failures."
549
+ "description": "Non-linear Tree/Graph-of-Thoughts exploratory testing engine exploring Happy Path, Boundary/Race, and Negative/Chaos branches with Beam Search risk scoring and multi-hypothesis RCA. Use when decomposing complex user stories into exploratory test trees or triaging complex failures.",
550
+ "policies": {
551
+ "network": "none",
552
+ "shell": "none",
553
+ "filesystem": "read-only"
554
+ }
490
555
  },
491
556
  {
492
557
  "id": "review-spec",
@@ -499,7 +564,12 @@
499
564
  "profiles": [
500
565
  "enterprise-rbt"
501
566
  ],
502
- "description": "Stress-test specifications, user stories, and BDD feature files with zero-context rigor. Use when reviewing requirements, user stories, or acceptance criteria before code generation."
567
+ "description": "Stress-test specifications, user stories, and BDD feature files with zero-context rigor. Use when reviewing requirements, user stories, or acceptance criteria before code generation.",
568
+ "policies": {
569
+ "network": "none",
570
+ "shell": "none",
571
+ "filesystem": "read-only"
572
+ }
503
573
  },
504
574
  {
505
575
  "id": "architecture-decision-records",
@@ -512,7 +582,12 @@
512
582
  "profiles": [
513
583
  "enterprise-rbt"
514
584
  ],
515
- "description": "Record, structure, and maintain technical Architecture Decision Records (ADRs). Use when documenting significant architecture decisions as ADRs."
585
+ "description": "Record, structure, and maintain technical Architecture Decision Records (ADRs). Use when documenting significant architecture decisions as ADRs.",
586
+ "policies": {
587
+ "network": "none",
588
+ "shell": "none",
589
+ "filesystem": "workspace-sandbox"
590
+ }
516
591
  },
517
592
  {
518
593
  "id": "api-spec-to-e2e-matrix",
@@ -525,7 +600,12 @@
525
600
  "profiles": [
526
601
  "api-security"
527
602
  ],
528
- "description": "Generate automated positive, boundary, and negative test matrices from OpenAPI specifications. Use when converting an OpenAPI/Swagger spec into an end-to-end test matrix."
603
+ "description": "Generate automated positive, boundary, and negative test matrices from OpenAPI specifications. Use when converting an OpenAPI/Swagger spec into an end-to-end test matrix.",
604
+ "policies": {
605
+ "network": "none",
606
+ "shell": "none",
607
+ "filesystem": "workspace-sandbox"
608
+ }
529
609
  },
530
610
  {
531
611
  "id": "api-network-mocking-interception",
@@ -538,7 +618,12 @@
538
618
  "profiles": [
539
619
  "api-security"
540
620
  ],
541
- "description": "Intercept HTTP/GraphQL traffic, stub routes, and simulate chaos network failures. Use when stubbing, mocking, or intercepting network calls during UI or API tests."
621
+ "description": "Intercept HTTP/GraphQL traffic, stub routes, and simulate chaos network failures. Use when stubbing, mocking, or intercepting network calls during UI or API tests.",
622
+ "policies": {
623
+ "network": "localhost-only",
624
+ "shell": "workspace-sandbox",
625
+ "filesystem": "workspace-sandbox"
626
+ }
542
627
  },
543
628
  {
544
629
  "id": "consumer-driven-contract-testing",
@@ -551,7 +636,12 @@
551
636
  "profiles": [
552
637
  "api-security"
553
638
  ],
554
- "description": "Standardize Consumer-Driven Contract (CDC) testing with Pact and OpenAPI Bidirectional Contract Testing. Detect and prevent breaking schema changes, payload drift, and microservice integration failures."
639
+ "description": "Standardize Consumer-Driven Contract (CDC) testing with Pact and OpenAPI Bidirectional Contract Testing. Detect and prevent breaking schema changes, payload drift, and microservice integration failures. Use when implementing contract testing, verifying CDC providers, or preventing breaking API schema changes.",
640
+ "policies": {
641
+ "network": "localhost-only",
642
+ "shell": "workspace-sandbox",
643
+ "filesystem": "workspace-sandbox"
644
+ }
555
645
  },
556
646
  {
557
647
  "id": "backend-load-and-stress-patterns",
@@ -564,7 +654,12 @@
564
654
  "profiles": [
565
655
  "perf-and-load"
566
656
  ],
567
- "description": "Orchestrate k6, Locust, and JMeter backend load, stress, and SLA endurance test suites. Use when designing load, stress, or spike test patterns for backend systems."
657
+ "description": "Orchestrate k6, Locust, and JMeter backend load, stress, and SLA endurance test suites. Use when designing load, stress, or spike test patterns for backend systems.",
658
+ "policies": {
659
+ "network": "sandbox-only",
660
+ "shell": "workspace-sandbox",
661
+ "filesystem": "workspace-sandbox"
662
+ }
568
663
  },
569
664
  {
570
665
  "id": "web-vitals-and-performance-profiler",
@@ -577,7 +672,12 @@
577
672
  "profiles": [
578
673
  "perf-and-load"
579
674
  ],
580
- "description": "Measure Core Web Vitals (LCP, CLS, INP) and network waterfalls via CDP. Use when the user asks why a page is slow or needs CWV budgets enforced in CI."
675
+ "description": "Measure Core Web Vitals (LCP, CLS, INP) and network waterfalls via CDP. Use when the user asks why a page is slow or needs CWV budgets enforced in CI.",
676
+ "policies": {
677
+ "network": "localhost-only",
678
+ "shell": "workspace-sandbox",
679
+ "filesystem": "workspace-sandbox"
680
+ }
581
681
  },
582
682
  {
583
683
  "id": "lean-impact-scoreboard",
@@ -590,7 +690,12 @@
590
690
  "profiles": [
591
691
  "perf-and-load"
592
692
  ],
593
- "description": "Display empirical impact scoreboards (code reduction, token savings, mutation rigor). Use when reviewing lean engineering benchmarks, token throughput, or reporting quality metrics."
693
+ "description": "Display empirical impact scoreboards (code reduction, token savings, mutation rigor). Use when reviewing lean engineering benchmarks, token throughput, or reporting quality metrics.",
694
+ "policies": {
695
+ "network": "none",
696
+ "shell": "none",
697
+ "filesystem": "read-only"
698
+ }
594
699
  },
595
700
  {
596
701
  "id": "security-dast-sentinel",
@@ -603,7 +708,12 @@
603
708
  "profiles": [
604
709
  "api-security"
605
710
  ],
606
- "description": "Run dynamic security audits: OWASP Top 10, security headers, BOLA/IDOR, and token leakage. Use when running or planning DAST and security scans against a target app."
711
+ "description": "Run dynamic security audits: OWASP Top 10, security headers, BOLA/IDOR, and token leakage. Use when running or planning DAST and security scans against a target app.",
712
+ "policies": {
713
+ "network": "sandbox-only",
714
+ "shell": "workspace-sandbox",
715
+ "filesystem": "workspace-sandbox"
716
+ }
607
717
  },
608
718
  {
609
719
  "id": "skillspector-security-guard",
@@ -616,7 +726,12 @@
616
726
  "profiles": [
617
727
  "api-security"
618
728
  ],
619
- "description": "Audit and verify AI agent skills, prompts, and MCP configurations against vulnerability vectors inspired by NVIDIA SkillSpector. Use when auditing skills and plugins for prompt-injection and security threats."
729
+ "description": "Audit and verify AI agent skills, prompts, and MCP configurations against vulnerability vectors inspired by NVIDIA SkillSpector. Use when auditing skills and plugins for prompt-injection and security threats.",
730
+ "policies": {
731
+ "network": "none",
732
+ "shell": "read-only",
733
+ "filesystem": "read-only"
734
+ }
620
735
  },
621
736
  {
622
737
  "id": "wcag-audit-patterns",
@@ -629,7 +744,12 @@
629
744
  "profiles": [
630
745
  "enterprise-rbt"
631
746
  ],
632
- "description": "Audit WCAG 2.2 accessibility (A/AA), keyboard navigation, and ARIA roles. Use when auditing accessibility against WCAG 2.2 A/AA criteria."
747
+ "description": "Audit WCAG 2.2 accessibility (A/AA), keyboard navigation, and ARIA roles. Use when auditing accessibility against WCAG 2.2 A/AA criteria.",
748
+ "policies": {
749
+ "network": "localhost-only",
750
+ "shell": "read-only",
751
+ "filesystem": "workspace-sandbox"
752
+ }
633
753
  },
634
754
  {
635
755
  "id": "self-healing-locator",
@@ -642,7 +762,12 @@
642
762
  "profiles": [
643
763
  "core-web-qa"
644
764
  ],
645
- "description": "Heal broken locators using semantic AOM diffing with Role, Label, and TestId hierarchy. Use when locators break and automated healing strategies are needed."
765
+ "description": "Heal broken locators using semantic AOM diffing with Role, Label, and TestId hierarchy. Use when locators break and automated healing strategies are needed.",
766
+ "policies": {
767
+ "network": "none",
768
+ "shell": "workspace-sandbox",
769
+ "filesystem": "workspace-sandbox"
770
+ }
646
771
  },
647
772
  {
648
773
  "id": "failure-autopsy-and-healing",
@@ -655,7 +780,12 @@
655
780
  "profiles": [
656
781
  "core-web-qa"
657
782
  ],
658
- "description": "Triage test failures from JUnit XML/screenshots and heal broken Page Class locators. Use when diagnosing failed test runs and producing closed-loop healing plans."
783
+ "description": "Triage test failures from JUnit XML/screenshots and heal broken Page Class locators. Use when diagnosing failed test runs and producing closed-loop healing plans.",
784
+ "policies": {
785
+ "network": "none",
786
+ "shell": "workspace-sandbox",
787
+ "filesystem": "workspace-sandbox"
788
+ }
659
789
  },
660
790
  {
661
791
  "id": "flaky-test-sentinel-and-quarantine",
@@ -668,7 +798,12 @@
668
798
  "profiles": [
669
799
  "core-web-qa"
670
800
  ],
671
- "description": "Detect non-deterministic flaky tests, calculate flakiness scores, and manage quarantine. Use when detecting flaky tests and managing quarantine lifecycles."
801
+ "description": "Detect non-deterministic flaky tests, calculate flakiness scores, and manage quarantine. Use when detecting flaky tests and managing quarantine lifecycles.",
802
+ "policies": {
803
+ "network": "none",
804
+ "shell": "workspace-sandbox",
805
+ "filesystem": "workspace-sandbox"
806
+ }
672
807
  },
673
808
  {
674
809
  "id": "agentless-qa-repair",
@@ -681,7 +816,12 @@
681
816
  "profiles": [
682
817
  "core-web-qa"
683
818
  ],
684
- "description": "Repair broken test scripts and Page Classes using an Agentless 3-phase flow: localization, candidate synthesis, and minimal diff validation. Use when repairing test failures without multi-agent chat bloat."
819
+ "description": "Repair broken test scripts and Page Classes using an Agentless 3-phase flow: localization, candidate synthesis, and minimal diff validation. Use when repairing test failures without multi-agent chat bloat.",
820
+ "policies": {
821
+ "network": "none",
822
+ "shell": "workspace-sandbox",
823
+ "filesystem": "workspace-sandbox"
824
+ }
685
825
  },
686
826
  {
687
827
  "id": "visual-regression-sentinel",
@@ -694,7 +834,12 @@
694
834
  "profiles": [
695
835
  "core-web-qa"
696
836
  ],
697
- "description": "Run pixel and layout shift visual regression checks with anti-flake masking. Use when comparing screenshots for visual regressions with anti-flake masking."
837
+ "description": "Run pixel and layout shift visual regression checks with anti-flake masking. Use when comparing screenshots for visual regressions with anti-flake masking.",
838
+ "policies": {
839
+ "network": "localhost-only",
840
+ "shell": "workspace-sandbox",
841
+ "filesystem": "workspace-sandbox"
842
+ }
698
843
  },
699
844
  {
700
845
  "id": "antigravity-test-sentinel",
@@ -707,7 +852,12 @@
707
852
  "profiles": [
708
853
  "core-web-qa"
709
854
  ],
710
- "description": "Enforce verification-first discipline: blocks task completion until tests and quality gates pass. Use when enforcing Definition-of-Done quality gates before completing a code or test task."
855
+ "description": "Enforce verification-first discipline: blocks task completion until tests and quality gates pass. Use when enforcing Definition-of-Done quality gates before completing a code or test task.",
856
+ "policies": {
857
+ "network": "none",
858
+ "shell": "workspace-sandbox",
859
+ "filesystem": "workspace-sandbox"
860
+ }
711
861
  },
712
862
  {
713
863
  "id": "verification-before-completion",
@@ -720,7 +870,12 @@
720
870
  "profiles": [
721
871
  "core-web-qa"
722
872
  ],
723
- "description": "Require fresh verification evidence — a command run in the current session with its real output — before any claim that work is complete, fixed, or passing. Use when about to report success, commit, open a PR, or close a task."
873
+ "description": "Require fresh verification evidence — a command run in the current session with its real output — before any claim that work is complete, fixed, or passing. Use when about to report success, commit, open a PR, or close a task.",
874
+ "policies": {
875
+ "network": "none",
876
+ "shell": "read-only",
877
+ "filesystem": "read-only"
878
+ }
724
879
  },
725
880
  {
726
881
  "id": "systematic-debugging",
@@ -733,7 +888,12 @@
733
888
  "profiles": [
734
889
  "core-web-qa"
735
890
  ],
736
- "description": "Investigate root cause through four disciplined phases before proposing any fix for a test failure, bug, or unexpected behavior. Use when a test fails, a defect appears, or a fix attempt has already failed and guessing is tempting."
891
+ "description": "Investigate root cause through four disciplined phases before proposing any fix for a test failure, bug, or unexpected behavior. Use when a test fails, a defect appears, or a fix attempt has already failed and guessing is tempting.",
892
+ "policies": {
893
+ "network": "none",
894
+ "shell": "workspace-sandbox",
895
+ "filesystem": "workspace-sandbox"
896
+ }
737
897
  },
738
898
  {
739
899
  "id": "test-driven-development",
@@ -746,7 +906,12 @@
746
906
  "profiles": [
747
907
  "core-web-qa"
748
908
  ],
749
- "description": "Enforce the RED-GREEN-REFACTOR cycle: no production or automation code is written before a failing test exists and has been watched failing. Use when implementing new helpers, Page Class logic, bug fixes, or any behavior change in test codebases."
909
+ "description": "Enforce the RED-GREEN-REFACTOR cycle: no production or automation code is written before a failing test exists and has been watched failing. Use when implementing new helpers, Page Class logic, bug fixes, or any behavior change in test codebases.",
910
+ "policies": {
911
+ "network": "none",
912
+ "shell": "workspace-sandbox",
913
+ "filesystem": "workspace-sandbox"
914
+ }
750
915
  },
751
916
  {
752
917
  "id": "db-state-verifier-and-seeder",
@@ -760,7 +925,12 @@
760
925
  "perf-and-load",
761
926
  "api-security"
762
927
  ],
763
- "description": "Seed isolated test fixtures and assert database mutations across SQL and NoSQL. Use when seeding, verifying, or cleaning database state around tests."
928
+ "description": "Seed isolated test fixtures and assert database mutations across SQL and NoSQL. Use when seeding, verifying, or cleaning database state around tests.",
929
+ "policies": {
930
+ "network": "localhost-only",
931
+ "shell": "workspace-sandbox",
932
+ "filesystem": "workspace-sandbox"
933
+ }
764
934
  },
765
935
  {
766
936
  "id": "synthetic-test-data-generator",
@@ -773,7 +943,12 @@
773
943
  "profiles": [
774
944
  "core-web-qa"
775
945
  ],
776
- "description": "Generate idempotent, boundary-value synthetic test data with unique runtime timestamps. Use when generating idempotent, unique test data for creation tests."
946
+ "description": "Generate idempotent, boundary-value synthetic test data with unique runtime timestamps. Use when generating idempotent, unique test data for creation tests.",
947
+ "policies": {
948
+ "network": "none",
949
+ "shell": "none",
950
+ "filesystem": "workspace-sandbox"
951
+ }
777
952
  },
778
953
  {
779
954
  "id": "file-and-report-validator",
@@ -787,7 +962,12 @@
787
962
  "api-security",
788
963
  "enterprise-rbt"
789
964
  ],
790
- "description": "Validate downloaded and uploaded files (Excel, CSV, PDF) schemas and tabular integrity. Use when validating exported files or reports against a schema."
965
+ "description": "Validate downloaded and uploaded files (Excel, CSV, PDF) schemas and tabular integrity. Use when validating exported files or reports against a schema.",
966
+ "policies": {
967
+ "network": "none",
968
+ "shell": "read-only",
969
+ "filesystem": "read-only"
970
+ }
791
971
  },
792
972
  {
793
973
  "id": "senior-code-review",
@@ -796,11 +976,16 @@
796
976
  "category": "architecture_and_analysis",
797
977
  "path": ".agents/skills/08-code-quality/senior-code-review/SKILL.md",
798
978
  "summary": "Review code changes across logic, security, concurrency, and test coverage. Use when conducting pull request reviews, diff inspections, or auditing commit changes before merge.",
799
- "version": "1.0.0",
979
+ "version": "1.1.0",
800
980
  "profiles": [
801
981
  "enterprise-rbt"
802
982
  ],
803
- "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."
983
+ "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.",
984
+ "policies": {
985
+ "network": "none",
986
+ "shell": "read-only",
987
+ "filesystem": "read-only"
988
+ }
804
989
  },
805
990
  {
806
991
  "id": "code-refactoring-refactor-clean",
@@ -813,7 +998,12 @@
813
998
  "profiles": [
814
999
  "core-web-qa"
815
1000
  ],
816
- "description": "Eliminate technical debt and refactor code using SOLID and Clean Code patterns. Use when refactoring legacy test code toward clean, maintainable structures."
1001
+ "description": "Eliminate technical debt and refactor code using SOLID and Clean Code patterns. Use when refactoring legacy test code toward clean, maintainable structures.",
1002
+ "policies": {
1003
+ "network": "none",
1004
+ "shell": "workspace-sandbox",
1005
+ "filesystem": "workspace-sandbox"
1006
+ }
817
1007
  },
818
1008
  {
819
1009
  "id": "lean-code-ladder",
@@ -826,7 +1016,12 @@
826
1016
  "profiles": [
827
1017
  "core-web-qa"
828
1018
  ],
829
- "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."
1019
+ "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.",
1020
+ "policies": {
1021
+ "network": "none",
1022
+ "shell": "none",
1023
+ "filesystem": "read-only"
1024
+ }
830
1025
  },
831
1026
  {
832
1027
  "id": "surgical-coding-principles",
@@ -839,7 +1034,12 @@
839
1034
  "profiles": [
840
1035
  "core-web-qa"
841
1036
  ],
842
- "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."
1037
+ "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.",
1038
+ "policies": {
1039
+ "network": "none",
1040
+ "shell": "none",
1041
+ "filesystem": "workspace-sandbox"
1042
+ }
843
1043
  },
844
1044
  {
845
1045
  "id": "technical-debt-harvester",
@@ -852,7 +1052,12 @@
852
1052
  "profiles": [
853
1053
  "enterprise-rbt"
854
1054
  ],
855
- "description": "Harvest shortcut: comments into a tracked technical debt ledger. Use when auditing code compromises, tracking deferred refactorings, or scanning for shortcut markers."
1055
+ "description": "Harvest shortcut: comments into a tracked technical debt ledger. Use when auditing code compromises, tracking deferred refactorings, or scanning for shortcut markers.",
1056
+ "policies": {
1057
+ "network": "none",
1058
+ "shell": "read-only",
1059
+ "filesystem": "read-only"
1060
+ }
856
1061
  },
857
1062
  {
858
1063
  "id": "repo-quality-audit",
@@ -865,7 +1070,12 @@
865
1070
  "profiles": [
866
1071
  "enterprise-rbt"
867
1072
  ],
868
- "description": "Comprehensive codebase quality audit covering bugs, security, bottlenecks, and bloat. Use when auditing an entire project, evaluating repository health, or prioritizing technical debt."
1073
+ "description": "Comprehensive codebase quality audit covering bugs, security, bottlenecks, and bloat. Use when auditing an entire project, evaluating repository health, or prioritizing technical debt.",
1074
+ "policies": {
1075
+ "network": "none",
1076
+ "shell": "read-only",
1077
+ "filesystem": "read-only"
1078
+ }
869
1079
  },
870
1080
  {
871
1081
  "id": "graphify-impact-analyzer",
@@ -878,7 +1088,12 @@
878
1088
  "profiles": [
879
1089
  "enterprise-rbt"
880
1090
  ],
881
- "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."
1091
+ "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.",
1092
+ "policies": {
1093
+ "network": "none",
1094
+ "shell": "workspace-sandbox",
1095
+ "filesystem": "workspace-sandbox"
1096
+ }
882
1097
  },
883
1098
  {
884
1099
  "id": "github-actions-templates",
@@ -891,7 +1106,12 @@
891
1106
  "profiles": [
892
1107
  "core-web-qa"
893
1108
  ],
894
- "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."
1109
+ "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.",
1110
+ "policies": {
1111
+ "network": "none",
1112
+ "shell": "none",
1113
+ "filesystem": "workspace-sandbox"
1114
+ }
895
1115
  },
896
1116
  {
897
1117
  "id": "actor-qa-swarm",
@@ -904,7 +1124,12 @@
904
1124
  "profiles": [
905
1125
  "perf-and-load"
906
1126
  ],
907
- "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."
1127
+ "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.",
1128
+ "policies": {
1129
+ "network": "none",
1130
+ "shell": "workspace-sandbox",
1131
+ "filesystem": "workspace-sandbox"
1132
+ }
908
1133
  },
909
1134
  {
910
1135
  "id": "agent-orchestration-multi-agent-optimize",
@@ -917,7 +1142,12 @@
917
1142
  "profiles": [
918
1143
  "perf-and-load"
919
1144
  ],
920
- "description": "Profile, benchmark, and orchestrate multi-agent test workloads and token throughput. Use when orchestrating multi-agent swarms, partitioning workloads, or optimizing agent roles."
1145
+ "description": "Profile, benchmark, and orchestrate multi-agent test workloads and token throughput. Use when orchestrating multi-agent swarms, partitioning workloads, or optimizing agent roles.",
1146
+ "policies": {
1147
+ "network": "none",
1148
+ "shell": "none",
1149
+ "filesystem": "read-only"
1150
+ }
921
1151
  },
922
1152
  {
923
1153
  "id": "event-stream-qa-orchestrator",
@@ -930,7 +1160,12 @@
930
1160
  "profiles": [
931
1161
  "perf-and-load"
932
1162
  ],
933
- "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."
1163
+ "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.",
1164
+ "policies": {
1165
+ "network": "localhost-only",
1166
+ "shell": "workspace-sandbox",
1167
+ "filesystem": "workspace-sandbox"
1168
+ }
934
1169
  },
935
1170
  {
936
1171
  "id": "qa-memory-os",
@@ -943,7 +1178,12 @@
943
1178
  "profiles": [
944
1179
  "core-web-qa"
945
1180
  ],
946
- "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."
1181
+ "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.",
1182
+ "policies": {
1183
+ "network": "none",
1184
+ "shell": "read-only",
1185
+ "filesystem": "workspace-sandbox"
1186
+ }
947
1187
  },
948
1188
  {
949
1189
  "id": "persistent-planning-files",
@@ -956,7 +1196,12 @@
956
1196
  "profiles": [
957
1197
  "enterprise-rbt"
958
1198
  ],
959
- "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."
1199
+ "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.",
1200
+ "policies": {
1201
+ "network": "none",
1202
+ "shell": "none",
1203
+ "filesystem": "workspace-sandbox"
1204
+ }
960
1205
  },
961
1206
  {
962
1207
  "id": "token-and-context-optimizer",
@@ -969,7 +1214,12 @@
969
1214
  "profiles": [
970
1215
  "core-web-qa"
971
1216
  ],
972
- "description": "Optimize prompt context, distill verbose logs, and prevent context rot in Antigravity. Use when optimizing prompts or reducing token and context overhead."
1217
+ "description": "Optimize prompt context, distill verbose logs, and prevent context rot in Antigravity. Use when optimizing prompts or reducing token and context overhead.",
1218
+ "policies": {
1219
+ "network": "none",
1220
+ "shell": "none",
1221
+ "filesystem": "read-only"
1222
+ }
973
1223
  },
974
1224
  {
975
1225
  "id": "meta-prompt-crafter",
@@ -982,7 +1232,12 @@
982
1232
  "profiles": [
983
1233
  "enterprise-rbt"
984
1234
  ],
985
- "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."
1235
+ "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.",
1236
+ "policies": {
1237
+ "network": "none",
1238
+ "shell": "none",
1239
+ "filesystem": "read-only"
1240
+ }
986
1241
  },
987
1242
  {
988
1243
  "id": "mipro-prompt-compiler",
@@ -995,7 +1250,12 @@
995
1250
  "profiles": [
996
1251
  "perf-and-load"
997
1252
  ],
998
- "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."
1253
+ "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.",
1254
+ "policies": {
1255
+ "network": "none",
1256
+ "shell": "workspace-sandbox",
1257
+ "filesystem": "workspace-sandbox"
1258
+ }
999
1259
  },
1000
1260
  {
1001
1261
  "id": "qa-aci-interface",
@@ -1008,7 +1268,12 @@
1008
1268
  "profiles": [
1009
1269
  "core-web-qa"
1010
1270
  ],
1011
- "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."
1271
+ "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.",
1272
+ "policies": {
1273
+ "network": "none",
1274
+ "shell": "read-only",
1275
+ "filesystem": "read-only"
1276
+ }
1012
1277
  }
1013
1278
  ]
1014
1279
  }