agentic-qe 3.8.2 → 3.8.3

package/.claude/skills/trust-tier-manifest.json

@@ -5,17 +5,17 @@
   "generator": "scripts/update-skill-manifest.ts",
   "trustTierPolicy": "ADR-056",
   "summary": {
-    "tier0": 41,
+    "tier0": 51,
     "tier1": 5,
     "tier2": 7,
-    "tier3": 51,
-    "total": 104
+    "tier3": 49,
+    "total": 112
   },
   "validationStatus": {
-    "passing": 51,
+    "passing": 49,
     "failing": 0,
     "unknown": 12,
-    "skipped": 41
+    "skipped": 51
   },
   "skillsByTier": {
     "tier3": [
@@ -314,16 +314,6 @@
         },
         "file": "qe-code-intelligence/SKILL.md"
       },
-      {
-        "name": "qe-contract-testing",
-        "validation": {
-          "status": "passing",
-          "schemaPath": "schemas/output.json",
-          "validatorPath": "scripts/validate-config.json",
-          "evalPath": "evals/qe-contract-testing.yaml"
-        },
-        "file": "qe-contract-testing/SKILL.md"
-      },
       {
         "name": "qe-coverage-analysis",
         "validation": {
@@ -374,16 +364,6 @@
         },
         "file": "qe-requirements-validation/SKILL.md"
       },
-      {
-        "name": "qe-security-compliance",
-        "validation": {
-          "status": "passing",
-          "schemaPath": "schemas/output.json",
-          "validatorPath": "scripts/validate-config.json",
-          "evalPath": "evals/qe-security-compliance.yaml"
-        },
-        "file": "qe-security-compliance/SKILL.md"
-      },
       {
         "name": "qe-test-execution",
         "validation": {
@@ -650,14 +630,6 @@
         },
         "file": "agentic-quality-engineering/SKILL.md"
       },
-      {
-        "name": "aqe-v2-v3-migration",
-        "validation": {
-          "status": "unknown",
-          "schemaPath": "schemas/output.json"
-        },
-        "file": "aqe-v2-v3-migration/SKILL.md"
-      },
       {
         "name": "consultancy-practices",
         "category": "professional-practice",
@@ -716,6 +688,16 @@
         "category": "testing-methodologies",
         "file": "context-driven-testing/SKILL.md"
       },
+      {
+        "name": "coverage-drop-investigator",
+        "category": "investigation",
+        "file": "coverage-drop-investigator/SKILL.md"
+      },
+      {
+        "name": "coverage-guard",
+        "category": "on-demand-hooks",
+        "file": "coverage-guard/SKILL.md"
+      },
       {
         "name": "debug-loop",
         "category": "debugging",
@@ -724,6 +706,11 @@
         },
         "file": "debug-loop/SKILL.md"
       },
+      {
+        "name": "e2e-flow-verifier",
+        "category": "product-verification",
+        "file": "e2e-flow-verifier/SKILL.md"
+      },
       {
         "name": "exploratory-testing-advanced",
         "category": "testing-methodologies",
@@ -744,6 +731,11 @@
         "category": "orchestration",
         "file": "flow-nexus-swarm/SKILL.md"
       },
+      {
+        "name": "freeze-tests",
+        "category": "on-demand-hooks",
+        "file": "freeze-tests/SKILL.md"
+      },
       {
         "name": "github-code-review",
         "category": "github",
@@ -787,6 +779,11 @@
         "name": "iterative-loop",
         "file": "iterative-loop/SKILL.md"
       },
+      {
+        "name": "no-skip",
+        "category": "on-demand-hooks",
+        "file": "no-skip/SKILL.md"
+      },
       {
         "name": "pair-programming",
         "file": "pair-programming/SKILL.md"
@@ -807,6 +804,11 @@
         "name": "reasoningbank-intelligence",
         "file": "reasoningbank-intelligence/SKILL.md"
       },
+      {
+        "name": "security-watch",
+        "category": "on-demand-hooks",
+        "file": "security-watch/SKILL.md"
+      },
       {
         "name": "six-thinking-hats",
         "category": "methodology",
@@ -816,11 +818,21 @@
         "name": "skill-builder",
         "file": "skill-builder/SKILL.md"
       },
+      {
+        "name": "skill-stats",
+        "category": "measurement",
+        "file": "skill-stats/SKILL.md"
+      },
       {
         "name": "sparc-methodology",
         "category": "development",
         "file": "sparc-methodology/SKILL.md"
       },
+      {
+        "name": "strict-tdd",
+        "category": "on-demand-hooks",
+        "file": "strict-tdd/SKILL.md"
+      },
       {
         "name": "stream-chain",
         "category": "workflow",
@@ -835,6 +847,16 @@
         "name": "swarm-orchestration",
         "file": "swarm-orchestration/SKILL.md"
       },
+      {
+        "name": "test-failure-investigator",
+        "category": "investigation",
+        "file": "test-failure-investigator/SKILL.md"
+      },
+      {
+        "name": "test-metrics-dashboard",
+        "category": "analytics",
+        "file": "test-metrics-dashboard/SKILL.md"
+      },
       {
         "name": "v3-cli-modernization",
         "file": "v3-cli-modernization/SKILL.md"
@@ -1361,16 +1383,6 @@
       },
       "file": "qe-code-intelligence/SKILL.md"
     },
-    "qe-contract-testing": {
-      "trustTier": 3,
-      "validation": {
-        "status": "passing",
-        "schemaPath": "schemas/output.json",
-        "validatorPath": "scripts/validate-config.json",
-        "evalPath": "evals/qe-contract-testing.yaml"
-      },
-      "file": "qe-contract-testing/SKILL.md"
-    },
     "qe-coverage-analysis": {
       "trustTier": 3,
       "validation": {
@@ -1421,16 +1433,6 @@
       },
       "file": "qe-requirements-validation/SKILL.md"
     },
-    "qe-security-compliance": {
-      "trustTier": 3,
-      "validation": {
-        "status": "passing",
-        "schemaPath": "schemas/output.json",
-        "validatorPath": "scripts/validate-config.json",
-        "evalPath": "evals/qe-security-compliance.yaml"
-      },
-      "file": "qe-security-compliance/SKILL.md"
-    },
     "qe-test-execution": {
       "trustTier": 3,
       "validation": {
@@ -1923,14 +1925,6 @@
       ],
       "lastUpdated": "2025-12-02"
     },
-    "aqe-v2-v3-migration": {
-      "trustTier": 1,
-      "validation": {
-        "status": "unknown",
-        "schemaPath": "schemas/output.json"
-      },
-      "file": "aqe-v2-v3-migration/SKILL.md"
-    },
     "consultancy-practices": {
       "trustTier": 1,
       "category": "professional-practice",
@@ -2050,6 +2044,30 @@
       ],
       "lastUpdated": "2025-12-02"
     },
+    "coverage-drop-investigator": {
+      "trustTier": 0,
+      "category": "investigation",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "coverage-drop-investigator/SKILL.md"
+    },
+    "coverage-guard": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "coverage-guard/SKILL.md"
+    },
+    "e2e-flow-verifier": {
+      "trustTier": 0,
+      "category": "product-verification",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "e2e-flow-verifier/SKILL.md"
+    },
     "exploratory-testing-advanced": {
       "trustTier": 0,
       "category": "testing-methodologies",
@@ -2109,6 +2127,14 @@
         "message-queue"
       ]
     },
+    "freeze-tests": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "freeze-tests/SKILL.md"
+    },
     "github-code-review": {
       "trustTier": 0,
       "category": "github",
@@ -2225,6 +2251,14 @@
       },
       "file": "iterative-loop/SKILL.md"
     },
+    "no-skip": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "no-skip/SKILL.md"
+    },
     "pair-programming": {
       "trustTier": 0,
       "validation": {
@@ -2246,6 +2280,14 @@
       },
       "file": "reasoningbank-intelligence/SKILL.md"
     },
+    "security-watch": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "security-watch/SKILL.md"
+    },
     "six-thinking-hats": {
       "trustTier": 0,
       "category": "methodology",
@@ -2271,6 +2313,14 @@
       },
       "file": "skill-builder/SKILL.md"
     },
+    "skill-stats": {
+      "trustTier": 0,
+      "category": "measurement",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "skill-stats/SKILL.md"
+    },
     "sparc-methodology": {
       "trustTier": 0,
       "category": "development",
@@ -2279,6 +2329,14 @@
       },
       "file": "sparc-methodology/SKILL.md"
     },
+    "strict-tdd": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "strict-tdd/SKILL.md"
+    },
     "stream-chain": {
       "trustTier": 0,
       "category": "workflow",
@@ -2318,6 +2376,22 @@
       },
       "file": "swarm-orchestration/SKILL.md"
     },
+    "test-failure-investigator": {
+      "trustTier": 0,
+      "category": "investigation",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "test-failure-investigator/SKILL.md"
+    },
+    "test-metrics-dashboard": {
+      "trustTier": 0,
+      "category": "analytics",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "test-metrics-dashboard/SKILL.md"
+    },
     "v3-cli-modernization": {
       "trustTier": 0,
       "validation": {

package/.claude/skills/validation-pipeline/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: "Validation Pipeline"
-description: "Structured step-by-step validation of requirements, code, and artifacts with gate enforcement, per-step scoring, and structured reports."
+description: "Use when validating requirements, code, or artifacts through structured gate enforcement with per-step scoring and pass/fail reports."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json

package/.claude/skills/verification-quality/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: "Verification & Quality Assurance"
-description: "Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability."
+description: "Use when verifying agent outputs are correct, validating code changes before merge, or setting up automatic rollback for failed quality checks."
 version: "2.0.0"
 category: "quality-assurance"
 tags: ["verification", "truth-scoring", "quality", "rollback", "metrics", "ci-cd"]
@@ -641,6 +641,20 @@ Verification commands return standard exit codes:
 7. **Review Rollbacks**: Understand why changes were rejected
 8. **Train Agents**: Use verification feedback to improve agent performance
 
+## Skill Composition
+
+- **Before verification** → Run `/qe-test-generation` and `/qe-coverage-analysis` first
+- **If verification fails** → Use `/test-failure-investigator` for root cause analysis
+- **Ship decision** → Feed into `/qe-quality-assessment` for final assessment
+
+## Gotchas
+
+- Verification is the HIGHEST-VALUE skill category (Anthropic: "worth having an engineer spend a week making verification skills excellent")
+- "Success is silent, only failures are verbose" — swallow passing test output, surface only errors to avoid context window flooding
+- Agent completion claims are unreliable — always include programmatic assertions on state, not just "looks right"
+- Have Claude record a video of its output so you can see exactly what it tested (Playwright trace, screenshot evidence)
+- Hardcoded values are the #1 completion theater pattern — grep for literals that should be dynamic
+
 ### Additional Resources
 
 - Truth Scoring Algorithm: See `/docs/truth-scoring.md`

package/.claude/skills/xp-practices/SKILL.md

@@ -50,31 +50,6 @@ A: Make test pass + refactor
 
 ## Quick Reference Card
 
-### The Five XP Values
-
-| Value | Meaning | Practice |
-|-------|---------|----------|
-| **Communication** | Everyone knows what everyone does | Daily standups, pairing |
-| **Simplicity** | Simplest thing that works | YAGNI, small design |
-| **Feedback** | Get feedback early and often | TDD, CI, short iterations |
-| **Courage** | Tell truth, adapt | Refactor, admit mistakes |
-| **Respect** | Everyone contributes value | Sustainable pace, pairing |
-
-### Core Practices
-
-| Practice | Description | Benefit |
-|----------|-------------|---------|
-| **Pair Programming** | Two devs, one workstation | Quality + knowledge sharing |
-| **TDD** | Red-Green-Refactor | Confidence + design |
-| **CI** | Integrate multiple times/day | Fast feedback |
-| **Collective Ownership** | Anyone can change anything | No bottlenecks |
-| **Sustainable Pace** | 40-hour weeks | Long-term productivity |
-| **Small Releases** | Ship frequently | Risk reduction |
-
----
-
-## Pair Programming
-
 ### When to Pair
 
 | Context | Pair? | Why |
@@ -86,73 +61,6 @@ A: Make test pass + refactor
 | Simple tasks | ❌ Skip | Not worth overhead |
 | Research spikes | ❌ Skip | Pair to discuss findings |
 
-### Pairing Dos and Don'ts
-
-**Do:**
-- ✅ Switch roles every 20-30 min
-- ✅ Take breaks together
-- ✅ Think out loud
-- ✅ Ask questions
-- ✅ Keep sessions 2-4 hours max
-
-**Don't:**
-- ❌ Grab keyboard without asking
-- ❌ Check phone while pairing
-- ❌ Dominate conversation
-- ❌ Pair all day (exhausting)
-
----
-
-## Ensemble (Mob) Programming
-
-**Setup:** 3+ developers, one screen, rotating driver
-
-```
-[Screen]
-   ↓
-[Driver] ← Directions from navigators
-   ↑
-[Navigator 1] [Navigator 2] [Navigator 3]
-```
-
-**Rotation:** Driver switches every 5-10 min
-
-**Best for:**
-- Complex problem solving
-- Architectural decisions
-- Learning new frameworks
-- Resolving blockers
-
----
-
-## Continuous Integration
-
-**CI Workflow:**
-```
-1. Pull latest from main
-2. Make small change (<2 hrs work)
-3. Run tests locally (all pass)
-4. Commit and push
-5. CI runs tests automatically
-6. If fail → fix immediately
-```
-
-**Best Practices:**
-- Commit frequently (small changes)
-- Keep build fast (<10 min)
-- Fix broken builds immediately
-- Never commit to broken build
-
----
-
-## Four Rules of Simple Design
-
-(In priority order)
-1. **Passes all tests** - Works correctly
-2. **Reveals intention** - Clear, expressive code
-3. **No duplication** - DRY principle
-4. **Fewest elements** - No speculative code
-
 ---
 
 ## Agent Integration
@@ -202,17 +110,6 @@ const xpFleet = await FleetManager.coordinate({
 
 ---
 
-## Common Objections
-
-| Objection | Response |
-|-----------|----------|
-| "Pairing is 2x slower" | 15% slower writing, 15% fewer bugs, net positive |
-| "No time for TDD" | Debugging takes longer than testing |
-| "CI is hard to setup" | Start simple: one action, one test |
-| "Collective ownership = chaos" | Only without tests + CI |
-
----
-
 ## Related Skills
 - [tdd-london-chicago](../tdd-london-chicago/) - TDD deep dive
 - [refactoring-patterns](../refactoring-patterns/) - Safe refactoring
@@ -222,10 +119,6 @@ const xpFleet = await FleetManager.coordinate({
 
 ## Remember
 
-**XP practices work as a system.** Don't cherry-pick randomly:
-- TDD enables collective ownership
-- CI enables small releases
-- Pairing enables collective ownership
-- Sustainable pace enables everything
+**XP practices work as a system** - TDD enables collective ownership, CI enables small releases, pairing enables collective ownership. Don't cherry-pick randomly.
 
-**With Agents:** Agents amplify XP. Pair humans with agents. Agents handle repetitive work, humans provide judgment and creativity.
+**With Agents:** Pair humans with agents. Agents handle repetitive work (regression, data generation, coverage analysis), humans provide judgment and creativity.

package/CHANGELOG.md

@@ -5,6 +5,35 @@ All notable changes to the Agentic QE project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.8.3] - 2026-03-18
+
+### Fixed
+
+- **Portable hook commands** — `aqe init` no longer embeds the host machine's absolute path into `.claude/settings.json` hook commands. Commands now use simple relative paths (`node .claude/helpers/brain-checkpoint.cjs`), making settings fully portable across machines. ([#369](https://github.com/proffesor-for-testing/agentic-qe/issues/369))
+- **SONA persistence initialization** — Fixed circular `ensureInitialized()` call during `PersistentSONAEngine._doInitialize()` that caused all 31 sona-persistence tests to fail when `useSONAThreeLoop` flag was enabled by default.
+- **RuVector feature flag test compatibility** — Updated compressed-hnsw and temporal-compression tests to explicitly set flag state instead of assuming defaults, fixing 9 test failures introduced when v3.8.0 enabled all flags by default.
+- **CI timeout and contract test path** — Resolved CI workflow timeouts and broken contract test path. ([#350](https://github.com/proffesor-for-testing/agentic-qe/issues/350))
+- **OpenCode config schema** — `aqe init --with-opencode` now generates valid `opencode.json` matching OpenCode's `McpLocal.strict()` zod schema (`command` as string array, `environment` instead of `env`, no extra `args` field). ([#370](https://github.com/proffesor-for-testing/agentic-qe/issues/370))
+- **Infra-healing fallback playbook** — Fixed field name mismatches (`check` → `healthCheck`, added `verify`) in the hardcoded fallback playbook that caused a TypeError on every MCP startup. ([#371](https://github.com/proffesor-for-testing/agentic-qe/issues/371))
+- **Fleet init crash** — `LearningOptimizationCoordinator` now gracefully degrades when SONA init fails, matching the other 6 coordinators. Combined with the circular init fix, fleet initialization succeeds on MCP startup. ([#372](https://github.com/proffesor-for-testing/agentic-qe/issues/372))
+
+### Added
+
+- **ADR-086 skill design standards** — Major overhaul of all 84 QE skills based on Anthropic's "Lessons from Building Claude Code" skill design guidance. Skills are now folder-based systems with progressive disclosure, gotchas, composition, config, and run history.
+- **5 new skills** — `test-failure-investigator`, `coverage-drop-investigator`, `e2e-flow-verifier`, `test-metrics-dashboard`, and `skill-stats` fill previously missing categories.
+- **5 on-demand hook skills** — `strict-tdd`, `no-skip`, `coverage-guard`, `freeze-tests`, and `security-watch` with executable scripts that activate via slash commands.
+- **Gotchas sections** — 30 skills now include battle-tested failure data from production learning records.
+- **Reference and template files** — 10 reference/template files across 7 skills (OWASP top 10, k6 configs, mutation operators, security report templates, etc.).
+- **Skill composition** — Cross-references added to 10 key skills showing how to chain skills together for complex workflows.
+- **Config and run-history** — `config.json` with `_setupPrompt` added to 7 skills; `run-history.json` with write instructions added to 5 metric-producing skills.
+
+### Changed
+
+- **Skill descriptions rewritten** — All 84 skill descriptions now use "Use when..." trigger conditions for better auto-detection.
+- **Textbook knowledge stripped** — 892 lines of generic content removed from 15 skills (26% size reduction) to focus on actionable guidance.
+- **3 redundant skills removed** — `qe-contract-testing` (→ `contract-testing`), `qe-security-compliance` (→ `security-testing`), `aqe-v2-v3-migration` (obsolete). `aqe init --upgrade` auto-cleans these.
+- **Removed tracked generated file** — `aqe.rvf.manifest.json` is now gitignored as it changes every session.
+
 ## [3.8.2] - 2026-03-17
 
 ### Fixed

package/README.md

@@ -177,12 +177,16 @@ Agents automatically apply relevant skills from the skill library. Skills are ra
 
 **Specialized Testing (13):** accessibility-testing, mobile-testing, database-testing, contract-testing, chaos-engineering-resilience, visual-testing-advanced, security-visual-testing, compliance-testing, compatibility-testing, localization-testing, mutation-testing, performance-testing, security-testing
 
-**Domain Skills (14):** qe-test-generation, qe-test-execution, qe-coverage-analysis, qe-quality-assessment, qe-defect-intelligence, qe-requirements-validation, qe-code-intelligence, qe-security-compliance, qe-contract-testing, qe-visual-accessibility, qe-chaos-resilience, qe-learning-optimization, qe-iterative-loop, aqe-v2-v3-migration
+**Domain Skills (11):** qe-test-generation, qe-test-execution, qe-coverage-analysis, qe-quality-assessment, qe-defect-intelligence, qe-requirements-validation, qe-code-intelligence, qe-visual-accessibility, qe-chaos-resilience, qe-learning-optimization, qe-iterative-loop
 
 **Strategic (8):** six-thinking-hats, brutal-honesty-review, sherlock-review, cicd-pipeline-qe-orchestrator, bug-reporting-excellence, consultancy-practices, quality-metrics, pair-programming
 
 **Testing Techniques (9):** exploratory-testing-advanced, test-design-techniques, test-data-management, test-environment-management, test-reporting-analytics, testability-scoring, technical-writing, code-review-quality, api-testing-patterns
 
+**On-Demand Hooks (5):** strict-tdd, no-skip, coverage-guard, freeze-tests, security-watch
+
+**Runbooks & Analysis (5):** test-failure-investigator, coverage-drop-investigator, e2e-flow-verifier, test-metrics-dashboard, skill-stats
+
 **n8n Workflow Testing (5):** n8n-workflow-testing-fundamentals, n8n-expression-testing, n8n-security-testing, n8n-trigger-testing-strategies, n8n-integration-testing-patterns
 
 **QCSD Swarms (5):** qcsd-ideation-swarm, qcsd-refinement-swarm, qcsd-development-swarm, qcsd-cicd-swarm, qcsd-production-swarm