docs: update PROJECT-KNOWLEDGE, README, and user docs for specs 037/038/039

PROJECT-KNOWLEDGE.md:
- Add specs 037 (ISTQB techniques), 038 (Testimize integration), 039
  (unified critic provider list) to the Completed Feature Specs table
- Add testimize section to the spectra.config.json schema example
- Update Test Counts to 1551 (491 Core + 709 CLI + 351 MCP)

README.md:
- AI Test Generation feature blurb mentions ISTQB techniques and the
  category + technique breakdown
- Ecosystem section gains a callout for the optional Testimize MCP
  integration with install instructions
- Documentation index gains a Testimize Integration link

docs/cli-reference.md:
- spectra ai generate description mentions systematic ISTQB techniques
- New "Testimize Commands (Optional)" section documenting
  spectra testimize check (human + JSON output, install hint, no MCP
  process when disabled)

docs/coverage.md:
- Note about boundary coverage gains from spec 037 ISTQB techniques
- Note about optional spec 038 Testimize precision

docs/generation-profiles.md:
- Three-layer customization clarification table: profile (style),
  prompt template (reasoning, ISTQB), Testimize (test data values)

docs/skills-integration.md:
- Document the technique_breakdown field in analysis JSON output
- Document the spectra testimize check JSON shape

Author: angelovstanton

PROJECT-KNOWLEDGE.md

@@ -291,10 +291,23 @@ Three-section unified coverage with distinct semantics:
     "criteria_file": "docs/criteria/_criteria_index.yaml",
     "criteria_dir": "docs/criteria",
     "automation_dirs": ["tests"]
+  },
+  "testimize": {
+    "enabled": false,
+    "mode": "exploratory",
+    "strategy": "HybridArtificialBeeColony",
+    "mcp": { "command": "testimize-mcp", "args": ["--mcp"] }
   }
 }
 ```
 
+> **Spec 039**: critic providers now use the same five names as the generator
+> (`github-models`, `azure-openai`, `azure-anthropic`, `openai`, `anthropic`).
+> Legacy `github` is a soft alias; legacy `google` is rejected.
+>
+> **Spec 038**: optional `testimize` section enables external Testimize MCP
+> integration for algorithmic test data optimization (off by default).
+
 ## Code Conventions
 
 - **C# 12, .NET 8+**
@@ -310,6 +323,9 @@ Three-section unified coverage with distinct semantics:
 
 | # | Feature | Key Changes |
 |---|---------|-------------|
+| 039 | Unified Critic Provider List | Critic provider validation now matches the generator provider list (`github-models`, `azure-openai`, `azure-anthropic`, `openai`, `anthropic`). Legacy `github` is a soft alias with deprecation warning; legacy `google` is hard-rejected. New `ResolveProvider` helper in `CriticFactory`. Enables Azure-only billing setups. |
+| 038 | Testimize Integration | Optional MCP integration with the external `Testimize.MCP.Server` global tool for algorithmic test data optimization (BVA, EP, pairwise, ABC). New `testimize` config section (disabled by default), `TestimizeMcpClient` (process lifecycle, JSON-RPC, 30s/5s timeouts, idempotent disposal), two new conditionally-registered AI tools (`GenerateTestData`, `AnalyzeFieldSpec`), `{{#if testimize_enabled}}` blocks in behavior-analysis and test-generation templates, new `spectra testimize check` CLI command, full graceful degradation. No NuGet dependency. |
+| 037 | ISTQB Test Design Techniques | All five built-in prompt templates rewritten to teach the AI six ISTQB techniques (EP, BVA, DT, ST, EG, UC). New `IdentifiedBehavior.Technique` field, `BehaviorAnalysisResult.TechniqueBreakdown` map, `AcceptanceCriterion.TechniqueHint` field. Analysis output includes `technique_breakdown` alongside `breakdown`. Terminal and progress page render a Technique Breakdown section in fixed display order. Distribution guideline caps any single category at 40%. Existing user-edited templates preserved; opt in via `spectra prompts reset --all`. |
 | 033 | From-Description Chat Flow | Dedicated `--from-description` SKILL section, agent intent routing (focus vs from-description vs from-suggestions), doc-aware manual tests with populated `source_refs` and `criteria` (verdict stays manual) |
 | 029 | spectra-update SKILL (10th) | Agent delegation, documentation sync, version 1.35.0 |
 | 028 | Coverage & Criteria Pipeline | Fixed criteria propagation in parser, wired criteria into generation pipeline, always write criteria: [] |
@@ -332,11 +348,12 @@ Three-section unified coverage with distinct semantics:
 | 008 | Grounding Verification | Dual-model critic, grounded/partial/hallucinated verdicts |
 | 006 | Conversational Generation | Direct/interactive modes, test updates, classification |
 
-## Test Counts (as of 2026-04-08)
+## Test Counts (as of 2026-04-11)
 
 | Project | Tests |
 |---------|-------|
-| Spectra.Core.Tests | 462 |
-| Spectra.CLI.Tests | 466 |
+| Spectra.Core.Tests | 491 |
+| Spectra.CLI.Tests | 709 |
 | Spectra.MCP.Tests | 351 |
+| **Total** | **1551** |
 | **Total** | **1279** |

README.md

@@ -61,6 +61,8 @@ SPECTRA reads your product documentation, generates comprehensive test suites, a
 Generate test cases from product documentation through an iterative session.
 The AI analyzes your docs, identifies testable behaviors, generates structured test cases, suggests additional tests for uncovered areas, and lets you describe undocumented behaviors — all in one continuous flow.
 
+Behavior analysis applies six **ISTQB test design techniques** systematically (Equivalence Partitioning, Boundary Value Analysis, Decision Table, State Transition, Error Guessing, Use Case) so the produced suites have meaningful boundary and negative coverage instead of happy-path-only scenarios. Analysis output exposes both a category breakdown and a per-technique breakdown.
+
 ```bash
 spectra ai generate                    # Interactive session
 spectra ai generate checkout           # Direct mode
@@ -195,6 +197,14 @@ SPECTRA is part of the [Automate The Planet](https://www.automatetheplanet.com/)
 
 **BELLATRIX** automates test execution. **Testimize** optimizes test case selection. **SPECTRA** generates and maintains the test cases themselves — closing the loop between documentation and quality assurance.
 
+> **Optional Testimize integration**: SPECTRA can call the
+> [Testimize.MCP.Server](https://github.com/AutomateThePlanet/Testimize) global
+> tool to replace AI-approximated boundary values with mathematically optimal
+> ones (BVA / EP / pairwise / ABC). Disabled by default; enable with
+> `dotnet tool install --global Testimize.MCP.Server` and set
+> `testimize.enabled` to `true` in `spectra.config.json`. See
+> [Testimize Integration](docs/testimize-integration.md).
+
 ## Documentation
 
 | Guide | Description |
@@ -210,6 +220,7 @@ SPECTRA is part of the [Automate The Planet](https://www.automatetheplanet.com/)
 | [Skills Integration](docs/skills-integration.md) | Copilot Chat SKILLs and agent prompts |
 | [Usage (Copilot Chat)](docs/usage.md) | Workflow-by-workflow guide for driving SPECTRA via Copilot Chat |
 | [Customization](docs/customization.md) | Every customization knob — config, profiles, prompts, palettes |
+| [Testimize Integration](docs/testimize-integration.md) | Optional algorithmic test data optimization (BVA / EP / pairwise / ABC) |
 | [Execution Agent](docs/execution-agent/overview.md) | MCP tools and AI-driven test execution |
 | [Architecture](docs/architecture/overview.md) | System design and key decisions |
 | [Development Guide](docs/DEVELOPMENT.md) | Building, testing, and running locally |

docs/cli-reference.md

@@ -129,7 +129,12 @@ See [Document Index](document-index.md) for full details.
 
 ### `spectra ai generate`
 
-Generate test cases from documentation. Supports multiple modes.
+Generate test cases from documentation using systematic ISTQB test design
+techniques (Equivalence Partitioning, Boundary Value Analysis, Decision
+Table, State Transition, Error Guessing, Use Case). The analysis output
+includes both a category breakdown (`happy_path`, `boundary`, `negative`, …)
+and a technique breakdown (`BVA`, `EP`, `DT`, `ST`, `EG`, `UC`) — see spec
+037. Supports multiple modes.
 
 **Interactive Session** — four-phase guided session:
 
@@ -283,6 +288,30 @@ See [Generation Profiles](generation-profiles.md) for details.
 
 ---
 
+## Testimize Commands (Optional)
+
+### `spectra testimize check`
+
+Reports the status of the optional Testimize integration (spec 038): whether
+it is enabled in config, whether the `Testimize.MCP.Server` global tool is
+installed, whether the server passes a health probe, the configured mode and
+strategy, and whether the optional `testimizeSettings.json` is present.
+
+```bash
+spectra testimize check
+spectra testimize check --output-format json
+```
+
+When Testimize is disabled (the default), the command does NOT start the MCP
+process — it just reports `enabled: false`. When enabled but not installed,
+the output includes a one-line `dotnet tool install --global Testimize.MCP.Server`
+instruction. JSON output always contains the fields `enabled`, `installed`,
+`healthy`, plus `mode`, `strategy`, and (when not installed) `install_command`.
+
+See [Testimize Integration](testimize-integration.md) for the full guide.
+
+---
+
 ## Execution Commands
 
 ### `spectra-mcp` (separate tool)

docs/coverage.md

@@ -22,6 +22,18 @@ SPECTRA produces a unified coverage report with three sections:
 | **Acceptance Criteria** | Which criteria are covered | `criteria` field in test frontmatter + `_criteria_index.yaml` |
 | **Automation** | Which tests have automation code | `automated_by` field in test frontmatter + code scanning |
 
+> **Spec 037 — boundary coverage from ISTQB techniques**: Test generation now
+> applies six ISTQB test design techniques systematically (EP, BVA, DT, ST, EG,
+> UC). Suites generated after spec 037 typically have 50%+ more tests in the
+> `boundary` and `negative` categories than pre-037 suites on the same docs.
+> The analysis output exposes this via a `technique_breakdown` map alongside
+> the existing category `breakdown`.
+>
+> **Spec 038 — algorithmic precision (optional)**: When the optional
+> [Testimize integration](testimize-integration.md) is enabled, the AI replaces
+> approximated boundary values with mathematically optimal ones from
+> Testimize's BVA / EP / pairwise / ABC algorithms. Disabled by default.
+
 ## Run Coverage Analysis
 
 ```bash

docs/generation-profiles.md

@@ -14,7 +14,18 @@ Related: [CLI Reference](cli-reference.md) | [Test Format](test-format.md) | [Co
 
 ## Overview
 
-Profiles control test generation style: detail level, negative scenario count, step formatting, domain-specific considerations, and more. They're optional but recommended for consistent output.
+Profiles control test generation **style**: detail level, negative scenario count, step formatting, domain-specific considerations, and more. They're optional but recommended for consistent output.
+
+> **Profiles vs prompt templates vs Testimize** — three orthogonal customization layers:
+>
+> | Layer | What it controls | Where it lives | Default |
+> |-------|-----------------|---------------|---------|
+> | **Profile** | Output format and style (step granularity, priority defaults, domain hints) | `profiles/_default.yaml` | Built-in default |
+> | **Prompt template** | Reasoning strategy (which ISTQB techniques to apply, which categories to use, how to structure analysis) — see [spec 037](../specs/037-istqb-test-techniques/spec.md) | `.spectra/prompts/*.md` | ISTQB-enhanced built-ins |
+> | **Testimize** (optional) | Test data values (boundary numbers, equivalence class examples, pairwise combinations) — see [spec 038](testimize-integration.md) | `testimize` section in `spectra.config.json` | Disabled |
+>
+> A typical setup uses the default profile, the default ISTQB prompts, and
+> leaves Testimize disabled. Power users mix and match independently.
 
 ## Create a Profile
 

docs/skills-integration.md

@@ -67,6 +67,34 @@ spectra <command> --output-format json --verbosity quiet
 - `--output-format json`: Structured JSON on stdout (no colors, spinners, or ANSI codes)
 - `--verbosity quiet`: Only the final result (no progress indicators)
 
+#### Analysis JSON includes a `technique_breakdown` (spec 037)
+
+The `analysis` subobject in `.spectra-result.json` from `spectra ai generate
+--analyze-only` exposes both the existing category `breakdown` and a new
+`technique_breakdown` map. Keys are short ISTQB codes (`BVA`, `EP`, `DT`,
+`ST`, `EG`, `UC`); values are counts. Always present (`{}` when empty)
+so SKILL parsers can rely on the field existing.
+
+```json
+{
+  "analysis": {
+    "total_behaviors": 141,
+    "breakdown": { "happy_path": 42, "boundary": 38, "negative": 24, "edge_case": 18 },
+    "technique_breakdown": { "BVA": 38, "EP": 24, "UC": 32, "EG": 15, "DT": 18, "ST": 14 }
+  }
+}
+```
+
+The `spectra-generate` SKILL renders both breakdowns to the user when
+presenting the analyze recommendation.
+
+#### `spectra testimize check` JSON (spec 038)
+
+When the optional Testimize integration is in use, `spectra testimize check
+--output-format json` returns a `TestimizeCheckResult` object with the
+required fields `enabled`, `installed`, `healthy` plus `mode`, `strategy`,
+and (when not installed) `install_command`. See [Testimize Integration](testimize-integration.md).
+
 ### Generation Session in SKILLs
 
 The generate SKILL supports the full session flow: