feat: enhance spec loading capabilities and add new categories

- Added support for loading specs from new categories: debug, test, review, and validation.
- Updated various agents and skills to include instructions for loading project context from the new spec categories.
- Introduced new spec documents for test conventions, review standards, and validation rules to improve project guidelines.
- Enhanced the frontend to support new watcher settings and display auto-watch status.
- Improved the spec index builder to accommodate new categories and ensure proper loading of specifications.

.claude/agents/cli-planning-agent.md

@@ -31,6 +31,9 @@ If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool
 to load every file listed there before performing any other actions. This is your
 primary context.
 
+**Load Project Context** (from spec system):
+- Run: `ccw spec load --category test` for test framework context, coverage targets, and conventions
+
 **Core responsibilities:**
 - **FIRST: Execute CLI analysis** with appropriate templates and context
 - Parse structured results (fix strategies, root causes, modification points)

.claude/agents/debug-explore-agent.md

@@ -36,6 +36,7 @@ Phase 5: Fix & Verification
 ## Phase 1: Bug Analysis
 
 **Load Project Context** (from spec system):
+- Load debug specs using: `ccw spec load --category debug` for known issues, workarounds, and root-cause notes
 - Load exploration specs using: `ccw spec load --category exploration` for tech stack context and coding constraints
 
 **Session Setup**:

.claude/agents/tdd-developer.md

@@ -383,6 +383,7 @@ Bash(
 ### Context Loading (Inherited from code-developer)
 
 **Standard Context Sources**:
+- Test specs: Run `ccw spec load --category test` for test framework context, conventions, and coverage targets
 - Task JSON: `description`, `convergence.criteria`, `focus_paths`
 - Context Package: `context_package_path` → brainstorm artifacts, exploration results
 - Tech Stack: `meta.shared_context.tech_stack` (skip auto-detection if present)

.claude/agents/test-action-planning-agent.md

@@ -52,6 +52,9 @@ Read("d:\Claude_dms3\.claude\agents\action-planning-agent.md")
 ```
 <!-- TODO: verify mandatory read path -->
 
+**Load Project Context** (from spec system):
+- Run: `ccw spec load --category test` for test framework, coverage targets, and conventions
+
 </role>
 
 <test_specification_reference>

.claude/agents/test-context-search-agent.md

@@ -25,6 +25,7 @@ You are a test context discovery specialist focused on gathering test coverage i
 **Mandatory Initial Read:**
 - Project `CLAUDE.md` for coding standards and conventions
 - Test session metadata (`workflow-session.json`) for session context
+- Run: `ccw spec load --category test` for test framework, coverage targets, and conventions
 
 **Core Responsibilities:**
 - Coverage-first analysis of existing tests

.claude/agents/test-fix-agent.md

@@ -34,6 +34,9 @@ If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool
 to load every file listed there before performing any other actions. This is your
 primary context.
 
+**Load Project Context** (from spec system):
+- Run: `ccw spec load --category test` for test framework, coverage targets, and conventions
+
 ## Core Philosophy
 
 **"Tests Are the Review"** - When all tests pass across all layers, the code is approved and ready. No separate review process is needed.

.claude/skills/review-code/SKILL.md

@@ -40,6 +40,8 @@ Multi-dimensional code review skill that analyzes code across 6 key dimensions a
 └─────────────────────────────────────────────────────────────────┘
 ```
 
+**Project Context**: Run `ccw spec load --category review` for review standards, checklists, and approval gates.
+
 ## Key Design Principles
 
 1. **多维度审查**: 覆盖正确性、可读性、性能、安全性、测试覆盖、架构一致性六大维度

.claude/skills/review-cycle/SKILL.md

@@ -98,6 +98,10 @@ Skill(skill="review-cycle", args="-y src/auth/**")
 | module | [phases/review-module.md](phases/review-module.md) | review-module-cycle.md | Module-based review: path patterns → 7-dimension parallel analysis → aggregation → deep-dive → completion |
 | fix | [phases/review-fix.md](phases/review-fix.md) | review-cycle-fix.md | Automated fix: export file → intelligent batching → parallel planning → execution → completion |
 
+## Project Context
+
+Run `ccw spec load --category review` for review standards, checklists, and approval gates.
+
 ## Core Rules
 
 1. **Mode Detection First**: Parse input to determine session/module/fix mode before anything else

.claude/skills/skill-simplify/phases/02-optimize.md

@@ -9,6 +9,10 @@ Apply simplification rules from analysisResult to produce optimized content. Wri
 - Fix pseudo-code format issues
 - Write optimized content back to target file
 
+## Pre-Step: Load Context
+
+Run `ccw spec load --category validation` for verification rules and acceptance criteria to validate optimization preserves functional integrity.
+
 ## Execution
 
 ### Step 2.1: Apply Operations in Order

.claude/skills/spec-generator/phases/05-epics-stories.md

@@ -19,6 +19,10 @@ Decompose the specification into executable Epics and Stories with dependency ma
 
 ## Execution Steps
 
+### Step 0: Load Validation Context
+
+Run `ccw spec load --category validation` for verification rules and acceptance criteria to validate epic decomposition.
+
 ### Step 1: Load Phase 2-4 Context
 
 ```javascript

.claude/skills/team-frontend-debug/roles/analyzer/role.md

@@ -31,8 +31,9 @@ Root cause analysis from debug evidence.
 
 ## Phase 2: Load Evidence
 
-1. Read upstream artifacts via team_msg(operation="get_state", role="reproducer")
-2. Extract evidence paths from reproducer's state_update ref
+1. Load debug specs: Run `ccw spec load --category debug` for known issues, workarounds, and root-cause notes
+2. Read upstream artifacts via team_msg(operation="get_state", role="reproducer")
+3. Extract evidence paths from reproducer's state_update ref
 3. Load evidence-summary.json from session evidence/
 4. Load all evidence files:
    - Read screenshot files (visual inspection)

.claude/skills/team-quality-assurance/roles/executor/role.md

@@ -26,7 +26,8 @@ Run test suites, collect coverage data, and perform automatic fix cycles when te
 | Target layer | task description `layer: L1/L2/L3` | Yes |
 
 1. Extract session path and target layer from task description
-2. Read .msg/meta.json for strategy and generated test file list
+2. Load validation specs: Run `ccw spec load --category validation` for verification rules and acceptance criteria
+3. Read .msg/meta.json for strategy and generated test file list
 3. Detect test command by framework:
 
 | Framework | Command |

.claude/skills/team-review/roles/reviewer/role.md

@@ -21,7 +21,8 @@ Deep analysis on scan findings: triage, root cause / impact / optimization enric
 | .msg/meta.json | <session>/.msg/meta.json | No |
 
 1. Extract session path, input path, dimensions from task description
-2. Load scan results. If missing or empty -> report clean, complete immediately
+2. Load review specs: Run `ccw spec load --category review` for review standards, checklists, and approval gates
+3. Load scan results. If missing or empty -> report clean, complete immediately
 3. Load wisdom files from `<session>/wisdom/`
 4. Triage findings into two buckets:
 

.claude/skills/team-tech-debt/roles/scanner/role.md

@@ -18,7 +18,8 @@ Multi-dimension tech debt scanner. Scan codebase across 5 dimensions (code, arch
 | .msg/meta.json | <session>/.msg/meta.json | Yes |
 
 1. Extract session path and scan scope from task description
-2. Read .msg/meta.json for team context
+2. Load debug specs: Run `ccw spec load --category debug` for known issues, workarounds, and root-cause notes
+3. Read .msg/meta.json for team context
 3. Detect project type and framework:
 
 | Signal File | Project Type |

.claude/skills/team-testing/roles/executor/role.md

@@ -24,7 +24,8 @@ Execute tests, collect coverage, attempt auto-fix for failures. Acts as the Crit
 | .msg/meta.json | <session>/wisdom/.msg/meta.json | No |
 
 1. Extract session path and test directory from task description
-2. Extract coverage target (default: 80%)
+2. Load test specs: Run `ccw spec load --category test` for test framework conventions and coverage targets
+3. Extract coverage target (default: 80%)
 3. Read .msg/meta.json for framework info (from strategist namespace)
 4. Determine test framework:
 

.claude/skills/team-testing/roles/generator/role.md

@@ -22,7 +22,8 @@ Generate test code by layer (L1 unit / L2 integration / L3 E2E). Acts as the Gen
 | .msg/meta.json | <session>/wisdom/.msg/meta.json | No |
 
 1. Extract session path and layer from task description
-2. Read test strategy:
+2. Load test specs: Run `ccw spec load --category test` for test framework conventions and coverage targets
+3. Read test strategy:
 
 ```
 Read("<session>/strategy/test-strategy.md")

.claude/skills/team-ultra-analyze/roles/explorer/role.md

@@ -18,7 +18,8 @@ Explore codebase structure through cli-explore-agent, collecting structured cont
 | Task description | From task subject/description | Yes |
 | Session path | Extracted from task description | Yes |
 
-1. Extract session path, topic, perspective, dimensions from task description:
+1. Load debug specs: Run `ccw spec load --category debug` for known issues and root-cause notes
+2. Extract session path, topic, perspective, dimensions from task description:
 
 | Field | Pattern | Default |
 |-------|---------|---------|

.claude/skills/workflow-execute/phases/06-review.md

@@ -93,7 +93,7 @@ rg "password|token|secret|auth" -g "*.{ts,js,py}"
 rg "eval|exec|innerHTML|dangerouslySetInnerHTML" -g "*.{ts,js,tsx}"
 
 # Gemini security analysis
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Security audit of completed implementation
 TASK: Review code for security vulnerabilities, insecure patterns, auth/authz issues
@@ -105,7 +105,7 @@ RULES: Focus on OWASP Top 10, authentication, authorization, data validation, in
 
 **Architecture Review** (`architecture`):
 ```bash
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Architecture compliance review
 TASK: Evaluate adherence to architectural patterns, identify technical debt, review design decisions
@@ -117,7 +117,7 @@ RULES: Check for patterns, separation of concerns, modularity, scalability
 
 **Quality Review** (`quality`):
 ```bash
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Code quality and best practices review
 TASK: Assess code readability, maintainability, adherence to best practices
@@ -139,7 +139,7 @@ for task_file in ${sessionPath}/.task/*.json; do
 done
 
 # Cross-check implementation against requirements
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Verify all requirements and acceptance criteria are met
 TASK: Cross-check implementation summaries against original requirements

.claude/skills/workflow-lite-test-review/SKILL.md

@@ -8,6 +8,8 @@ allowed-tools: Skill, Agent, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash
 
 Test review and fix engine for lite-execute chain or standalone invocation.
 
+**Project Context**: Run `ccw spec load --category test` for test framework conventions, coverage targets, and fixtures.
+
 ---
 
 ## Usage

.claude/skills/workflow-plan/phases/05-plan-verify.md

@@ -34,6 +34,10 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 ## Execution
 
+### Step 5.0: Load Validation Context
+
+Run `ccw spec load --category validation` for verification rules and acceptance criteria.
+
 ### Step 5.1: Initialize Analysis Context
 
 ```bash

.claude/skills/workflow-tdd-plan/phases/02-context-gathering.md

@@ -222,6 +222,7 @@ Execute complete context-search-agent workflow for TDD implementation planning:
 ### Phase 1: Initialization & Pre-Analysis
 1. **Project State Loading**:
    - Run: \`ccw spec load --category execution\` to load project context, tech stack, and guidelines.
+   - Run: \`ccw spec load --category test\` to load test framework conventions, coverage targets, and fixtures.
    - If files don't exist, proceed with fresh analysis.
 2. **Detection**: Check for existing context-package (early exit if valid)
 3. **Foundation**: Initialize CodexLens, get project structure, load docs

.claude/skills/workflow-tdd-plan/phases/05-tdd-task-generation.md

@@ -237,13 +237,14 @@ MCP Capabilities: {exa_code, exa_web, code_index}
 These files provide project-level constraints that apply to ALL tasks:
 
 1. **ccw spec load --category execution** (project specs and tech analysis)
+2. **ccw spec load --category test** (test framework, coverage targets, conventions)
    - Contains: tech_stack, architecture_type, key_components, build_system, test_framework, coding_conventions, naming_rules, forbidden_patterns, quality_gates, custom_constraints
    - Usage: Populate plan.json shared_context, align task tech choices, set correct test commands
    - Apply as HARD CONSTRAINTS on all generated tasks — task implementation steps,
      acceptance criteria, and convergence.verification MUST respect these guidelines
    - If empty/missing: No additional constraints (proceed normally)
 
-Loading order: \`ccw spec load --category execution\` → planning-notes.md → context-package.json
+Loading order: \`ccw spec load --category execution\` → \`ccw spec load --category test\` → planning-notes.md → context-package.json
 
 ## USER CONFIGURATION (from Phase 0)
 Execution Method: ${userConfig.executionMethod}  // agent|hybrid|cli

.claude/skills/workflow-test-fix/phases/02-test-context-gather.md

@@ -346,6 +346,7 @@ Execute complete context-search-agent workflow for implementation planning:
 ### Phase 1: Initialization & Pre-Analysis
 1. **Project State Loading**:
    - Run: \`ccw spec load --category execution\` to load project context, tech stack, and guidelines.
+   - Run: \`ccw spec load --category test\` to load test framework conventions, coverage targets, and fixtures.
    - If files don't exist, proceed with fresh analysis.
 2. **Detection**: Check for existing context-package (early exit if valid)
 3. **Foundation**: Initialize CodexLens, get project structure, load docs

.claude/skills/workflow-test-fix/phases/05-test-cycle-execute.md

@@ -249,7 +249,8 @@ Task(
     ${selectedStrategy} - ${strategyDescription}
 
     ## PROJECT CONTEXT (MANDATORY)
-    1. Run: \`ccw spec load --category execution\` (tech stack, test framework, build system, constraints)
+    1. Run: \`ccw spec load --category execution\` (tech stack, build system, constraints)
+    2. Run: \`ccw spec load --category test\` (test framework, coverage targets, conventions)
 
     ## MANDATORY FIRST STEPS
     1. Read test results: ${session.test_results_path}

.claude/skills/workflow-tune/phases/01-setup.md

@@ -377,6 +377,99 @@ if (invalidSteps.length > 0) {
 }
 ```
 
+### Step 1.2b: Generate Test Requirements (Acceptance Criteria)
+
+> 调优的前提：为每一步生成跟任务匹配的验收标准。没有预期基准，就无法判断命令执行是否达标。
+
+用 Gemini 根据 step command + workflow context + 上下游关系，自动推断每步的验收标准。
+
+```javascript
+// Build step chain description for context
+const stepChainDesc = steps.map((s, i) =>
+  `Step ${i + 1}: ${s.name} (${s.type}) — ${s.command}`
+).join('\n');
+
+const reqGenPrompt = `PURPOSE: Generate concrete acceptance criteria (test requirements) for each step in a workflow pipeline. These criteria will be used to objectively judge whether each step's execution succeeded or failed.
+
+WORKFLOW:
+Name: ${workflowName}
+Goal: ${workflowContext}
+
+STEP CHAIN:
+${stepChainDesc}
+
+TASK:
+For each step, generate:
+1. **expected_outputs** — what files/artifacts should be produced (specific filenames or patterns)
+2. **content_signals** — what content patterns indicate success (keywords, structures, data shapes)
+3. **quality_thresholds** — minimum quality bar (e.g., "no empty files", "JSON must be parseable", "must contain at least N items")
+4. **pass_criteria** — 1-2 sentence description of what "pass" looks like for this step
+5. **fail_signals** — what patterns indicate failure (error messages, empty output, wrong format)
+6. **handoff_contract** — what this step must provide for the next step to work (data format, required fields)
+
+CONTEXT RULES:
+- Infer from the command what the step is supposed to do
+- Consider workflow goal when judging what "good enough" means
+- Each step's handoff_contract should match what the next step needs as input
+- Be specific: "report.md with ## Summary section" not "a report file"
+
+EXPECTED OUTPUT (strict JSON, no markdown):
+{
+  "step_requirements": [
+    {
+      "step_index": 0,
+      "step_name": "<name>",
+      "expected_outputs": ["<file or pattern>"],
+      "content_signals": ["<keyword or pattern that indicates success>"],
+      "quality_thresholds": ["<minimum bar>"],
+      "pass_criteria": "<what pass looks like>",
+      "fail_signals": ["<pattern that indicates failure>"],
+      "handoff_contract": "<what next step needs from this step>"
+    }
+  ]
+}
+
+CONSTRAINTS: Be specific to each command, output ONLY JSON`;
+
+Bash({
+  command: `ccw cli -p "${escapeForShell(reqGenPrompt)}" --tool gemini --mode analysis --rule universal-rigorous-style`,
+  run_in_background: true,
+  timeout: 300000
+});
+
+// STOP — wait for hook callback
+// After callback: parse JSON, attach requirements to each step
+
+const reqOutput = /* CLI output from callback */;
+const reqJsonMatch = reqOutput.match(/\{[\s\S]*\}/);
+
+if (reqJsonMatch) {
+  try {
+    const reqData = JSON.parse(reqJsonMatch[0]);
+    (reqData.step_requirements || []).forEach(req => {
+      const idx = req.step_index;
+      if (idx >= 0 && idx < steps.length) {
+        steps[idx].test_requirements = {
+          expected_outputs: req.expected_outputs || [],
+          content_signals: req.content_signals || [],
+          quality_thresholds: req.quality_thresholds || [],
+          pass_criteria: req.pass_criteria || '',
+          fail_signals: req.fail_signals || [],
+          handoff_contract: req.handoff_contract || ''
+        };
+      }
+    });
+  } catch (e) {
+    // Fallback: proceed without generated requirements
+    // Steps will use any manually provided success_criteria
+  }
+}
+
+// Capture session ID for resume chain start
+const reqSessionMatch = reqOutput.match(/\[CCW_EXEC_ID=([^\]]+)\]/);
+const reqSessionId = reqSessionMatch ? reqSessionMatch[1] : null;
+```
+
 ### Step 1.3: Create Workspace
 
 ```javascript
@@ -414,9 +507,10 @@ const initialState = {
     index: i,
     status: 'pending',
     execution: null,
-    analysis: null
+    analysis: null,
+    test_requirements: s.test_requirements || null  // from Step 1.2b
   })),
-  analysis_session_id: null,  // ccw cli resume chain
+  analysis_session_id: reqSessionId || null,  // resume chain starts from requirements generation
   process_log_entries: [],
   synthesis: null,
   errors: [],