knowzcode 0.3.6 → 0.4.0

package/skills/continue.md

@@ -1,126 +1,126 @@
----
-name: continue
-description: Detect continuation intent and resume active WorkGroup workflow
-trigger: User says "continue", "keep going", "resume", or similar continuation intent
----
-
-# Continue Skill
-
-**Purpose**: Detect when user wants to continue work and resume the active WorkGroup with proper context restoration.
-
-## Trigger Patterns
-
-Activate when user message matches ANY of these patterns:
-- "continue"
-- "keep going"
-- "resume"
-- "carry on"
-- "next"
-- "continue with this"
-- "let's continue"
-- "keep working"
-
-**Context Requirements**:
-- Must be in a KnowzCode-initialized project (knowzcode/ directory exists)
-- Should NOT trigger if user is clearly giving new instructions
-- Should NOT trigger during explicit command execution
-
-## When NOT to Trigger
-
-- User is giving specific new instructions
-- User is asking a question
-- Already executing a /kc:* command
-- knowzcode/ directory doesn't exist
-
-## Skill Behavior
-
-When triggered:
-
-### Step 1: Find Active WorkGroup
-
-Search `knowzcode/knowzcode_tracker.md` for `[WIP]` entries.
-
-- **One active WorkGroup**: Use it automatically
-- **Multiple active**: Present options to user
-- **None active**: Inform user and suggest `/kc:work`
-
-### Step 2: Load WorkGroup Context
-
-Read `knowzcode/workgroups/{WorkGroupID}.md` to determine:
-- Current phase
-- Primary goal
-- Change Set
-- Outstanding todos
-- **Autonomous Mode**: If the WorkGroup file contains `**Autonomous Mode**: Active`, restore `AUTONOMOUS_MODE = true` and announce: `> **Autonomous Mode: RESTORED** — continuing with auto-approved gates.`
-- **Orchestration Config**: If `knowzcode/knowzcode_orchestration.md` exists, parse and restore `MAX_BUILDERS`, `SCOUT_MODE`, `MCP_AGENTS_ENABLED`, `DEFAULT_SPECIALISTS` (same logic as work.md Step 2.4). Defaults apply if file is absent.
-
-### Step 3: Resume at Current Phase
-
-Read `knowzcode/knowzcode_loop.md` and resume the workflow at the detected phase.
-
-#### Parallel Mode Detection
-
-If the WorkGroup file contains a `## Current Stage` section (instead of `Current Phase`):
-- This is a **parallel-mode WorkGroup**
-- Read the per-NodeID phase table to determine what's in progress
-- Resume by recreating the team and spawning agents appropriate for the current stage:
-  - **Stage 0/1**: Spawn analyst + architect. If `SCOUT_MODE != "none"` and context is stale, re-spawn scout(s) per SCOUT_MODE.
-  - **Stage 2**: Spawn builder(s) per the dependency map + reviewer if any NodeIDs are past implementation
-  - **Stage 3**: Spawn closer
-- Builders and reviewer persist through gap loops (don't respawn per iteration)
-- Announce: `**Resuming Parallel Teams** — Stage {N}: {description}`
-
-If resuming mid-Stage-2 (e.g., builder was implementing, reviewer had started auditing):
-- Read the per-NodeID status table to determine which NodeIDs need builders and which need reviewer
-- Carry forward existing context by reading the WorkGroup file
-
-#### Sequential Mode Detection
-
-If the WorkGroup file contains `Current Phase:` (standard format):
-- This is a **sequential-mode WorkGroup**
-- Create tasks only for the **remaining** phases (not completed ones):
-
-| Detected Phase | Remaining Work |
-|----------------|----------------|
-| 1A | All phases (1A → 1B → 2A → 2B → 3) |
-| 1B | Specs + implementation + audit + finalization |
-| 2A | Implementation + audit + finalization |
-| 2B | Audit + finalization |
-| 3 | Finalization only |
-
-**Set up execution mode** — check `~/.claude/settings.json` and `.claude/settings.json` for `"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"` in the `env` block. If found, Agent Teams is available — create a team named `kc-{wgid}` and activate delegate mode (you coordinate only, never write code directly). Read `knowzcode/claude_code_execution.md` for team conventions. For each remaining phase, spawn one teammate with the spawn prompt from the corresponding phase section of `/kc:work`, create a task, wait for completion, present quality gate, shut down teammate. Shut down all teammates when done or on cancel.
-
-If Agent Teams is not available, announce `**Execution Mode: Subagent Delegation** — Agent Teams not available (add "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" to the env block in settings.json, then restart Claude Code)` and use `Task()` calls to delegate each remaining phase to the named agent.
-
-Follow the same phase delegation patterns (spawn prompts, quality gates, gap loop) as `/kc:work`.
-
-### Step 4: Present Status
-
-```markdown
-## Resuming WorkGroup: {wgid}
-
-**Goal**: {primary goal}
-**Phase**: {current phase}
-**NodeIDs**: {list}
-
-**Outstanding Todos**:
-{list from WorkGroup file}
-
-Continuing from where we left off...
-```
-
-Then proceed with the appropriate phase using the same agents as `/kc:work`.
-
-## Logging
-
-```markdown
----
-**Type:** SkillActivation
-**Timestamp:** [timestamp]
-**Skill:** continue
-**Trigger:** User said "{user_message}"
-**WorkGroup:** {wgid}
-**Phase:** {current phase}
-**Logged By:** AI-Agent
----
-```
+---
+name: continue
+description: Detect continuation intent and resume active WorkGroup workflow
+trigger: User says "continue", "keep going", "resume", or similar continuation intent
+---
+
+# Continue Skill
+
+**Purpose**: Detect when user wants to continue work and resume the active WorkGroup with proper context restoration.
+
+## Trigger Patterns
+
+Activate when user message matches ANY of these patterns:
+- "continue"
+- "keep going"
+- "resume"
+- "carry on"
+- "next"
+- "continue with this"
+- "let's continue"
+- "keep working"
+
+**Context Requirements**:
+- Must be in a KnowzCode-initialized project (knowzcode/ directory exists)
+- Should NOT trigger if user is clearly giving new instructions
+- Should NOT trigger during explicit command execution
+
+## When NOT to Trigger
+
+- User is giving specific new instructions
+- User is asking a question
+- Already executing a /kc:* command
+- knowzcode/ directory doesn't exist
+
+## Skill Behavior
+
+When triggered:
+
+### Step 1: Find Active WorkGroup
+
+Search `knowzcode/knowzcode_tracker.md` for `[WIP]` entries.
+
+- **One active WorkGroup**: Use it automatically
+- **Multiple active**: Present options to user
+- **None active**: Inform user and suggest `/kc:work`
+
+### Step 2: Load WorkGroup Context
+
+Read `knowzcode/workgroups/{WorkGroupID}.md` to determine:
+- Current phase
+- Primary goal
+- Change Set
+- Outstanding todos
+- **Autonomous Mode**: If the WorkGroup file contains `**Autonomous Mode**: Active`, restore `AUTONOMOUS_MODE = true` and announce: `> **Autonomous Mode: RESTORED** — continuing with auto-approved gates.`
+- **Orchestration Config**: If `knowzcode/knowzcode_orchestration.md` exists, parse and restore `MAX_BUILDERS`, `SCOUT_MODE`, `MCP_AGENTS_ENABLED`, `DEFAULT_SPECIALISTS` (same logic as work.md Step 2.4). Defaults apply if file is absent.
+
+### Step 3: Resume at Current Phase
+
+Read `knowzcode/knowzcode_loop.md` and resume the workflow at the detected phase.
+
+#### Parallel Mode Detection
+
+If the WorkGroup file contains a `## Current Stage` section (instead of `Current Phase`):
+- This is a **parallel-mode WorkGroup**
+- Read the per-NodeID phase table to determine what's in progress
+- Resume by recreating the team and spawning agents appropriate for the current stage:
+  - **Stage 0/1**: Spawn analyst + architect. If `SCOUT_MODE != "none"` and context is stale, re-spawn scout(s) per SCOUT_MODE.
+  - **Stage 2**: Spawn builder(s) per the dependency map + reviewer if any NodeIDs are past implementation
+  - **Stage 3**: Spawn closer
+- Builders and reviewer persist through gap loops (don't respawn per iteration)
+- Announce: `**Resuming Parallel Teams** — Stage {N}: {description}`
+
+If resuming mid-Stage-2 (e.g., builder was implementing, reviewer had started auditing):
+- Read the per-NodeID status table to determine which NodeIDs need builders and which need reviewer
+- Carry forward existing context by reading the WorkGroup file
+
+#### Sequential Mode Detection
+
+If the WorkGroup file contains `Current Phase:` (standard format):
+- This is a **sequential-mode WorkGroup**
+- Create tasks only for the **remaining** phases (not completed ones):
+
+| Detected Phase | Remaining Work |
+|----------------|----------------|
+| 1A | All phases (1A → 1B → 2A → 2B → 3) |
+| 1B | Specs + implementation + audit + finalization |
+| 2A | Implementation + audit + finalization |
+| 2B | Audit + finalization |
+| 3 | Finalization only |
+
+**Set up execution mode** — check `~/.claude/settings.json` and `.claude/settings.json` for `"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"` in the `env` block. If found, Agent Teams is available — create a team named `kc-{wgid}` and activate delegate mode (you coordinate only, never write code directly). Read `knowzcode/claude_code_execution.md` for team conventions. For each remaining phase, spawn one teammate with the spawn prompt from the corresponding phase section of `/kc:work`, create a task, wait for completion, present quality gate, shut down teammate. Shut down all teammates when done or on cancel.
+
+If Agent Teams is not available, announce `**Execution Mode: Subagent Delegation** — Agent Teams not available (add "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" to the env block in settings.json, then restart Claude Code)` and use `Task()` calls to delegate each remaining phase to the named agent.
+
+Follow the same phase delegation patterns (spawn prompts, quality gates, gap loop) as `/kc:work`.
+
+### Step 4: Present Status
+
+```markdown
+## Resuming WorkGroup: {wgid}
+
+**Goal**: {primary goal}
+**Phase**: {current phase}
+**NodeIDs**: {list}
+
+**Outstanding Todos**:
+{list from WorkGroup file}
+
+Continuing from where we left off...
+```
+
+Then proceed with the appropriate phase using the same agents as `/kc:work`.
+
+## Logging
+
+```markdown
+---
+**Type:** SkillActivation
+**Timestamp:** [timestamp]
+**Skill:** continue
+**Trigger:** User said "{user_message}"
+**WorkGroup:** {wgid}
+**Phase:** {current phase}
+**Logged By:** AI-Agent
+---
+```

package/skills/environment-guard.json

@@ -1,12 +1,12 @@
-{
-  "name": "environment-guard",
-  "version": "0.3.6",
-  "description": "Verifies that knowzcode/environment_context.md no longer contains placeholder brackets.",
-  "parameters": [],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\ntext = Path('knowzcode/environment_context.md').read_text()\nplaceholders = [line.strip() for line in text.splitlines() if '[' in line and ']' in line]\nif placeholders:\n    raise ValueError('environment_context.md still contains placeholders: ' + ', '.join(placeholders[:5]))\n"
-    }
-  ]
-}
+{
+  "name": "environment-guard",
+  "version": "0.4.0",
+  "description": "Verifies that knowzcode/environment_context.md no longer contains placeholder brackets.",
+  "parameters": [],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\ntext = Path('knowzcode/environment_context.md').read_text()\nplaceholders = [line.strip() for line in text.splitlines() if '[' in line and ']' in line]\nif placeholders:\n    raise ValueError('environment_context.md still contains placeholders: ' + ', '.join(placeholders[:5]))\n"
+    }
+  ]
+}

package/skills/generate-workgroup-id.json

@@ -1,25 +1,25 @@
-{
-  "name": "generate-workgroup-id",
-  "version": "0.3.6",
-  "description": "Generates a WorkGroupID following the KnowzCode convention [type]-[slug]-YYYYMMDD-HHMMSS. The slug is a 2-4 word descriptor extracted from the goal.",
-  "parameters": [
-    {
-      "name": "type",
-      "type": "string",
-      "required": true,
-      "description": "One of feat, fix, refactor, issue"
-    },
-    {
-      "name": "slug",
-      "type": "string",
-      "required": false,
-      "description": "A 2-4 word kebab-case descriptor (e.g., 'auth-jwt', 'dark-mode'). If not provided, generates ID without slug."
-    }
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "import datetime\nimport re\nallowed = {'feat', 'fix', 'refactor', 'issue'}\nwg_type = inputs['type']\nif wg_type not in allowed:\n    raise ValueError(f'Invalid type {wg_type!r}, expected one of {sorted(allowed)}')\ntimestamp = datetime.datetime.utcnow().strftime('%Y%m%d-%H%M%S')\nslug = inputs.get('slug', '')\nif slug:\n    # Sanitize slug: lowercase, replace spaces with hyphens, remove non-alphanumeric\n    slug = re.sub(r'[^a-z0-9-]', '', slug.lower().replace(' ', '-'))\n    slug = re.sub(r'-+', '-', slug).strip('-')[:25]  # Max 25 chars\n    outputs['workgroup_id'] = f'{wg_type}-{slug}-{timestamp}'\nelse:\n    outputs['workgroup_id'] = f'{wg_type}-{timestamp}'"
-    }
-  ]
-}
+{
+  "name": "generate-workgroup-id",
+  "version": "0.4.0",
+  "description": "Generates a WorkGroupID following the KnowzCode convention [type]-[slug]-YYYYMMDD-HHMMSS. The slug is a 2-4 word descriptor extracted from the goal.",
+  "parameters": [
+    {
+      "name": "type",
+      "type": "string",
+      "required": true,
+      "description": "One of feat, fix, refactor, issue"
+    },
+    {
+      "name": "slug",
+      "type": "string",
+      "required": false,
+      "description": "A 2-4 word kebab-case descriptor (e.g., 'auth-jwt', 'dark-mode'). If not provided, generates ID without slug."
+    }
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "import datetime\nimport re\nallowed = {'feat', 'fix', 'refactor', 'issue'}\nwg_type = inputs['type']\nif wg_type not in allowed:\n    raise ValueError(f'Invalid type {wg_type!r}, expected one of {sorted(allowed)}')\ntimestamp = datetime.datetime.utcnow().strftime('%Y%m%d-%H%M%S')\nslug = inputs.get('slug', '')\nif slug:\n    # Sanitize slug: lowercase, replace spaces with hyphens, remove non-alphanumeric\n    slug = re.sub(r'[^a-z0-9-]', '', slug.lower().replace(' ', '-'))\n    slug = re.sub(r'-+', '-', slug).strip('-')[:25]  # Max 25 chars\n    outputs['workgroup_id'] = f'{wg_type}-{slug}-{timestamp}'\nelse:\n    outputs['workgroup_id'] = f'{wg_type}-{timestamp}'"
+    }
+  ]
+}

package/skills/install-knowzcode.json

@@ -1,21 +1,21 @@
-{
-  "name": "install-knowzcode",
-  "version": "0.3.6",
-  "description": "Initializes KnowzCode directory structure and required files in the current project",
-
-  "parameters": [
-    {
-      "name": "force",
-      "type": "boolean",
-      "required": false,
-      "description": "Force reinstall even if knowzcode/ exists"
-    }
-  ],
-
-  "actions": [
-    {
-      "type": "python",
-      "code": "import os\nimport json\nfrom pathlib import Path\nfrom datetime import datetime\n\n# Configuration\ntarget_dir = Path('knowzcode')\nforce = inputs.get('force', False)\n\n# Check if target exists\nif target_dir.exists() and not force:\n    outputs['success'] = False\n    outputs['error'] = 'knowzcode/ already exists. Use force=true to reinitialize'\n    outputs['already_installed'] = True\n    exit()\n\n# Create directory structure\ntarget_dir.mkdir(exist_ok=True)\n(target_dir / 'specs').mkdir(exist_ok=True)\n(target_dir / 'workgroups').mkdir(exist_ok=True)\n(target_dir / 'prompts').mkdir(exist_ok=True)\n(target_dir / 'planning').mkdir(exist_ok=True)\n\n# Create .gitignore if it doesn't exist\ngitignore_path = target_dir / '.gitignore'\nif not gitignore_path.exists():\n    gitignore_content = '''# KnowzCode gitignore - protects environment-specific files\n\n# Environment-specific (contains local paths, commands)\nenvironment_context.md\n\n# Session-specific work (can be regenerated)\nworkgroups/\n\n# Personal notes and scratch files\n*.local.md\n.scratch/\n'''\n    with open(gitignore_path, 'w') as f:\n        f.write(gitignore_content)\n\n# Note: The actual template files (knowzcode_loop.md, etc.) should be copied\n# from the plugin template directory or created by the /kc:init command.\n# This skill creates the structure; the command copies the content.\n\noutputs['success'] = True\noutputs['target_dir'] = str(target_dir)\noutputs['directories_created'] = ['specs', 'workgroups', 'prompts', 'planning']\noutputs['gitignore_created'] = not gitignore_path.exists()\noutputs['message'] = f'KnowzCode directory structure created at {target_dir}/'"
-    }
-  ]
-}
+{
+  "name": "install-knowzcode",
+  "version": "0.4.0",
+  "description": "Initializes KnowzCode directory structure and required files in the current project",
+
+  "parameters": [
+    {
+      "name": "force",
+      "type": "boolean",
+      "required": false,
+      "description": "Force reinstall even if knowzcode/ exists"
+    }
+  ],
+
+  "actions": [
+    {
+      "type": "python",
+      "code": "import os\nimport json\nfrom pathlib import Path\nfrom datetime import datetime\n\n# Configuration\ntarget_dir = Path('knowzcode')\nforce = inputs.get('force', False)\n\n# Check if target exists\nif target_dir.exists() and not force:\n    outputs['success'] = False\n    outputs['error'] = 'knowzcode/ already exists. Use force=true to reinitialize'\n    outputs['already_installed'] = True\n    exit()\n\n# Create directory structure\ntarget_dir.mkdir(exist_ok=True)\n(target_dir / 'specs').mkdir(exist_ok=True)\n(target_dir / 'workgroups').mkdir(exist_ok=True)\n(target_dir / 'prompts').mkdir(exist_ok=True)\n(target_dir / 'planning').mkdir(exist_ok=True)\n\n# Create .gitignore if it doesn't exist\ngitignore_path = target_dir / '.gitignore'\nif not gitignore_path.exists():\n    gitignore_content = '''# KnowzCode gitignore - protects environment-specific files\n\n# Environment-specific (contains local paths, commands)\nenvironment_context.md\n\n# Session-specific work (can be regenerated)\nworkgroups/\n\n# Personal notes and scratch files\n*.local.md\n.scratch/\n'''\n    with open(gitignore_path, 'w') as f:\n        f.write(gitignore_content)\n\n# Note: The actual template files (knowzcode_loop.md, etc.) should be copied\n# from the plugin template directory or created by the /kc:init command.\n# This skill creates the structure; the command copies the content.\n\noutputs['success'] = True\noutputs['target_dir'] = str(target_dir)\noutputs['directories_created'] = ['specs', 'workgroups', 'prompts', 'planning']\noutputs['gitignore_created'] = not gitignore_path.exists()\noutputs['message'] = f'KnowzCode directory structure created at {target_dir}/'"
+    }
+  ]
+}

package/skills/load-core-context.json

@@ -1,18 +1,18 @@
-{
-  "name": "load-core-context",
-  "version": "0.3.6",
-  "description": "Loads the KnowzCode project overview, architecture, tracker, log header, and automation manifest for downstream steps.",
-  "parameters": [],
-  "actions": [
-    {
-      "type": "read_file",
-      "paths": [
-        "knowzcode/knowzcode_project.md",
-        "knowzcode/knowzcode_architecture.md",
-        "knowzcode/knowzcode_tracker.md",
-        "knowzcode/knowzcode_log.md",
-        "knowzcode/automation_manifest.md"
-      ]
-    }
-  ]
-}
+{
+  "name": "load-core-context",
+  "version": "0.4.0",
+  "description": "Loads the KnowzCode project overview, architecture, tracker, log header, and automation manifest for downstream steps.",
+  "parameters": [],
+  "actions": [
+    {
+      "type": "read_file",
+      "paths": [
+        "knowzcode/knowzcode_project.md",
+        "knowzcode/knowzcode_architecture.md",
+        "knowzcode/knowzcode_tracker.md",
+        "knowzcode/knowzcode_log.md",
+        "knowzcode/automation_manifest.md"
+      ]
+    }
+  ]
+}

package/skills/log-entry-builder.json

@@ -1,15 +1,15 @@
-{
-  "name": "log-entry-builder",
-  "version": "0.3.6",
-  "description": "Appends structured entries to knowzcode/knowzcode_log.md with KnowzCode formatting.",
-  "parameters": [
-    {"name": "entry_type", "type": "string", "required": true},
-    {"name": "content", "type": "string", "required": true}
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nentry_type = inputs['entry_type']\ncontent = inputs['content'].strip()\npath = Path('knowzcode/knowzcode_log.md')\ntext = path.read_text()\nmarker = '---\n**[NEWEST ENTRIES APPEAR HERE - DO NOT REMOVE THIS MARKER]**'\nidx = text.index(marker) + len(marker)\nnew_entry = f"\n---\n**Type:** {entry_type}\n{content}\n"\nupdated = text[:idx] + new_entry + text[idx:]\npath.write_text(updated)"
-    }
-  ]
-}
+{
+  "name": "log-entry-builder",
+  "version": "0.4.0",
+  "description": "Appends structured entries to knowzcode/knowzcode_log.md with KnowzCode formatting.",
+  "parameters": [
+    {"name": "entry_type", "type": "string", "required": true},
+    {"name": "content", "type": "string", "required": true}
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nentry_type = inputs['entry_type']\ncontent = inputs['content'].strip()\npath = Path('knowzcode/knowzcode_log.md')\ntext = path.read_text()\nmarker = '---\n**[NEWEST ENTRIES APPEAR HERE - DO NOT REMOVE THIS MARKER]**'\nidx = text.index(marker) + len(marker)\nnew_entry = f"\n---\n**Type:** {entry_type}\n{content}\n"\nupdated = text[:idx] + new_entry + text[idx:]\npath.write_text(updated)"
+    }
+  ]
+}

package/skills/spec-quality-check.json

@@ -1,14 +1,14 @@
-{
-  "name": "spec-quality-check",
-  "version": "0.3.6",
-  "description": "Validates KnowzCode spec files for mandatory sections. Supports new 4-section format and legacy numbered format.",
-  "parameters": [
-    {"name": "node_id", "type": "string", "required": true}
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nimport re\nnode_id = inputs['node_id']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nif not path.exists():\n    raise FileNotFoundError(f'Spec for {node_id} not found')\ntext = path.read_text()\n\n# Check new format first\nnew_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\nlegacy_sections = ['## 1. Purpose', '## 2. Dependencies & Triggers', '## 3. Interfaces', '## 4. Core Logic & Processing Steps', '## 5. Data Structures', '## 6. ARC Verification Criteria', '## 7. Technical Debt']\n\nnew_missing = [s for s in new_sections if s not in text]\nlegacy_missing = [s for s in legacy_sections if s not in text]\n\n# Use whichever format has fewer missing sections\nif len(new_missing) <= len(legacy_missing):\n    outputs['format'] = 'v2'\n    outputs['missing_sections'] = new_missing\nelse:\n    outputs['format'] = 'legacy'\n    outputs['missing_sections'] = legacy_missing\n    outputs['deprecation_warning'] = 'Spec uses old numbered format. New specs should use: Rules & Decisions, Interfaces, Verification Criteria, Debt & Gaps'\n"
-    }
-  ]
-}
+{
+  "name": "spec-quality-check",
+  "version": "0.4.0",
+  "description": "Validates KnowzCode spec files for mandatory sections. Supports new 4-section format and legacy numbered format.",
+  "parameters": [
+    {"name": "node_id", "type": "string", "required": true}
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nimport re\nnode_id = inputs['node_id']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nif not path.exists():\n    raise FileNotFoundError(f'Spec for {node_id} not found')\ntext = path.read_text()\n\n# Check new format first\nnew_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\nlegacy_sections = ['## 1. Purpose', '## 2. Dependencies & Triggers', '## 3. Interfaces', '## 4. Core Logic & Processing Steps', '## 5. Data Structures', '## 6. ARC Verification Criteria', '## 7. Technical Debt']\n\nnew_missing = [s for s in new_sections if s not in text]\nlegacy_missing = [s for s in legacy_sections if s not in text]\n\n# Use whichever format has fewer missing sections\nif len(new_missing) <= len(legacy_missing):\n    outputs['format'] = 'v2'\n    outputs['missing_sections'] = new_missing\nelse:\n    outputs['format'] = 'legacy'\n    outputs['missing_sections'] = legacy_missing\n    outputs['deprecation_warning'] = 'Spec uses old numbered format. New specs should use: Rules & Decisions, Interfaces, Verification Criteria, Debt & Gaps'\n"
+    }
+  ]
+}

package/skills/spec-template.json

@@ -1,15 +1,15 @@
-{
-  "name": "spec-template",
-  "version": "0.3.6",
-  "description": "Seeds or repairs KnowzCode spec files with the lean 4-section template.",
-  "parameters": [
-    {"name": "node_id", "type": "string", "required": true},
-    {"name": "label", "type": "string", "required": true}
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nfrom datetime import datetime\nnode_id = inputs['node_id']\nlabel = inputs['label']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nnow = datetime.utcnow().strftime('%Y-%m-%d %H:%M:%SZ')\ntemplate_lines = [\n    f'# {node_id}: {label}',\n    '',\n    f'**Updated:** {now}',\n    '**Status:** Draft',\n    '',\n    '## Rules & Decisions',\n    '- [Key architectural decisions, business rules, constraints, and purpose]',\n    '',\n    '## Interfaces',\n    '- [Public contracts: inputs, outputs, API signatures, dependencies, events]',\n    '',\n    '## Verification Criteria',\n    '- VERIFY: [testable assertion 1]',\n    '- VERIFY: [testable assertion 2]',\n    '',\n    '## Debt & Gaps',\n    '- [Known limitations and future work, or \"None\"]',\n    ''\n]\ntemplate = '\\n'.join(template_lines)\nif not path.exists():\n    path.write_text(template + '\\n')\n    outputs['created'] = True\nelse:\n    text = path.read_text()\n    new_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\n    if all(section in text for section in new_sections):\n        outputs['created'] = False\n    else:\n        merged = text.strip() + '\\n\\n<!-- Template sections restored -->\\n' + template + '\\n'\n        path.write_text(merged)\n        outputs['created'] = False"
-    }
-  ]
-}
+{
+  "name": "spec-template",
+  "version": "0.4.0",
+  "description": "Seeds or repairs KnowzCode spec files with the lean 4-section template.",
+  "parameters": [
+    {"name": "node_id", "type": "string", "required": true},
+    {"name": "label", "type": "string", "required": true}
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nfrom datetime import datetime\nnode_id = inputs['node_id']\nlabel = inputs['label']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nnow = datetime.utcnow().strftime('%Y-%m-%d %H:%M:%SZ')\ntemplate_lines = [\n    f'# {node_id}: {label}',\n    '',\n    f'**Updated:** {now}',\n    '**Status:** Draft',\n    '',\n    '## Rules & Decisions',\n    '- [Key architectural decisions, business rules, constraints, and purpose]',\n    '',\n    '## Interfaces',\n    '- [Public contracts: inputs, outputs, API signatures, dependencies, events]',\n    '',\n    '## Verification Criteria',\n    '- VERIFY: [testable assertion 1]',\n    '- VERIFY: [testable assertion 2]',\n    '',\n    '## Debt & Gaps',\n    '- [Known limitations and future work, or \"None\"]',\n    ''\n]\ntemplate = '\\n'.join(template_lines)\nif not path.exists():\n    path.write_text(template + '\\n')\n    outputs['created'] = True\nelse:\n    text = path.read_text()\n    new_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\n    if all(section in text for section in new_sections):\n        outputs['created'] = False\n    else:\n        merged = text.strip() + '\\n\\n<!-- Template sections restored -->\\n' + template + '\\n'\n        path.write_text(merged)\n        outputs['created'] = False"
+    }
+  ]
+}

package/skills/spec-validator.json

@@ -1,25 +1,25 @@
-{
-  "name": "spec-validator",
-  "version": "0.3.6",
-  "description": "Validates NodeID specification completeness and quality. Supports new 4-section format (preferred) and legacy numbered sections (deprecated).",
-  "parameters": [
-    {
-      "name": "spec_path",
-      "type": "string",
-      "required": true,
-      "description": "Absolute path to the spec file to validate"
-    },
-    {
-      "name": "node_id",
-      "type": "string",
-      "required": true,
-      "description": "NodeID being validated (for error reporting)"
-    }
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nimport re\n\nspec_path = Path(inputs['spec_path'])\nnode_id = inputs['node_id']\n\nif not spec_path.exists():\n    outputs['valid'] = False\n    outputs['errors'] = [f'Spec file does not exist: {spec_path}']\n    outputs['warnings'] = []\n    outputs['score'] = 0\n    outputs['node_id'] = node_id\n    outputs['format'] = 'missing'\n    exit()\n\ncontent = spec_path.read_text()\n\nerrors = []\nwarnings = []\nscore = 100\n\n# Detect format: new 4-section or legacy numbered\nnew_sections = {\n    'rules': r'##\\s*Rules\\s*(&|and)\\s*Decisions',\n    'interfaces': r'##\\s*Interfaces',\n    'verification': r'##\\s*Verification\\s*Criteria',\n    'debt': r'##\\s*Debt\\s*(&|and)\\s*Gaps'\n}\nlegacy_sections = {\n    'purpose': r'##\\s*1\\.\\s*Purpose',\n    'deps': r'##\\s*2\\.\\s*Dependencies',\n    'interfaces': r'##\\s*3\\.\\s*Interfaces',\n    'logic': r'##\\s*4\\.\\s*Core\\s*Logic',\n    'arc': r'##\\s*(6\\.\\s*Error\\s*Handling|7\\.\\s*ARC\\s*Verification)'\n}\n\nnew_count = sum(1 for p in new_sections.values() if re.search(p, content, re.IGNORECASE))\nlegacy_count = sum(1 for p in legacy_sections.values() if re.search(p, content, re.IGNORECASE))\n\nif new_count >= legacy_count:\n    spec_format = 'v2'\n    # Validate new 4-section format\n    required = [\n        (new_sections['rules'], 'Missing \"Rules & Decisions\" section'),\n        (new_sections['interfaces'], 'Missing \"Interfaces\" section'),\n        (new_sections['verification'], 'Missing \"Verification Criteria\" section'),\n        (new_sections['debt'], 'Missing \"Debt & Gaps\" section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check VERIFY: statements (minimum 2)\n    verify_section = re.search(r'##\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if verify_section:\n        verify_content = verify_section.group(1)\n        verify_count = len(re.findall(r'VERIFY:', verify_content))\n        if verify_count < 2:\n            errors.append(f'Only {verify_count} VERIFY: statements found (minimum 2 required)')\n            score -= 15\n    else:\n        errors.append('Verification Criteria section is empty or malformed')\n        score -= 20\n    \n    # Check Rules has content\n    rules_section = re.search(r'##\\s*Rules\\s*(&|and)\\s*Decisions(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if rules_section:\n        rules_content = rules_section.group(2).strip()\n        if len(rules_content) < 20 or re.search(r'^\\s*-\\s*\\[', rules_content):\n            warnings.append('Rules & Decisions section appears to have only placeholder content')\n            score -= 10\n    \n    # Check Interfaces has content\n    iface_section = re.search(r'##\\s*Interfaces(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if iface_section:\n        iface_content = iface_section.group(1).strip()\n        if len(iface_content) < 20 or re.search(r'^\\s*-\\s*\\[', iface_content):\n            warnings.append('Interfaces section appears to have only placeholder content')\n            score -= 10\nelse:\n    spec_format = 'legacy'\n    warnings.append('DEPRECATED: Spec uses old numbered format. Will be migrated when next touched during finalization.')\n    \n    # Validate legacy format\n    required = [\n        (legacy_sections['purpose'], 'Missing \"1. Purpose\" section'),\n        (legacy_sections['deps'], 'Missing \"2. Dependencies\" section'),\n        (legacy_sections['interfaces'], 'Missing \"3. Interfaces\" section'),\n        (legacy_sections['logic'], 'Missing \"4. Core Logic\" section'),\n        (legacy_sections['arc'], 'Missing ARC/Error Handling section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check ARC criteria (legacy format)\n    arc_section = re.search(r'##\\s*7\\.\\s*ARC\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if arc_section:\n        arc_content = arc_section.group(1)\n        criteria_count = len(re.findall(r'ARC_[A-Z]+_\\d+:', arc_content))\n        if criteria_count < 3:\n            errors.append(f'Only {criteria_count} testable ARC criteria found (minimum 3 required)')\n            score -= 15\n    else:\n        errors.append('ARC Verification Criteria section is empty or malformed')\n        score -= 20\n\n# Check for placeholder text (both formats)\nplaceholder_patterns = [\n    (r'\\[Agent:', 'Contains [Agent: placeholder'),\n    (r'\\[TODO', 'Contains [TODO] placeholder'),\n    (r'\\[FILL', 'Contains [FILL] placeholder'),\n    (r'\\[TBD\\]', 'Contains [TBD] placeholder'),\n    (r'\\[INSERT', 'Contains [INSERT] placeholder')\n]\nfor pattern, msg in placeholder_patterns:\n    if re.search(pattern, content, re.IGNORECASE):\n        errors.append(msg)\n        score -= 20\n        break\n\n# Calculate final validation\noutputs['valid'] = (score >= 70 and len(errors) == 0)\noutputs['score'] = max(0, score)\noutputs['errors'] = errors\noutputs['warnings'] = warnings\noutputs['node_id'] = node_id\noutputs['spec_path'] = str(spec_path)\noutputs['format'] = spec_format"
-    }
-  ]
-}
+{
+  "name": "spec-validator",
+  "version": "0.4.0",
+  "description": "Validates NodeID specification completeness and quality. Supports new 4-section format (preferred) and legacy numbered sections (deprecated).",
+  "parameters": [
+    {
+      "name": "spec_path",
+      "type": "string",
+      "required": true,
+      "description": "Absolute path to the spec file to validate"
+    },
+    {
+      "name": "node_id",
+      "type": "string",
+      "required": true,
+      "description": "NodeID being validated (for error reporting)"
+    }
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nimport re\n\nspec_path = Path(inputs['spec_path'])\nnode_id = inputs['node_id']\n\nif not spec_path.exists():\n    outputs['valid'] = False\n    outputs['errors'] = [f'Spec file does not exist: {spec_path}']\n    outputs['warnings'] = []\n    outputs['score'] = 0\n    outputs['node_id'] = node_id\n    outputs['format'] = 'missing'\n    exit()\n\ncontent = spec_path.read_text()\n\nerrors = []\nwarnings = []\nscore = 100\n\n# Detect format: new 4-section or legacy numbered\nnew_sections = {\n    'rules': r'##\\s*Rules\\s*(&|and)\\s*Decisions',\n    'interfaces': r'##\\s*Interfaces',\n    'verification': r'##\\s*Verification\\s*Criteria',\n    'debt': r'##\\s*Debt\\s*(&|and)\\s*Gaps'\n}\nlegacy_sections = {\n    'purpose': r'##\\s*1\\.\\s*Purpose',\n    'deps': r'##\\s*2\\.\\s*Dependencies',\n    'interfaces': r'##\\s*3\\.\\s*Interfaces',\n    'logic': r'##\\s*4\\.\\s*Core\\s*Logic',\n    'arc': r'##\\s*(6\\.\\s*Error\\s*Handling|7\\.\\s*ARC\\s*Verification)'\n}\n\nnew_count = sum(1 for p in new_sections.values() if re.search(p, content, re.IGNORECASE))\nlegacy_count = sum(1 for p in legacy_sections.values() if re.search(p, content, re.IGNORECASE))\n\nif new_count >= legacy_count:\n    spec_format = 'v2'\n    # Validate new 4-section format\n    required = [\n        (new_sections['rules'], 'Missing \"Rules & Decisions\" section'),\n        (new_sections['interfaces'], 'Missing \"Interfaces\" section'),\n        (new_sections['verification'], 'Missing \"Verification Criteria\" section'),\n        (new_sections['debt'], 'Missing \"Debt & Gaps\" section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check VERIFY: statements (minimum 2)\n    verify_section = re.search(r'##\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if verify_section:\n        verify_content = verify_section.group(1)\n        verify_count = len(re.findall(r'VERIFY:', verify_content))\n        if verify_count < 2:\n            errors.append(f'Only {verify_count} VERIFY: statements found (minimum 2 required)')\n            score -= 15\n    else:\n        errors.append('Verification Criteria section is empty or malformed')\n        score -= 20\n    \n    # Check Rules has content\n    rules_section = re.search(r'##\\s*Rules\\s*(&|and)\\s*Decisions(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if rules_section:\n        rules_content = rules_section.group(2).strip()\n        if len(rules_content) < 20 or re.search(r'^\\s*-\\s*\\[', rules_content):\n            warnings.append('Rules & Decisions section appears to have only placeholder content')\n            score -= 10\n    \n    # Check Interfaces has content\n    iface_section = re.search(r'##\\s*Interfaces(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if iface_section:\n        iface_content = iface_section.group(1).strip()\n        if len(iface_content) < 20 or re.search(r'^\\s*-\\s*\\[', iface_content):\n            warnings.append('Interfaces section appears to have only placeholder content')\n            score -= 10\nelse:\n    spec_format = 'legacy'\n    warnings.append('DEPRECATED: Spec uses old numbered format. Will be migrated when next touched during finalization.')\n    \n    # Validate legacy format\n    required = [\n        (legacy_sections['purpose'], 'Missing \"1. Purpose\" section'),\n        (legacy_sections['deps'], 'Missing \"2. Dependencies\" section'),\n        (legacy_sections['interfaces'], 'Missing \"3. Interfaces\" section'),\n        (legacy_sections['logic'], 'Missing \"4. Core Logic\" section'),\n        (legacy_sections['arc'], 'Missing ARC/Error Handling section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check ARC criteria (legacy format)\n    arc_section = re.search(r'##\\s*7\\.\\s*ARC\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if arc_section:\n        arc_content = arc_section.group(1)\n        criteria_count = len(re.findall(r'ARC_[A-Z]+_\\d+:', arc_content))\n        if criteria_count < 3:\n            errors.append(f'Only {criteria_count} testable ARC criteria found (minimum 3 required)')\n            score -= 15\n    else:\n        errors.append('ARC Verification Criteria section is empty or malformed')\n        score -= 20\n\n# Check for placeholder text (both formats)\nplaceholder_patterns = [\n    (r'\\[Agent:', 'Contains [Agent: placeholder'),\n    (r'\\[TODO', 'Contains [TODO] placeholder'),\n    (r'\\[FILL', 'Contains [FILL] placeholder'),\n    (r'\\[TBD\\]', 'Contains [TBD] placeholder'),\n    (r'\\[INSERT', 'Contains [INSERT] placeholder')\n]\nfor pattern, msg in placeholder_patterns:\n    if re.search(pattern, content, re.IGNORECASE):\n        errors.append(msg)\n        score -= 20\n        break\n\n# Calculate final validation\noutputs['valid'] = (score >= 70 and len(errors) == 0)\noutputs['score'] = max(0, score)\noutputs['errors'] = errors\noutputs['warnings'] = warnings\noutputs['node_id'] = node_id\noutputs['spec_path'] = str(spec_path)\noutputs['format'] = spec_format"
+    }
+  ]
+}