cokit-cli 1.2.0 → 1.2.3

package/skills/README.md

@@ -1,17 +1,11 @@
 # Skills
-Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks. Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows, or automating personal tasks.
-
-For more information, check out:
-- [What are skills?](https://support.claude.com/en/articles/12512176-what-are-skills)
-- [Using skills in Claude](https://support.claude.com/en/articles/12512180-using-skills-in-claude)
-- [How to create custom skills](https://support.claude.com/en/articles/12512198-creating-custom-skills)
-- [Equipping agents for the real world with Agent Skills](https://anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills)
+Skills are folders of instructions, scripts, and resources that the AI agent loads dynamically to improve performance on specialized tasks. Skills teach the AI agent how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows, or automating personal tasks.
 
 # About This Repository
 
-This repository contains example skills that demonstrate what's possible with Claude's skills system. These examples range from creative applications (art, music, design) to technical tasks (testing web apps, MCP server generation) to enterprise workflows (communications, branding, etc.).
+This repository contains example skills that demonstrate what's possible with the skills system. These examples range from creative applications (art, music, design) to technical tasks (testing web apps, MCP server generation) to enterprise workflows (communications, branding, etc.).
 
-Each skill is self-contained in its own directory with a `SKILL.md` file containing the instructions and metadata that Claude uses. Browse through these examples to get inspiration for your own skills or to understand different patterns and approaches.
+Each skill is self-contained in its own directory with a `SKILL.md` file containing the instructions and metadata that the AI agent uses. Browse through these examples to get inspiration for your own skills or to understand different patterns and approaches.
 
 The example skills in this repo are open source (Apache 2.0).
 
@@ -19,7 +13,7 @@ The example skills in this repo are open source (Apache 2.0).
 
 ## Disclaimer
 
-**These skills are provided for demonstration and educational purposes only.** While some of these capabilities may be available in Claude, the implementations and behaviors you receive from Claude may differ from what is shown in these examples. These examples are meant to illustrate patterns and possibilities. Always test skills thoroughly in your own environment before relying on them for critical tasks.
+**These skills are provided for demonstration and educational purposes only.** The implementations and behaviors you receive may differ from what is shown in these examples. These examples are meant to illustrate patterns and possibilities. Always test skills thoroughly in your own environment before relying on them for critical tasks.
 
 # Installation
 
@@ -69,34 +63,18 @@ This repository includes a diverse collection of example skills demonstrating di
 - **slack-gif-creator** - Create animated GIFs optimized for Slack's size constraints
 
 ## Development & Technical
-- **artifacts-builder** - Build complex claude.ai HTML artifacts using React, Tailwind CSS, and shadcn/ui components
+- **artifacts-builder** - Build complex HTML artifacts using React, Tailwind CSS, and shadcn/ui components
 - **mcp-server** - Guide for creating high-quality MCP servers to integrate external APIs and services
 - **webapp-testing** - Test local web applications using Playwright for UI verification and debugging
 
 ## Enterprise & Communication
-- **brand-guidelines** - Apply Anthropic's official brand colors and typography to artifacts
+- **brand-guidelines** - Apply brand colors and typography to artifacts
 - **internal-comms** - Write internal communications like status reports, newsletters, and FAQs
 - **theme-factory** - Style artifacts with 10 pre-set professional themes or generate custom themes on-the-fly
 
-# Try in Claude Code, Claude.ai, and the API
-
-## Claude Code
-You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code:
-```
-/plugin marketplace add anthropics/skills
-```
-
-After installing the plugin, you can use the skill by just mentioning it. For instance, you can ask Claude Code to do something like: "use the pdf skill to extract the form fields from path/to/some-file.pdf"
-
-## Claude.ai
-
-These example skills are all already available to paid plans in Claude.ai. 
-
-To use any skill from this repository or upload custom skills, follow the instructions in [Using skills in Claude](https://support.claude.com/en/articles/12512180-using-skills-in-claude#h_a4222fa77b).
-
-## Claude API
+# Using Skills
 
-You can use Anthropic's pre-built skills, and upload custom skills, via the Claude API. See the [Skills API Quickstart](https://docs.claude.com/en/api/skills-guide#creating-a-skill) for more.
+You can use skills by mentioning them in conversation. For instance, you can ask the AI agent to do something like: "use the pdf skill to extract the form fields from path/to/some-file.pdf"
 
 # Creating a Basic Skill
 
@@ -110,7 +88,7 @@ description: A clear description of what this skill does and when to use it
 
 # My Skill Name
 
-[Add your instructions here that Claude will follow when this skill is active]
+[Add your instructions here that the AI agent will follow when this skill is active]
 
 ## Examples
 - Example usage 1
@@ -125,10 +103,10 @@ The frontmatter requires only two fields:
 - `name` - A unique identifier for your skill (lowercase, hyphens for spaces)
 - `description` - A complete description of what the skill does and when to use it
 
-The markdown content below contains the instructions, examples, and guidelines that Claude will follow. For more details, see [How to create custom skills](https://support.claude.com/en/articles/12512198-creating-custom-skills).
+The markdown content below contains the instructions, examples, and guidelines that the AI agent will follow.
 
 # Partner Skills
 
-Skills are a great way to teach Claude how to get better at using specific pieces of software. As we see awesome example skills from partners, we may highlight some of them here:
+Skills are a great way to teach the AI agent how to get better at using specific pieces of software. Here are some partner skills:
 
-- **Notion** - [Notion Skills for Claude](https://www.notion.so/notiondevs/Notion-Skills-for-Claude-28da4445d27180c7af1df7d8615723d0)
+- **Notion** - [Notion Skills](https://www.notion.so/notiondevs/Notion-Skills-28da4445d27180c7af1df7d8615723d0)

package/skills/agent-browser/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: agent-browser
 description: AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
-license: Apache-2.0
 ---
 
 # agent-browser Skill

package/skills/agent_skills_spec.md

@@ -27,7 +27,7 @@ The YAML frontmatter has 2 required properties:
     - Restricted to lowercase Unicode alphanumeric + hyphen
     - Must match the name of the directory containing the SKILL.md
 - `description` 
-    - Description of what the skill does and when Claude should use it
+    - Description of what the skill does and when the agent should use it
 
 There are 3 optional properties:
 
@@ -36,7 +36,7 @@ There are 3 optional properties:
     - We recommend keeping it short (either the name of a license or the name of a bundled license file)
 - `allowed-tools` 
     - A list of tools that are pre-approved to run
-    - Currently only supported in Claude Code
+    - Currently only supported in AI coding agents
 - `metadata`
     - A map from string keys to string values
     - Clients can use this to store additional properties not defined by the Agent Skills Spec

package/skills/backend-development/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: backend-development
 description: Build backends with Node.js, Python, Go, C#/.NET (NestJS, FastAPI, Django, ASP.NET Core). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.
-license: MIT
-version: 1.0.0
 ---
 
 # Backend Development Skill

package/skills/brainstorm/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: brainstorm
 description: Brainstorm solutions with trade-off analysis and brutal honesty. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment, design discussions.
-license: MIT
-version: 2.0.0
 ---
 
 # Brainstorming Skill
@@ -24,11 +22,11 @@ You operate by the holy trinity of software engineering: **YAGNI** (You Aren't G
 - Performance optimization and bottleneck identification
 
 ## Your Approach
-1. **Question Everything**: Use `AskUserQuestion` tool to ask probing questions to fully understand the user's request, constraints, and true objectives. Don't assume - clarify until you're 100% certain.
-2. **Brutal Honesty**: Use `AskUserQuestion` tool to provide frank, unfiltered feedback about ideas. If something is unrealistic, over-engineered, or likely to cause problems, say so directly. Your job is to prevent costly mistakes.
+1. **Question Everything**: Ask probing questions directly in your response to fully understand the user's request, constraints, and true objectives. Then stop and wait for user to answer. Don't assume - clarify until you're 100% certain.
+2. **Brutal Honesty**: Provide frank, unfiltered feedback about ideas directly in your response. If something is unrealistic, over-engineered, or likely to cause problems, say so directly. Your job is to prevent costly mistakes.
 3. **Explore Alternatives**: Always consider multiple approaches. Present 2-3 viable solutions with clear pros/cons, explaining why one might be superior.
-4. **Challenge Assumptions**: Use `AskUserQuestion` tool to question the user's initial approach. Often the best solution is different from what was originally envisioned.
-5. **Consider All Stakeholders**: Use `AskUserQuestion` tool to evaluate impact on end users, developers, operations team, and business objectives.
+4. **Challenge Assumptions**: Question the user's initial approach directly in your response. Often the best solution is different from what was originally envisioned. Wait for user input.
+5. **Consider All Stakeholders**: Ask the user about impact on end users, developers, operations team, and business objectives. Wait for response.
 
 ## Collaboration Tools
 - Consult the `planner` agent to research industry best practices and find proven solutions
@@ -41,13 +39,13 @@ You operate by the holy trinity of software engineering: **YAGNI** (You Aren't G
 
 ## Your Process
 1. **Scout Phase**: Use `scout` skill to discover relevant files and code patterns, read relevant docs in `<project-dir>/docs` directory, to understand the current state of the project
-2. **Discovery Phase**: Use `AskUserQuestion` tool to ask clarifying questions about requirements, constraints, timeline, and success criteria
+2. **Discovery Phase**: Ask clarifying questions about requirements, constraints, timeline, and success criteria directly in your response. Wait for user answers.
 3. **Research Phase**: Gather information from other agents and external sources
 4. **Analysis Phase**: Evaluate multiple approaches using your expertise and principles
-5. **Debate Phase**: Use `AskUserQuestion` tool to Present options, challenge user preferences, and work toward the optimal solution
+5. **Debate Phase**: Present options directly, challenge user preferences, and work toward the optimal solution. Wait for user input.
 6. **Consensus Phase**: Ensure alignment on the chosen approach and document decisions
 7. **Documentation Phase**: Create a comprehensive markdown summary report with the final agreed solution
-8. **Finalize Phase**: Use `AskUserQuestion` tool to ask if user wants to create a detailed implementation plan.
+8. **Finalize Phase**: Ask the user if they want to create a detailed implementation plan. Wait for response.
    - If `Yes`: Run `/plan` command with the brainstorm summary context as the argument to ensure plan continuity.
      **CRITICAL:** The invoked plan command will create `plan.md` with YAML frontmatter including `status: pending`.
    - If `No`: End the session.

package/skills/code-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: code-review
-description: Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion, for subagent reviews.
+description: Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion, for agent reviews.
 ---
 
 # Code Review
@@ -12,7 +12,7 @@ Guide proper code review practices emphasizing technical rigor, evidence-based c
 Code review requires three distinct practices:
 
 1. **Receiving feedback** - Technical evaluation over performative agreement
-2. **Requesting reviews** - Systematic review via code-reviewer subagent
+2. **Requesting reviews** - Systematic review via code-reviewer agent
 3. **Verification gates** - Evidence before any completion claims
 
 Each practice has specific triggers and protocols detailed in reference files.
@@ -38,7 +38,7 @@ Trigger when:
 
 ### Requesting Review
 Trigger when:
-- Completing tasks in subagent-driven development (after EACH task)
+- Completing tasks in agent-driven development (after EACH task)
 - Finishing major features or refactors
 - Before merging to main branch
 - Stuck and need fresh perspective
@@ -67,8 +67,8 @@ SITUATION?
 │  └─ From external reviewer? → Verify technically before implementing
 │
 ├─ Completed work
-│  ├─ Major feature/task? → Request code-reviewer subagent review
-│  └─ Before merge? → Request code-reviewer subagent review
+│  ├─ Major feature/task? → Request code-reviewer agent review
+│  └─ Before merge? → Request code-reviewer agent review
 │
 └─ About to claim status
    ├─ Have fresh verification? → State claim WITH evidence
@@ -96,13 +96,13 @@ READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT
 ## Requesting Review Protocol
 
 ### When to Request
-- After each task in subagent-driven development
+- After each task in agent-driven development
 - After major feature completion
 - Before merge to main
 
 ### Process
 1. Get git SHAs: `BASE_SHA=$(git rev-parse HEAD~1)` and `HEAD_SHA=$(git rev-parse HEAD)`
-2. Dispatch code-reviewer subagent via Task tool with: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION
+2. Delegate to code-reviewer agent with: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION
 3. Act on feedback: Fix Critical immediately, Important before proceeding, note Minor for later
 
 **Full protocol:** `references/requesting-code-review.md`
@@ -130,14 +130,14 @@ Using "should"/"probably"/"seems to", expressing satisfaction before verificatio
 
 ## Integration with Workflows
 
-- **Subagent-Driven:** Review after EACH task, verify before moving to next
+- **Agent-Driven:** Review after EACH task, verify before moving to next
 - **Pull Requests:** Verify tests pass, request code-reviewer review before merge
 - **General:** Apply verification gates before any status claims, push back on invalid feedback
 
 ## Bottom Line
 
 1. Technical rigor over social performance - No performative agreement
-2. Systematic review processes - Use code-reviewer subagent
+2. Systematic review processes - Use code-reviewer agent
 3. Evidence before claims - Verification gates always
 
 Verify. Question. Then implement. Evidence. Then claim.

package/skills/code-review/references/code-review-reception.md

@@ -27,7 +27,7 @@ WHEN receiving code review feedback:
 ## Forbidden Responses
 
 **NEVER:**
-- "You're absolutely right!" (explicit CLAUDE.md violation)
+- "You're absolutely right!" (explicit config violation)
 - "Great point!" / "Excellent feedback!" (performative)
 - "Let me implement that now" (before verification)
 

package/skills/code-review/references/requesting-code-review.md

@@ -1,18 +1,18 @@
 ---
 name: requesting-code-review
-description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent to review implementation against plan or requirements before proceeding
+description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer agent to review implementation against plan or requirements before proceeding
 ---
 
 # Requesting Code Review
 
-Dispatch code-reviewer subagent to catch issues before they cascade.
+Dispatch code-reviewer agent to catch issues before they cascade.
 
 **Core principle:** Review early, review often.
 
 ## When to Request Review
 
 **Mandatory:**
-- After each task in subagent-driven development
+- After each task in agent-driven development
 - After completing major feature
 - Before merge to main
 
@@ -29,7 +29,7 @@ BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
 HEAD_SHA=$(git rev-parse HEAD)
 ```
 
-**2. Dispatch code-reviewer subagent:**
+**2. Dispatch code-reviewer agent:**
 
 Use Task tool with `code-reviewer` type, fill template at `code-reviewer.md`
 
@@ -56,14 +56,14 @@ You: Let me request code review before proceeding.
 BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
 HEAD_SHA=$(git rev-parse HEAD)
 
-[Dispatch code-reviewer subagent]
+[Dispatch code-reviewer agent]
   WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
   PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
   BASE_SHA: a7981ec
   HEAD_SHA: 3df7661
   DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
 
-[Subagent returns]:
+[Agent returns]:
   Strengths: Clean architecture, real tests
   Issues:
     Important: Missing progress indicators
@@ -76,7 +76,7 @@ You: [Fix progress indicators]
 
 ## Integration with Workflows
 
-**Subagent-Driven Development:**
+**Agent-Driven Development:**
 - Review after EACH task
 - Catch issues before they compound
 - Fix before moving to next task

package/skills/common/api_key_helper.py

@@ -59,19 +59,19 @@ def find_api_key(skill_dir: Optional[Path] = None) -> Optional[str]:
             return api_key
 
     # Step 3: Check ./.copilot/.env
-    claude_env = project_dir / '.copilot' / '.env'
-    if claude_env.exists():
-        api_key = load_env_file(claude_env)
+    config_env = project_dir / '.copilot' / '.env'
+    if config_env.exists():
+        api_key = load_env_file(config_env)
         if api_key:
-            print(f"✓ Using API key from {claude_env}", file=sys.stderr)
+            print(f"✓ Using API key from {config_env}", file=sys.stderr)
             return api_key
 
     # Step 4: Check ./.copilot/skills/.env
-    claude_skills_env = project_dir / '.copilot' / 'skills' / '.env'
-    if claude_skills_env.exists():
-        api_key = load_env_file(claude_skills_env)
+    skills_config_env = project_dir / '.copilot' / 'skills' / '.env'
+    if skills_config_env.exists():
+        api_key = load_env_file(skills_config_env)
         if api_key:
-            print(f"✓ Using API key from {claude_skills_env}", file=sys.stderr)
+            print(f"✓ Using API key from {skills_config_env}", file=sys.stderr)
             return api_key
 
     # Step 5: Check skill directory .env

package/skills/context-engineering/SKILL.md

@@ -3,7 +3,6 @@ name: context-engineering
 description: >-
   Check context usage limits, monitor time remaining, optimize token consumption, debug context failures.
   Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
-version: 1.0.0
 ---
 
 # Context Engineering
@@ -31,7 +30,7 @@ Context engineering curates the smallest high-signal token set for LLM tasks. Th
 **IMPORTANT:**
 - Sacrifice grammar for the sake of concision.
 - Ensure token efficiency while maintaining high quality.
-- Pass these rules to subagents.
+- Pass these rules to agents.
 
 ## Quick Reference
 
@@ -88,7 +87,7 @@ The system automatically injects usage awareness via PostToolUse hook:
 
 ```xml
 <usage-awareness>
-Claude Usage Limits: 5h=45%, 7d=32%
+Usage Limits: 5h=45%, 7d=32%
 Context Window Usage: 67%
 </usage-awareness>
 ```
@@ -98,7 +97,7 @@ Context Window Usage: 67%
 - 90%: CRITICAL - immediate action needed
 
 **Data Sources:**
-- Usage limits: Anthropic OAuth API (`https://api.anthropic.com/api/oauth/usage`)
+- Usage limits: Platform OAuth API (platform-specific endpoint)
 - Context window: Statusline temp file (`/tmp/ck-context-{session_id}.json`)
 
 ## Scripts

package/skills/context-engineering/references/context-degradation.md

@@ -52,8 +52,8 @@ Predictable degradation as context grows. Not binary - a continuum.
 | Model | Degradation Onset | Severe Degradation |
 |-------|-------------------|-------------------|
 | GPT-5.2 | ~64K tokens | ~200K tokens |
-| Claude Opus 4.5 | ~100K tokens | ~180K tokens |
-| Claude Sonnet 4.5 | ~80K tokens | ~150K tokens |
+| Model (Large) | ~100K tokens | ~180K tokens |
+| Model (Medium) | ~80K tokens | ~150K tokens |
 | Gemini 3 Pro | ~500K tokens | ~800K tokens |
 
 ## Four-Bucket Mitigation

package/skills/context-engineering/references/runtime-awareness.md

@@ -1,6 +1,6 @@
 # Runtime Awareness
 
-Monitor usage limits and context window utilization in real-time to optimize Claude Code sessions.
+Monitor usage limits and context window utilization in real-time to optimize AI agent sessions.
 
 ## Overview
 
@@ -29,18 +29,18 @@ Runtime awareness provides visibility into two critical metrics:
 ### Endpoint
 
 ```
-GET https://api.anthropic.com/api/oauth/usage
+GET <platform-specific-usage-endpoint>
 ```
 
 ### Authentication
 
-Requires OAuth Bearer token with `anthropic-beta: oauth-2025-04-20` header.
+Requires OAuth Bearer token with platform-specific headers.
 
 ### Credential Locations
 
 | Platform | Method | Location |
 |----------|--------|----------|
-| macOS | Keychain | `Claude Code-credentials` |
+| macOS | Keychain | `agent-credentials` |
 | Windows | File | `%USERPROFILE%.copilot\.credentials.json` |
 | Linux | File | `~/.copilot/.credentials.json` |
 
@@ -157,7 +157,7 @@ Context: 91% [CRITICAL - compaction needed]
 | 5-Hour | Action |
 |--------|--------|
 | < 70% | Normal usage |
-| 70-90% | Reduce parallelization, delegate to subagents |
+| 70-90% | Reduce parallelization, delegate to agents |
 | > 90% | Wait for reset or use lower-tier models |
 
 | 7-Day | Action |
@@ -196,7 +196,7 @@ Context: 91% [CRITICAL - compaction needed]
 
 | Issue | Cause | Solution |
 |-------|-------|----------|
-| No usage limits shown | No OAuth token | Run `claude login` |
+| No usage limits shown | No OAuth token | Run the agent login command |
 | Stale context data | Statusline not updating | Check statusline config |
 | 401 Unauthorized | Expired token | Re-authenticate |
 | Hook not firing | Settings misconfigured | Verify PostToolUse matcher |

package/skills/cook/README.md

@@ -4,7 +4,7 @@ End-to-end feature implementation with smart intent detection.
 
 ## Installation
 
-Copy the `cook/` folder to your Claude skills directory:
+Copy the `cook/` folder to your skills directory:
 ```bash
 cp -r cook ~/.copilot/skills/
 ```
@@ -77,7 +77,7 @@ cook/
     ├── intent-detection.md            # Detection rules
     ├── workflow-steps.md              # Step definitions
     ├── review-cycle.md                # Review process
-    └── subagent-patterns.md           # Subagent usage
+    └── agent-patterns.md               # Agent usage
 ```
 
 ## Version

package/skills/cook/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: cook
 description: ALWAYS activate this skill before implementing EVERY feature, plan, or fix.
-version: 2.1.0
 ---
 
 # Cook - Smart Feature Implementation
@@ -74,9 +73,9 @@ Human review required at these checkpoints (skipped with `--auto`):
 - **Code Review:** User approval OR auto-approve (score≥9.5, 0 critical)
 - **Finalize:** project-manager AND docs-manager must complete
 
-## Required Subagents
+## Required Agents
 
-| Phase | Subagent |
+| Phase | Agent |
 |-------|----------|
 | Research | `researcher` (parallel, optional in fast) |
 | Scout | `scout` |
@@ -91,4 +90,4 @@ Human review required at these checkpoints (skipped with `--auto`):
 - `references/intent-detection.md` - Detection rules and routing logic
 - `references/workflow-steps.md` - Detailed step definitions for all modes
 - `references/review-cycle.md` - Interactive and auto review processes
-- `references/subagent-patterns.md` - Subagent invocation patterns
+- `references/agent-patterns.md` - Agent invocation patterns

package/skills/cook/references/agent-patterns.md

@@ -0,0 +1,75 @@
+# Agent Patterns
+
+Standard patterns for spawning and using agents in cook workflows.
+
+## Task Tool Pattern
+```
+Task(type="[type]", prompt="[task description]", description="[brief]")
+```
+
+## Research Phase
+```
+Task(type="researcher", prompt="Research [topic]. Report ≤150 lines.", description="Research [topic]")
+```
+- Use multiple researchers in parallel for different topics
+- Keep reports ≤150 lines with citations
+
+## Scout Phase
+```
+Task(type="scout", prompt="Find files related to [feature] in codebase", description="Scout [feature]")
+```
+- Use `/scout:ext` (preferred) or `/scout` (fallback)
+
+## Planning Phase
+```
+Task(type="planner", prompt="Create implementation plan based on reports: [reports]. Save to [path]", description="Plan [feature]")
+```
+- Input: researcher and scout reports
+- Output: `plan.md` + `phase-XX-*.md` files
+
+## UI Implementation
+```
+Task(type="ui-ux-designer", prompt="Implement [feature] UI per ./docs/design-guidelines.md", description="UI [feature]")
+```
+- For frontend work
+- Follow design guidelines
+
+## Testing
+```
+Task(type="tester", prompt="Run test suite for plan phase [phase-name]", description="Test [phase]")
+```
+- Must achieve 100% pass rate
+
+## Debugging
+```
+Task(type="debugger", prompt="Analyze failures: [details]", description="Debug [issue]")
+```
+- Use when tests fail
+- Provides root cause analysis
+
+## Code Review
+```
+Task(type="code-reviewer", prompt="Review changes for [phase]. Check security, performance, YAGNI/KISS/DRY. Return score (X/10), critical, warnings, suggestions.", description="Review [phase]")
+```
+
+## Project Management
+```
+Task(type="project-manager", prompt="Update plan status in [path]. Mark [phase] as DONE. Update roadmap.", description="Update plan")
+```
+
+## Documentation
+```
+Task(type="docs-manager", prompt="Update docs for [phase]. Changed files: [list]", description="Update docs")
+```
+
+## Git Operations
+```
+Task(type="git-manager", prompt="Stage and commit changes with conventional commit message", description="Commit changes")
+```
+
+## Parallel Execution
+```
+Task(type="fullstack-developer", prompt="Implement [phase-file] with file ownership: [files]", description="Implement phase [N]")
+```
+- Launch multiple for parallel phases
+- Include file ownership boundaries

package/skills/cook/references/review-cycle.md

@@ -24,7 +24,7 @@ LOOP:
      │  - [suggestion]                         │
      └─────────────────────────────────────────┘
 
-  3. AskUserQuestion (header: "Review & Approve"):
+  3. Ask user directly (header: "Review & Approve") — then wait for response:
      IF critical_count > 0:
        - "Fix critical issues" → fix, re-run tester, cycle++, LOOP
        - "Fix all issues" → fix all, re-run tester, cycle++, LOOP
@@ -37,7 +37,7 @@ LOOP:
 
   4. IF cycle >= 3 AND user selects fix:
      → "⚠ 3 review cycles completed. Final decision required."
-     → AskUserQuestion: "Approve with noted issues" / "Abort workflow"
+     → Ask user: "Approve with noted issues" / "Abort workflow" — wait for response
 ```
 
 ## Auto-Handling Cycle (for auto modes)

package/skills/cook/references/workflow-steps.md

@@ -25,7 +25,7 @@ All modes share core steps with mode-specific variations.
 
 ### [Review Gate 1] Post-Research (skip if auto mode)
 - Present research summary to user
-- AskUserQuestion: "Proceed to planning?" / "Request more research" / "Abort"
+- Ask user: "Proceed to planning?" / "Request more research" / "Abort" — then wait for response
 - **Auto mode:** Skip this gate
 
 ## Step 2: Planning
@@ -49,7 +49,7 @@ All modes share core steps with mode-specific variations.
 
 ### [Review Gate 2] Post-Plan (skip if auto mode)
 - Present plan overview with phases
-- AskUserQuestion: "Approve plan and start implementation?" / "Request revisions" / "Abort"
+- Ask user: "Approve plan and start implementation?" / "Request revisions" / "Abort" — then wait for response
 - **Auto mode:** Skip this gate
 
 ## Step 3: Implementation
@@ -69,7 +69,7 @@ All modes share core steps with mode-specific variations.
 
 ### [Review Gate 3] Post-Implementation (skip if auto mode)
 - Present implementation summary (files changed, key changes)
-- AskUserQuestion: "Proceed to testing?" / "Request implementation changes" / "Abort"
+- Ask user: "Proceed to testing?" / "Request implementation changes" / "Abort" — then wait for response
 - **Auto mode:** Skip this gate
 
 ## Step 4: Testing (skip if no-test mode)
@@ -84,7 +84,7 @@ All modes share core steps with mode-specific variations.
 
 ### [Review Gate 4] Post-Testing (skip if auto mode)
 - Present test results summary
-- AskUserQuestion: "Proceed to code review?" / "Request test fixes" / "Abort"
+- Ask user: "Proceed to code review?" / "Request test fixes" / "Abort" — then wait for response
 - **Auto mode:** Skip this gate
 
 ## Step 5: Code Review
@@ -108,9 +108,9 @@ All modes share core steps with mode-specific variations.
 ## Step 6: Finalize
 
 **All modes:**
-1. `project-manager` + `docs-manager` subagents in parallel
+1. `project-manager` + `docs-manager` agents in parallel
 2. Onboarding check (API keys, env vars)
-3. Auto-commit via `git-manager` subagent
+3. Auto-commit via `git-manager` agent
 
 **Auto mode:** Continue to next phase automatically
 **Others:** Ask user before next phase

package/skills/databases/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: databases
 description: Design schemas, write queries for MongoDB, PostgreSQL, SQL Server. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI, EF Core.
-license: MIT
 ---
 
 # Databases Skill

package/skills/databases/scripts/db_migrate.py

@@ -14,8 +14,8 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional
 
 # Windows UTF-8 compatibility (works for both local and global installs)
-CLAUDE_ROOT = Path(__file__).parent.parent.parent.parent
-sys.path.insert(0, str(CLAUDE_ROOT / 'scripts'))
+PROJECT_ROOT = Path(__file__).parent.parent.parent.parent
+sys.path.insert(0, str(PROJECT_ROOT / 'scripts'))
 try:
     from win_compat import ensure_utf8_stdout
     ensure_utf8_stdout()