cokit-cli 1.2.4 → 1.2.7

package/templates/repo/.github/skills/scout/SKILL.md

@@ -29,7 +29,7 @@ Fast, token-efficient codebase scouting using parallel agents to find files need
 ## Configuration
 
 Read from `$HOME/.copilot/.ck.json`:
-- `gemini.model` - Gemini model (default: `gemini-3.0-flash`)
+- `gemini.model` - Gemini model (default: `gemini-3-flash-preview`)
 
 ## Workflow
 
@@ -43,21 +43,33 @@ Read from `$HOME/.copilot/.ck.json`:
 - Assign each agent specific directories or patterns
 - Ensure no overlap, maximize coverage
 
-### 3. Spawn Parallel Agents
+### 3. Register Scout Tasks
+
+**Skip this step if agent count <= 2.**
+
+- Check for existing scout tasks in the current session to avoid duplicates.
+- Create a markdown checklist — one entry per agent — including scope metadata (directories, patterns assigned).
+- Example checklist entry: `- [ ] Agent 1: src/api/*, src/models/* — searching for auth-related files`
+- Reference: `references/task-management-scouting.md` for checklist format and metadata fields.
+
+### 4. Spawn Parallel Agents
+
 Load appropriate reference based on decision tree:
 - **Internal (Default):** `references/internal-scouting.md` (search agents)
 - **External:** `references/external-scouting.md` (Gemini/OpenCode)
 
 **Notes:**
-- Prompt detailed instructions for each agent with exact directories or files it should read
-- Remember that each agent has less than 200K tokens of context window
-- Amount of agents to-be-spawned depends on the current system resources available and amount of files to be scanned
-- Each agent must return a detailed summary report to a main agent
-
-### 4. Collect Results
-- Timeout: 3 minutes per agent (skip non-responders)
-- Aggregate findings into single report
-- List unresolved questions at end
+- Update each task to in_progress before spawning its agent.
+- Prompt detailed instructions for each agent with exact directories or files it should read.
+- Remember that each agent has less than 200K tokens of context window.
+- Amount of agents to-be-spawned depends on the current system resources available and amount of files to be scanned.
+- Each agent must return a detailed summary report to a main agent.
+
+### 5. Collect Results
+- Timeout: 3 minutes per agent (skip non-responders).
+- Update completed tasks to done; log timed-out agents in the report under "Unresolved Questions".
+- Aggregate findings into single report.
+- List unresolved questions at end.
 
 ## Report Format
 
@@ -76,3 +88,4 @@ Load appropriate reference based on decision tree:
 
 - `references/internal-scouting.md` - Using search agents
 - `references/external-scouting.md` - Using Gemini/OpenCode CLI
+- `references/task-management-scouting.md` - Checklist format and scope metadata for scout tasks

package/templates/repo/.github/skills/web-testing/SKILL.md

@@ -1,23 +1,52 @@
 ---
 name: web-testing
-description: Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
+description: Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Multi-language support (JS/TS, Python, Go, Rust, Flutter). Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
 ---
 
 # Web Testing Skill
 
-Comprehensive web testing: unit, integration, E2E, load, security, visual regression, accessibility.
+Comprehensive testing: unit, integration, E2E, load, security, visual regression, accessibility. Multi-language workflow orchestration with structured QA reporting.
+
+## Core Principle
+
+**NEVER IGNORE FAILING TESTS.** Fix root causes, not symptoms. No mocks/cheats/tricks to pass builds.
 
 ## Quick Start
 
 ```bash
+# JavaScript/TypeScript
 npx vitest run                    # Unit tests
 npx playwright test               # E2E tests
-npx playwright test --ui          # E2E with UI
+npm run test:coverage             # Coverage
+
+# Python
+pytest --cov=src                  # Unit + coverage
+
+# Go / Rust / Flutter
+go test ./... -cover              # Go
+cargo test                        # Rust
+flutter test --coverage           # Flutter
+
+# Web Quality
 k6 run load-test.js               # Load tests
-npx @axe-core/cli https://example.com  # Accessibility
-npx lighthouse https://example.com     # Performance
+npx @axe-core/cli https://...    # Accessibility
+npx lighthouse https://...       # Performance
 ```
 
+## Workflows
+
+Three orchestrated workflows — load the relevant reference when needed:
+
+| Workflow | Reference | Use When |
+|----------|-----------|----------|
+| Code Testing | `./references/test-execution-workflow.md` | Running unit/integration/e2e, checking coverage, validating builds |
+| UI Testing | `./references/ui-testing-workflow.md` | Visual regression, responsive checks, accessibility audits, form automation |
+| Report Format | `./references/report-format.md` | Generating structured QA summary reports |
+
+**Code Testing Process:** Identify scope → Pre-flight checks → Execute tests → Analyze results → Coverage analysis → Build verification → Report
+
+**UI Testing Process:** Discovery → Visual capture → Console errors → Network validation → Responsive testing → Form testing → Performance metrics → Report
+
 ## Testing Strategy (Choose Your Model)
 
 | Model | Structure | Best For |
@@ -26,10 +55,15 @@ npx lighthouse https://example.com     # Performance
 | Trophy | Integration-heavy | Modern SPAs |
 | Honeycomb | Contract-centric | Microservices |
 
-→ `./references/testing-pyramid-strategy.md`
+> `./references/testing-pyramid-strategy.md`
 
 ## Reference Documentation
 
+### Workflows & Reports
+- `./references/test-execution-workflow.md` - Orchestrated code testing (multi-language)
+- `./references/ui-testing-workflow.md` - Browser-based visual testing via `agent-browser`
+- `./references/report-format.md` - Structured QA report template
+
 ### Core Testing
 - `./references/unit-integration-testing.md` - Vitest, browser mode, AAA
 - `./references/e2e-testing-playwright.md` - Fixtures, sharding, selectors
@@ -64,6 +98,17 @@ npx lighthouse https://example.com     # Performance
 - `./references/pre-release-checklist.md` - Complete release checklist
 - `./references/functional-testing-checklist.md` - Feature testing
 
+## Tools Integration
+
+- **Test runners**: Vitest, Jest, Mocha, pytest, go test, cargo test, flutter test
+- **Coverage**: Istanbul/c8/nyc, pytest-cov, go cover
+- **E2E**: Playwright (multi-browser, sharding)
+- **Load**: k6
+- **Browser**: `agent-browser` skill for UI testing
+- **Analysis**: `ai-multimodal` skill (if available) for screenshot analysis
+- **Debugging**: `debug` skill when tests reveal bugs
+- **Thinking**: `sequential-thinking` skill for complex test failure analysis
+
 ## Scripts
 
 ### Initialize Playwright Project
@@ -92,3 +137,12 @@ jobs:
       - run: npm run test:a11y      # Accessibility
       - run: npx lhci autorun       # Performance
 ```
+
+## Quality Standards
+
+- All critical paths must have test coverage
+- Validate happy path AND error scenarios
+- Ensure test isolation — no interdependencies
+- Tests must be deterministic and reproducible
+- Clean up test data after execution
+- Coverage: 80%+ lines, 70%+ branches minimum

package/templates/repo/.github/skills/web-testing/references/report-format.md

@@ -0,0 +1,57 @@
+# Test Report Format
+
+Structured QA report template. Sacrifice grammar for concision.
+
+## Template
+
+```markdown
+# Test Report — {date} — {scope}
+
+## Test Results Overview
+- **Total**: X tests
+- **Passed**: X | **Failed**: X | **Skipped**: X
+- **Duration**: Xs
+
+## Coverage Metrics
+| Metric   | Value | Threshold | Status |
+|----------|-------|-----------|--------|
+| Lines    | X%    | 80%       | PASS/FAIL |
+| Branches | X%    | 70%       | PASS/FAIL |
+| Functions| X%    | 80%       | PASS/FAIL |
+
+## Failed Tests
+### `test/path/file.test.ts` — TestName
+- **Error**: Error message
+- **Stack**: Relevant stack trace (truncated)
+- **Cause**: Brief root cause analysis
+- **Fix**: Suggested resolution
+
+## UI Test Results (if applicable)
+- **Pages tested**: X
+- **Screenshots**: ./screenshots/
+- **Console errors**: none | [list]
+- **Responsive**: checked at [viewports] | skipped
+- **Performance**: LCP Xs, FID Xms, CLS X
+
+## Build Status
+- **Build**: PASS/FAIL
+- **Warnings**: none | [list]
+- **Dependencies**: all resolved | [issues]
+
+## Critical Issues
+1. [Blocking issue description + impact]
+
+## Recommendations
+1. [Actionable improvement with priority]
+
+## Unresolved Questions
+- [Any open questions, if any]
+```
+
+## Guidelines
+
+- Include ALL failed tests with error messages — don't summarize away details
+- Coverage: highlight specific uncovered files/functions, not just percentages
+- Screenshots: embed paths directly in report for easy access
+- Recommendations: prioritize by impact (critical > high > medium > low)
+- Keep report under 200 lines — split into sections if larger scope needed

package/templates/repo/.github/skills/web-testing/references/test-execution-workflow.md

@@ -0,0 +1,118 @@
+# Test Execution Workflow
+
+Orchestrated workflow for running code-level tests across any language/framework.
+
+## Step 1: Identify Scope
+
+Determine what to test based on recent changes:
+
+| Change Type | Test Strategy |
+|-------------|---------------|
+| New feature | Full test suite + new test cases |
+| Bug fix | Regression tests + targeted fix validation |
+| Refactor | Existing test suite (no new tests unless gaps found) |
+| Coverage check | Full suite with coverage flags |
+
+## Step 2: Pre-flight Checks
+
+Run syntax/type checks before tests to catch compile errors early:
+
+```bash
+# JavaScript/TypeScript
+npx tsc --noEmit
+npx eslint .
+
+# Python
+python -m py_compile file.py
+flake8 .
+
+# Flutter
+flutter analyze
+
+# Go
+go vet ./...
+
+# Rust
+cargo check
+```
+
+## Step 3: Execute Tests
+
+### JavaScript/TypeScript
+```bash
+npm test                      # project default
+npx vitest run                # Vitest
+npx jest --coverage           # Jest with coverage
+bun test                      # Bun
+```
+
+### Python
+```bash
+pytest                                          # basic
+pytest --cov=src --cov-report=term-missing      # with coverage
+python -m unittest discover                     # unittest
+```
+
+### Go
+```bash
+go test ./... -cover          # with coverage
+go test ./... -race           # race condition detection
+```
+
+### Rust
+```bash
+cargo test
+cargo test -- --nocapture     # show stdout
+```
+
+### Flutter
+```bash
+flutter test --coverage
+```
+
+## Step 4: Analyze Results
+
+Focus on:
+1. **Failing tests** — read error messages and stack traces carefully
+2. **Flaky tests** — pass/fail intermittently → race conditions or state leaks
+3. **Slow tests** — >5s per test is suspicious, identify bottlenecks
+4. **Skipped tests** — ensure skips are intentional, not hiding failures
+
+## Step 5: Coverage Analysis
+
+Thresholds:
+- **80%+** line coverage — standard minimum
+- **70%+** branch coverage — acceptable for most projects
+- Focus on critical paths: auth, payment, data mutations
+
+Identify gaps:
+- Uncovered error handlers
+- Missing edge case branches
+- Untested utility functions
+
+## Step 6: Build Verification
+
+```bash
+npm run build                 # JS/TS production build
+python setup.py build         # Python
+go build ./...                # Go
+cargo build --release         # Rust
+flutter build                 # Flutter
+```
+
+Check for:
+- Build warnings or deprecation notices
+- Unresolved dependencies
+- Production config correctness
+
+## Quality Checklist
+
+- [ ] All tests pass (zero failures)
+- [ ] Coverage meets project threshold
+- [ ] No flaky tests detected
+- [ ] Build completes without errors
+- [ ] Error scenarios tested
+- [ ] Test isolation verified (no shared state)
+- [ ] Test data cleaned up after execution
+- [ ] Mocks/stubs properly configured
+- [ ] Environment variables correctly set

package/templates/repo/.github/skills/web-testing/references/ui-testing-workflow.md

@@ -0,0 +1,97 @@
+# UI Testing Workflow
+
+Browser-based visual testing using `agent-browser` skill. Covers screenshots, responsive checks, accessibility, form automation, console errors.
+
+## Prerequisites
+
+Ensure `agent-browser` skill is available. For screenshot analysis, use `ai-multimodal` skill (if available).
+
+## Step 1: Discovery
+
+Browse target URL, discover pages, components, endpoints:
+
+```bash
+# Navigate and capture initial state
+# Use agent-browser skill to browse http://localhost:3000
+# Capture ARIA snapshot for accessibility baseline
+```
+
+## Step 2: Visual Capture
+
+```bash
+# Full page screenshot
+# Screenshot http://localhost:3000 → ./screenshots/home.png (full-page)
+
+# Specific component
+# Screenshot selector ".main-content" → ./screenshots/main.png
+```
+
+## Step 3: Console Error Check
+
+Capture JavaScript errors for 5 seconds on each page.
+
+- Zero errors = pass
+- Any errors = investigate before proceeding
+- Check for: uncaught exceptions, failed promises, deprecation warnings
+
+## Step 4: Network Validation
+
+Check for failed API calls:
+- Filter responses with status >= 400
+- Identify CORS issues, missing endpoints, auth failures
+- Validate API response times
+
+## Step 5: Responsive Testing
+
+Capture at key breakpoints:
+
+| Viewport | Size | Device |
+|----------|------|--------|
+| Desktop | 1920x1080 | Standard monitor |
+| Tablet | 768x1024 | iPad |
+| Mobile | 375x812 | iPhone |
+
+For each viewport:
+1. Resize browser window
+2. Capture full-page screenshot
+3. Check for layout breakage, overflow, hidden elements
+
+## Step 6: Form & Interaction Testing
+
+Test interactive elements:
+1. Fill form fields with valid data
+2. Submit and verify success state
+3. Fill with invalid data and verify error messages
+4. Test keyboard navigation (Tab, Enter, Escape)
+5. Capture screenshots of each state
+
+## Step 7: Performance Metrics
+
+Collect Core Web Vitals:
+- **LCP** (Largest Contentful Paint): < 2.5s
+- **FID/INP** (First Input Delay / Interaction to Next Paint): < 200ms
+- **CLS** (Cumulative Layout Shift): < 0.1
+
+## Authentication for Protected Routes
+
+For pages behind auth:
+
+| Method | Use Case |
+|--------|----------|
+| Cookie injection | Session-based auth |
+| Bearer token | API/JWT auth |
+| localStorage | SPA token storage |
+
+After injection, browser session persists for subsequent tests.
+
+## Screenshot Analysis
+
+Use `ai-multimodal` skill (if available) to analyze captured screenshots for:
+- Layout correctness
+- Visual regressions vs baseline
+- Missing elements or broken styling
+- Accessibility issues (contrast, text size)
+
+## Cleanup
+
+Close browser sessions when testing completes to free resources.

package/prompts/ck-journal.prompt.md

@@ -1,19 +0,0 @@
----
-agent: 'agent'
-description: 'Write journal entries from recent changes and memories'
----
-
-Use the `journal-writer` agent to explore the memories and recent code changes, and write some journal entries.
-Journal entries should be concise and focused on the most important events, key changes, impacts, and decisions.
-Keep journal entries in the `./docs/journals/` directory.
-
----
-
-## Suggested Next Steps
-
-| Command | Description |
-|---------|-------------|
-| `/ck-brainstorm` | Explore ideas |
-| `/ck-plan` | Create plan |
-| `/ck-fix` | Analyze and fix issues |
-| `/ck-spec-specify` | Write detailed feature spec |

package/prompts/ck-preview.prompt.md

@@ -1,77 +0,0 @@
----
-agent: 'agent'
-description: 'Preview markdown files, plan directories, or plans collection'
-argument-hint: 'Path to markdown file or directory'
-tools: ['execute/runInTerminal', 'execute/getTerminalOutput']
----
-
-Universal viewer - pass ANY path and see it rendered nicely.
-
-## Usage
-
-- `/ck-preview <file.md>` - View markdown file in novel-reader UI
-- `/ck-preview <directory/>` - Browse directory contents
-- `/ck-preview --stop` - Stop running server
-
-## Examples
-
-```bash
-/ck-preview plans/my-plan/ck-plan.md     # View markdown file
-/ck-preview plans/                    # Browse plans directory
-/ck-preview docs/                     # Browse docs directory
-/ck-preview any/path/to/file.md      # View any markdown file
-/ck-preview any/path/                 # Browse any directory
-```
-
-## Execution
-
-Run the server using `#tool:execute/runInTerminal`. The skill is located at `$HOME/.copilot/skills/markdown-novel-viewer/`.
-
-### Stop Server
-
-If `--stop` flag is provided:
-
-```bash
-node $HOME/.copilot/skills/markdown-novel-viewer/scripts/server.cjs --stop
-```
-
-### Start Server
-
-Otherwise, run the `markdown-novel-viewer` server with `--foreground` flag:
-
-```bash
-# Determine if path is file or directory
-INPUT_PATH="${input}"
-if [[ -d "$INPUT_PATH" ]]; then
-  # Directory mode - browse
-  node $HOME/.copilot/skills/markdown-novel-viewer/scripts/server.cjs \
-    --dir "$INPUT_PATH" \
-    --host 0.0.0.0 \
-    --open \
-    --foreground
-else
-  # File mode - view markdown
-  node $HOME/.copilot/skills/markdown-novel-viewer/scripts/server.cjs \
-    --file "$INPUT_PATH" \
-    --host 0.0.0.0 \
-    --open \
-    --foreground
-fi
-```
-
-After starting, parse the JSON output (e.g., `{"success":true,"url":"http://localhost:3456/view?file=...","networkUrl":"http://192.168.1.x:3456/view?file=..."}`) and report:
-- Local URL for browser access
-- Network URL for remote device access (if available)
-- Inform user that server is now running in the terminal; stop it by running the stop command
-
-**CRITICAL:** MUST display the FULL URL including path and query string (e.g., `http://localhost:3456/view?file=/path/to/file.md`). NEVER truncate to just `host:port` (e.g., `http://localhost:3456`). The full URL is required for direct file access.
-
----
-
-## Suggested Next Steps
-
-| Command | Description |
-|---------|-------------|
-| `/ck-brainstorm` | Explore ideas |
-| `/ck-plan` | Create plan |
-| `/ck-spec-specify` | Write detailed feature spec |

package/templates/repo/.github/prompts/ck-journal.prompt.md

@@ -1,19 +0,0 @@
----
-agent: 'agent'
-description: 'Write journal entries from recent changes and memories'
----
-
-Use the `journal-writer` agent to explore the memories and recent code changes, and write some journal entries.
-Journal entries should be concise and focused on the most important events, key changes, impacts, and decisions.
-Keep journal entries in the `./docs/journals/` directory.
-
----
-
-## Suggested Next Steps
-
-| Command | Description |
-|---------|-------------|
-| `/ck-brainstorm` | Explore ideas |
-| `/ck-plan` | Create plan |
-| `/ck-fix` | Analyze and fix issues |
-| `/ck-spec-specify` | Write detailed feature spec |

package/templates/repo/.github/prompts/ck-preview.prompt.md

@@ -1,77 +0,0 @@
----
-agent: 'agent'
-description: 'Preview markdown files, plan directories, or plans collection'
-argument-hint: 'Path to markdown file or directory'
-tools: ['execute/runInTerminal', 'execute/getTerminalOutput']
----
-
-Universal viewer - pass ANY path and see it rendered nicely.
-
-## Usage
-
-- `/ck-preview <file.md>` - View markdown file in novel-reader UI
-- `/ck-preview <directory/>` - Browse directory contents
-- `/ck-preview --stop` - Stop running server
-
-## Examples
-
-```bash
-/ck-preview plans/my-plan/ck-plan.md     # View markdown file
-/ck-preview plans/                    # Browse plans directory
-/ck-preview docs/                     # Browse docs directory
-/ck-preview any/path/to/file.md      # View any markdown file
-/ck-preview any/path/                 # Browse any directory
-```
-
-## Execution
-
-Run the server using `#tool:execute/runInTerminal`. The skill is located at `$HOME/.copilot/skills/markdown-novel-viewer/`.
-
-### Stop Server
-
-If `--stop` flag is provided:
-
-```bash
-node $HOME/.copilot/skills/markdown-novel-viewer/scripts/server.cjs --stop
-```
-
-### Start Server
-
-Otherwise, run the `markdown-novel-viewer` server with `--foreground` flag:
-
-```bash
-# Determine if path is file or directory
-INPUT_PATH="${input}"
-if [[ -d "$INPUT_PATH" ]]; then
-  # Directory mode - browse
-  node $HOME/.copilot/skills/markdown-novel-viewer/scripts/server.cjs \
-    --dir "$INPUT_PATH" \
-    --host 0.0.0.0 \
-    --open \
-    --foreground
-else
-  # File mode - view markdown
-  node $HOME/.copilot/skills/markdown-novel-viewer/scripts/server.cjs \
-    --file "$INPUT_PATH" \
-    --host 0.0.0.0 \
-    --open \
-    --foreground
-fi
-```
-
-After starting, parse the JSON output (e.g., `{"success":true,"url":"http://localhost:3456/view?file=...","networkUrl":"http://192.168.1.x:3456/view?file=..."}`) and report:
-- Local URL for browser access
-- Network URL for remote device access (if available)
-- Inform user that server is now running in the terminal; stop it by running the stop command
-
-**CRITICAL:** MUST display the FULL URL including path and query string (e.g., `http://localhost:3456/view?file=/path/to/file.md`). NEVER truncate to just `host:port` (e.g., `http://localhost:3456`). The full URL is required for direct file access.
-
----
-
-## Suggested Next Steps
-
-| Command | Description |
-|---------|-------------|
-| `/ck-brainstorm` | Explore ideas |
-| `/ck-plan` | Create plan |
-| `/ck-spec-specify` | Write detailed feature spec |