cokit-cli 1.3.0 → 1.4.0

package/skills/ck-sequential-thinking/SKILL.md

@@ -0,0 +1,94 @@
+---
+name: ck-sequential-thinking
+description: Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.
+license: MIT
+argument-hint: "[problem to analyze step-by-step]"
+---
+
+# Sequential Thinking
+
+Structured problem-solving via manageable, reflective thought sequences with dynamic adjustment.
+
+## When to Apply
+
+- Complex problem decomposition
+- Adaptive planning with revision capability
+- Analysis needing course correction
+- Problems with unclear/emerging scope
+- Multi-step solutions requiring context maintenance
+- Hypothesis-driven investigation/debugging
+
+## Core Process
+
+### 1. Start with Loose Estimate
+```
+Thought 1/5: [Initial analysis]
+```
+Adjust dynamically as understanding evolves.
+
+### 2. Structure Each Thought
+- Build on previous context explicitly
+- Address one aspect per thought
+- State assumptions, uncertainties, realizations
+- Signal what next thought should address
+
+### 3. Apply Dynamic Adjustment
+- **Expand**: More complexity discovered → increase total
+- **Contract**: Simpler than expected → decrease total
+- **Revise**: New insight invalidates previous → mark revision
+- **Branch**: Multiple approaches → explore alternatives
+
+### 4. Use Revision When Needed
+```
+Thought 5/8 [REVISION of Thought 2]: [Corrected understanding]
+- Original: [What was stated]
+- Why revised: [New insight]
+- Impact: [What changes]
+```
+
+### 5. Branch for Alternatives
+```
+Thought 4/7 [BRANCH A from Thought 2]: [Approach A]
+Thought 4/7 [BRANCH B from Thought 2]: [Approach B]
+```
+Compare explicitly, converge with decision rationale.
+
+### 6. Generate & Verify Hypotheses
+```
+Thought 6/9 [HYPOTHESIS]: [Proposed solution]
+Thought 7/9 [VERIFICATION]: [Test results]
+```
+Iterate until hypothesis verified.
+
+### 7. Complete Only When Ready
+Mark final: `Thought N/N [FINAL]`
+
+Complete when:
+- Solution verified
+- All critical aspects addressed
+- Confidence achieved
+- No outstanding uncertainties
+
+## Application Modes
+
+**Explicit**: Use visible thought markers when complexity warrants visible reasoning or user requests breakdown.
+
+**Implicit**: Apply methodology internally for routine problem-solving where thinking aids accuracy without cluttering response.
+
+## Scripts (Optional)
+
+Optional scripts for deterministic validation/tracking:
+- `scripts/process-thought.js` - Validate & track thoughts with history
+- `scripts/format-thought.js` - Format for display (box/markdown/simple)
+
+See README.md for usage examples. Use when validation/persistence needed; otherwise apply methodology directly.
+
+## References
+
+Load when deeper understanding needed:
+- `references/core-patterns.md` - Revision & branching patterns
+- `references/examples-api.md` - API design example
+- `references/examples-debug.md` - Debugging example
+- `references/examples-architecture.md` - Architecture decision example
+- `references/advanced-techniques.md` - Spiral refinement, hypothesis testing, convergence
+- `references/advanced-strategies.md` - Uncertainty, revision cascades, meta-thinking

package/skills/ck-ship/SKILL.md

@@ -0,0 +1,116 @@
+---
+name: ck-ship
+description: "Ship pipeline: merge main, test, review, commit, push, PR. Single command from feature branch to PR URL. Use for shipping official releases to main/master or beta releases to dev/beta branches."
+argument-hint: "[official|beta] [--skip-tests] [--skip-review] [--skip-journal] [--skip-docs] [--dry-run]"
+license: MIT
+---
+
+# Ship: Unified Ship Pipeline
+
+Single command to ship a feature branch. Fully automated — only stops for test failures, critical review issues, or major version bumps.
+
+**Inspired by:** gstack `/ship` by Garry Tan. Adapted for framework-agnostic, multi-language support.
+
+## Arguments
+
+| Flag | Effect |
+|------|--------|
+| `official` | Ship to default branch (main/master). Full pipeline with docs + journal |
+| `beta` | Ship to dev/beta branch. Lighter pipeline, skip docs update |
+| (none) | Auto-detect: if base branch is main/master → official, else → beta |
+| `--skip-tests` | Skip test step (use when tests already passed) |
+| `--skip-review` | Skip pre-landing review step |
+| `--skip-journal` | Skip journal writing step |
+| `--skip-docs` | Skip docs update step |
+| `--dry-run` | Show what would happen without executing |
+
+## Ship Mode Detection
+
+```
+If argument = "official" → target = main/master (auto-detect default branch)
+If argument = "beta"     → target = dev/beta (auto-detect dev branch)
+If no argument           → infer from current branch naming:
+  - feature/* hotfix/* bugfix/* → official (target main)
+  - dev/* beta/* experiment/*  → beta (target dev/beta)
+  - unclear                    → asking the user
+```
+
+## When to Stop (blocking)
+
+- On target branch already → abort
+- Merge conflicts that can't be auto-resolved → stop, show conflicts
+- Test failures → stop, show failures
+- Critical review issues → asking the user per issue
+- Major/minor version bump needed → asking the user
+
+## When NOT to Stop
+
+- Uncommitted changes → always include them
+- Patch version bump → auto-decide
+- Changelog content → auto-generate
+- Commit message → auto-compose
+- No version file → skip version step silently
+- No changelog → skip changelog step silently
+
+## Pipeline
+
+```
+Step 1:  Pre-flight      → Branch check, mode detection, status, diff analysis
+Step 2:  Link Issues      → Find/create related GitHub issues
+Step 3:  Merge target     → Fetch + merge origin/<target-branch>
+Step 4:  Run tests        → Auto-detect test runner, run, check results
+Step 5:  Review           → Two-pass checklist review (critical + informational)
+Step 6:  Version bump     → Auto-detect version file, bump patch/minor
+Step 7:  Changelog        → Auto-generate from commits + diff
+Step 8:  Journal          → Write technical journal via /ck-journal
+Step 9:  Docs update      → Update project docs via /ck-docs update (official only)
+Step 10: Commit           → Conventional commit with version/changelog
+Step 11: Push             → git push -u origin <branch>
+Step 12: Create PR        → gh pr create with structured body + linked issues
+```
+
+**Detailed steps:** Load `references/ship-workflow.md`
+**Auto-detection:** Load `references/auto-detect.md`
+**PR template:** Load `references/pr-template.md`
+
+## Token Efficiency Rules
+
+- Steps 4 (tests) and 5 (review): delegate to `ck-tester` and `ck-code-reviewer` subagents — don't inline
+- Steps 8 (journal) and 9 (docs): run in **background** — don't block pipeline
+- Step 2 (issues): use single `gh` command batch — avoid multiple API calls
+- Skip steps early via flags to save tokens on unnecessary work
+- Beta mode auto-skips: docs update (Step 9)
+- Capture step outputs inline — don't re-read files already in context
+
+## Quick Start
+
+User says `/ck-ship` → run full pipeline → output PR URL.
+User says `/ck-ship beta` → ship to dev branch with lighter pipeline.
+User says `/ck-ship official` → ship to main with full docs + journal.
+
+## Output Format
+
+```
+✓ Pre-flight: branch feature/foo, 5 commits, +200/-50 lines (mode: official)
+✓ Issues: linked #42, created #43
+✓ Merged: origin/main (up to date)
+✓ Tests: 42 passed, 0 failed
+✓ Review: 0 critical, 2 informational
+✓ Version: 1.2.3 → 1.2.4
+✓ Changelog: updated
+✓ Journal: written (background)
+✓ Docs: updated (background)
+✓ Committed: feat(auth): add OAuth2 login flow
+✓ Pushed: origin/feature/foo
+✓ PR: https://github.com/org/repo/pull/123 (linked: #42, #43)
+```
+
+## Important Rules
+
+- **Never skip tests** (unless `--skip-tests`). If tests fail, stop.
+- **Never force push.** Regular `git push` only.
+- **Never ask for confirmation** except for critical review issues and major/minor version bumps.
+- **Auto-detect everything.** Test runner, version file, changelog format, target branch — detect from project files.
+- **Framework-agnostic.** Works for Node, Python, Rust, Go, Ruby, Java, or any project with a test command.
+- **Subagent delegation.** Use `ck-tester` for tests, `ck-code-reviewer` for review, `journal-writer` for journal, `ck-docs-manager` for docs. Don't inline.
+- **Background tasks.** Journal and docs run in background to not block the pipeline.

package/skills/ck-ship/references/ship-workflow.md

@@ -0,0 +1,241 @@
+# Ship Workflow — Detailed Steps
+
+## Step 1: Pre-flight
+
+1. Check current branch: `git branch --show-current`
+   - If on target branch (main/master/dev): **ABORT** — "Ship from a feature branch, not the target branch."
+2. Determine ship mode from arguments:
+   - `official` → target = auto-detect default branch (main/master)
+   - `beta` → target = auto-detect dev branch (dev/beta/develop)
+   - No argument → infer from branch name:
+     - `feature/* hotfix/* bugfix/*` → official
+     - `dev/* beta/* experiment/*` → beta
+     - Unclear → asking the user with options: "Official (main)", "Beta (dev)"
+3. Auto-detect target branch:
+   ```bash
+   # For official: detect default branch
+   git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@'
+   # Fallback
+   git rev-parse --verify origin/main 2>/dev/null && echo "main" || echo "master"
+
+   # For beta: detect dev branch
+   for b in dev beta develop; do
+     git rev-parse --verify origin/$b 2>/dev/null && echo "$b" && break
+   done
+   ```
+4. Run `git status` (never use `-uall`). Uncommitted changes are always included.
+5. Run `git diff <target>...HEAD --stat` and `git log <target>..HEAD --oneline` to understand what's being shipped.
+6. If `--dry-run`: output what would happen at each step and stop here.
+
+## Step 2: Link Issues
+
+Find or create related GitHub issues for traceability.
+
+1. Search for related open issues by keywords from branch name and commit messages:
+   ```bash
+   # Extract keywords from branch name
+   BRANCH=$(git branch --show-current)
+   KEYWORDS=$(echo "$BRANCH" | sed 's/[^a-zA-Z0-9]/ /g' | tr '[:upper:]' '[:lower:]')
+
+   # Search existing issues
+   gh issue list --state open --limit 10 --search "$KEYWORDS"
+   ```
+
+2. Also check if any issues are referenced in commit messages:
+   ```bash
+   git log <target>..HEAD --oneline | grep -oE '#[0-9]+' | sort -u
+   ```
+
+3. **If related issues found:** Note issue numbers for PR linking.
+
+4. **If NO related issues found:** Create a new issue with structured format:
+   ```bash
+   gh issue create --title "<type>: <summary from commits>" --body "$(cat <<'EOF'
+   ## Problem Statement
+   <infer from diff and commit messages>
+
+   ## Proposal
+   <summarize the implementation approach>
+
+   ## How It Works
+   <describe key changes with bullet points>
+
+   ### Architecture
+   ```
+   <ASCII diagram of component interactions>
+   ```
+
+   ## Challenges
+   - <potential edge cases or risks>
+
+   ## Plan & Phases
+   - [x] Implementation complete
+   - [x] Tests passing
+   - [ ] Code review approved
+   - [ ] Merged to <target>
+
+   ## Human Review Tasks
+   - [ ] Verify business logic correctness
+   - [ ] Check for edge cases not covered by tests
+   - [ ] Validate UX/API contract changes (if any)
+   EOF
+   )"
+   ```
+
+5. Store issue numbers for Step 12 (PR creation).
+
+## Step 3: Merge target branch
+
+Fetch and merge so tests run against the merged state:
+
+```bash
+git fetch origin <target> && git merge origin/<target> --no-edit
+```
+
+- **If merge conflicts:** Try auto-resolve simple ones (lockfiles, version files). For complex conflicts, **STOP** and show them.
+- **If already up to date:** Continue silently.
+
+## Step 4: Run Tests
+
+**Skip if:** `--skip-tests` flag.
+
+1. Auto-detect test command (see `auto-detect.md`)
+2. Delegate to `ck-tester` subagent — don't inline test execution
+3. Check pass/fail from agent result
+
+- **If any test fails:** Show failures and **STOP**. Do not proceed.
+- **If all pass:** Note counts briefly and continue.
+- **If no test runner detected:** Use asking the user — "No test runner detected. Skip tests or provide command?"
+
+## Step 5: Pre-Landing Review
+
+**Skip if:** `--skip-review` flag.
+
+1. Run `git diff origin/<target>` to get the full diff
+2. Delegate to `ck-code-reviewer` subagent with the diff
+3. Two-pass model:
+   - **Pass 1 (CRITICAL):** Security, injection, race conditions, auth bypass
+   - **Pass 2 (INFORMATIONAL):** Dead code, magic numbers, test gaps, style
+
+4. **Output findings:**
+   ```
+   Pre-Landing Review: N issues (X critical, Y informational)
+   ```
+
+5. **If critical issues found:** For EACH critical issue, ask the user:
+   - Problem description with `file:line`
+   - Recommended fix
+   - Options: A) Fix now (recommended), B) Acknowledge and ship, C) False positive — skip
+
+6. **If user chose Fix (A):** Apply fixes, commit fixed files, then **re-run tests** (Step 4) before continuing.
+7. **If only informational:** Include in PR body, continue.
+8. **If no issues:** Output "No issues found." and continue.
+
+## Step 6: Version Bump (conditional)
+
+1. Auto-detect version source (see `auto-detect.md`)
+2. If no version file found: **skip silently**
+3. Auto-decide bump level from diff size:
+   - **< 50 lines:** patch bump
+   - **50+ lines:** patch bump (default safe choice)
+   - **Major feature or breaking change:** Use asking the user — "This looks like a significant change. Bump minor or patch?"
+4. For beta mode: use prerelease suffix (e.g., `1.2.4-beta.1`)
+5. Write new version to detected file
+
+## Step 7: Changelog (conditional)
+
+1. Check for CHANGELOG.md or CHANGES.md
+2. If not found: **skip silently**
+3. Auto-generate entry from ALL commits on branch:
+   - `git log <target>..HEAD --oneline` for commit list
+   - `git diff <target>...HEAD` for full diff context
+4. Categorize into: Added, Changed, Fixed, Removed
+5. Insert after file header, dated today
+6. Format: `## [X.Y.Z] - YYYY-MM-DD`
+
+**Do NOT ask user to describe changes.** Infer from diff and commits.
+
+## Step 8: Journal (background)
+
+**Skip if:** `--skip-journal` flag.
+
+Write a technical journal entry capturing this ship session. Run as **background task** to not block pipeline.
+
+1. Invoke `/ck-journal` skill via `journal-writer` subagent in background:
+   - Topic: summary of shipped changes (from commit messages + diff stats)
+   - Include: what was shipped, key decisions, technical challenges encountered
+   - Output: saved to `./docs/journals/` directory
+2. Don't wait for completion — continue to next step immediately.
+
+## Step 9: Docs Update (conditional, background)
+
+**Skip if:** `--skip-docs` flag OR ship mode is `beta`.
+
+Update project documentation for official releases. Run as **background task**.
+
+1. Invoke `/ck-docs update` skill via `ck-docs-manager` subagent in background:
+   - Analyzes code changes since last release
+   - Updates relevant docs in `./docs/` directory
+2. Don't wait for completion — continue to next step immediately.
+
+## Step 10: Commit
+
+1. Stage all changes: `git add -A`
+2. Security check: scan staged diff for secrets (API keys, tokens, passwords)
+   - If secrets found: **STOP**, warn user, suggest `.gitignore`
+3. Compose commit message:
+   - Format: `type(scope): description`
+   - Infer type from changes (feat/fix/refactor/chore)
+   - If version + changelog present, include in same commit
+4. Commit:
+
+```bash
+git commit -m "$(cat <<'EOF'
+type(scope): description
+
+Brief body describing the changes.
+EOF
+)"
+```
+
+## Step 11: Push
+
+```bash
+git push -u origin $(git branch --show-current)
+```
+
+- **Never force push.**
+- If push rejected: suggest `git pull --rebase` and retry once.
+
+## Step 12: Create PR
+
+Check if `gh` CLI is available:
+```bash
+which gh 2>/dev/null || echo "MISSING"
+```
+
+If missing: output "Install GitHub CLI (gh) to auto-create PRs" and stop after push.
+
+Create PR targeting the correct branch:
+```bash
+gh pr create --base <target-branch> --title "<type>: <summary>" --body "$(cat <<'EOF'
+<PR body from pr-template.md>
+EOF
+)"
+```
+
+**Link issues** collected from Step 2:
+```bash
+# If issues were found/created, add closing keywords in PR body
+# e.g., "Closes #42, Relates to #43"
+```
+
+**Output the PR URL** — this is the final output the user sees.
+
+If PR already exists for this branch, update it instead:
+```bash
+gh pr edit --title "<type>: <summary>" --body "$(cat <<'EOF'
+<PR body>
+EOF
+)"
+```

package/skills/ck-test/SKILL.md

@@ -0,0 +1,111 @@
+---
+name: ck-test
+description: "Run unit, integration, e2e, and UI tests. Use for test execution, coverage analysis, build verification, visual regression, and QA reports."
+argument-hint: "[context] OR ui [url]"
+---
+
+# Testing & Quality Assurance
+
+Comprehensive testing framework covering code-level testing (unit, integration, e2e), UI/visual testing via browser automation, coverage analysis, and structured QA reporting.
+
+## Default (No Arguments)
+
+If invoked with context (test scope), proceed with testing. If invoked WITHOUT arguments, ask the user to present available test operations:
+
+| Operation | Description |
+|-----------|-------------|
+| `(default)` | Run unit/integration/e2e tests |
+| `ui` | Run UI tests on a website |
+
+Present as options by asking the user with header "Test Operation", question "What would you like to do?".
+
+## Core Principle
+
+**NEVER IGNORE FAILING TESTS.** Fix root causes, not symptoms. No mocks/cheats/tricks to pass builds.
+
+## When to Use
+
+- **After implementation**: Validate new features or bug fixes
+- **Coverage checks**: Ensure coverage meets project thresholds (80%+)
+- **UI verification**: Visual regression, responsive layout, accessibility
+- **Build validation**: Verify build process, dependencies, CI/CD compatibility
+- **Pre-commit/push**: Final quality gate
+
+## Workflows
+
+### 1. Code Testing (`references/test-execution-workflow.md`)
+
+Execute test suites, analyze results, generate coverage. Supports JS/TS (Jest/Vitest/Mocha), Python (pytest), Go, Rust, Flutter. Includes working process, quality standards, and tool commands.
+
+**Load when:** Running unit/integration/e2e tests, checking coverage, validating builds
+
+### 2. UI Testing (`references/ui-testing-workflow.md`)
+
+Browser-based visual testing via `chrome-devtools` (if available) skill. Screenshots, responsive checks, accessibility audits, form automation, console error collection. Includes auth injection for protected routes.
+
+**Load when:** Visual regression testing, UI bugs, responsive layout checks, accessibility audits
+
+### 3. Report Format (`references/report-format.md`)
+
+Structured QA report template: test results overview, coverage metrics, failed tests, performance, build status, recommendations.
+
+**Load when:** Generating test summary reports
+
+## Quick Reference
+
+```
+Code tests     → test-execution-workflow.md
+  npm test / pytest / go test / cargo test / flutter test
+  Coverage: npm run test:coverage / pytest --cov
+
+UI tests       → ui-testing-workflow.md
+  Screenshots, responsive, a11y, forms, console errors
+  Auth: inject-auth.js for protected routes
+
+Reports        → report-format.md
+  Structured QA summary with metrics & recommendations
+```
+
+## Working Process
+
+1. Identify testing scope from recent changes or requirements
+2. Run typecheck/analyze commands to catch syntax errors first
+3. Execute appropriate test suites
+4. Analyze results — focus on failures
+5. Generate coverage reports if applicable
+6. For frontend: run UI tests via `chrome-devtools` (if available) skill
+7. Produce structured summary report
+
+## Tools Integration
+
+- **Test runners**: Jest, Vitest, Mocha, pytest, go test, cargo test, flutter test
+- **Coverage**: Istanbul/c8/nyc, pytest-cov, go cover
+- **Browser**: `chrome-devtools` (if available) skill for UI testing (screenshots, ARIA, console, network)
+- **Analysis**: `ai-multimodal` (if available) skill for screenshot analysis
+- **Debugging**: `ck-debug` skill when tests reveal bugs requiring investigation
+- **Thinking**: `ck-sequential-thinking` skill for complex test failure analysis
+
+## 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
+- Never ignore failing tests to pass the build
+
+## Report Output
+**IMPORTANT:** Invoke "/ck-project-organization" skill to organize the outputs.
+
+Use naming pattern from `## Naming` section injected by hooks.
+
+## Team Mode
+
+When operating as teammate:
+1. On start: check `TaskList`, claim assigned/next unblocked task via `TaskUpdate`
+2. Read full task description via `TaskGet` before starting
+3. Wait for blocked tasks (implementation) to complete before testing
+4. Respect file ownership — only create/edit test files assigned
+5. When done: `TaskUpdate(status: "completed")` then `SendMessage` results to lead
+
+**Fallback:** Task tools (`TaskList`/`TaskUpdate`/`TaskGet`) are CLI-only — unavailable in VSCode extension. If they error, use `TodoWrite` for progress tracking and coordinate via `SendMessage` only.

package/skills/ck-test/references/ui-testing-workflow.md

@@ -0,0 +1,65 @@
+# UI Testing Workflow
+
+Activate the ck:chrome-devtools (if available) skill.
+
+## Purpose
+Run comprehensive UI tests on a website and generate a detailed report.
+
+## Arguments
+- $1: URL - The URL of the website to test
+- $2: OPTIONS - Optional test configuration (e.g., --headless, --mobile, --auth)
+
+## Testing Protected Routes (Authentication)
+
+### Step 1: User Manual Login
+Instruct the user to:
+1. Open the target site in their browser
+2. Log in manually with their credentials
+3. Open browser DevTools (F12) → Application tab → Cookies/Storage
+
+### Step 2: Extract Auth Credentials
+Ask the user to provide one of:
+- **Cookies**: Copy cookie values (name, value, domain)
+- **Access Token**: Copy JWT/Bearer token from localStorage or cookies
+- **Session Storage**: Copy relevant session keys
+
+### Step 3: Inject Authentication
+Use the `inject-auth.js` script:
+
+```bash
+cd $SKILL_DIR  # chrome-devtools scripts (if available)
+
+# Option A: Inject cookies
+node inject-auth.js --url https://example.com --cookies '[{"name":"session","value":"abc123","domain":".example.com"}]'
+
+# Option B: Inject Bearer token
+node inject-auth.js --url https://example.com --token "Bearer eyJhbGciOi..." --header Authorization --token-key access_token
+
+# Option C: Inject localStorage
+node inject-auth.js --url https://example.com --local-storage '{"auth_token":"xyz","user_id":"123"}'
+```
+
+### Step 4: Run Tests
+After auth injection, run tests normally:
+```bash
+node navigate.js --url https://example.com/dashboard
+node screenshot.js --url https://example.com/profile --output profile.png
+```
+
+## Workflow
+- Use `plan` skill to organize the test plan & report
+- All screenshots saved in the same report directory
+- Browse URL, discover all pages, components, endpoints
+- Create test plan based on discovered structure
+- Use multiple `ck-tester` subagents in parallel for: pages, forms, navigation, user flows, accessibility, responsive layouts, performance, security, seo
+- Use `ai-multimodal` (if available) to analyze all screenshots
+- Generate comprehensive Markdown report
+- Ask user if they want to preview with `/ck-preview`
+
+## Output Requirements
+- Clear, structured Markdown with headers, lists, code blocks
+- Include test results summary, key findings, screenshot references
+- Ensure token efficiency while maintaining high quality
+- Sacrifice grammar for concision
+
+**Do not** start implementing fixes.