nemonix-cli 1.0.0

package/src/config/claude-code-config/skills/workflow-ci-fixer/steps/step-04-commit-push.md

@@ -0,0 +1,206 @@
+---
+name: step-04-commit-push
+description: Commit fixes and push, then loop back to watch CI
+prev_step: steps/step-03-fix-locally.md
+next_step: steps/step-01-watch-ci.md
+---
+
+# Step 4: Commit & Push
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+- 🛑 **NO HACKS OR BYPASSES** - If hooks fail, fix the issue properly
+- 🛑 NEVER commit without `{local_verified}` = true
+- 🛑 NEVER use `--no-verify` on commit
+- 🛑 NEVER use `--force` push
+- ✅ ALWAYS use descriptive commit messages
+- ✅ ALWAYS let pre-commit hooks run
+- ✅ ALWAYS push to trigger new CI run
+- 📋 YOU ARE A COMMITTER, making clean commits
+- 💬 FOCUS on committing and pushing only
+- 🚫 FORBIDDEN to skip or bypass any hooks
+
+---
+
+## 🚫 FORBIDDEN ON COMMIT - NEVER DO THESE
+
+- `git commit --no-verify` - Let hooks run and fix issues they find
+- `git push --force` - Push normally
+- `git commit --amend` to bypass - Create new commits
+- Empty commit messages - Write descriptive messages
+- Committing without local verification passing - Go back to step-03
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Stage → Commit → Push → Loop back to watch
+- 💾 Track commit in `{fixes_applied}`
+- 📖 Complete push before loading next step
+- 🚫 FORBIDDEN to commit unverified changes
+
+## CONTEXT BOUNDARIES:
+
+From previous steps:
+
+| Variable | Description |
+|----------|-------------|
+| `{auto_mode}` | Skip confirmations |
+| `{branch}` | Current git branch |
+| `{current_attempt}` | Current attempt number |
+| `{local_verified}` | Must be true to proceed |
+| `{fixes_applied}` | List of fixes applied |
+
+## YOUR TASK:
+
+Create a clean commit with all fixes, push to remote, and loop back to watch CI for the result.
+
+---
+
+## EXECUTION SEQUENCE:
+
+### 1. Verify Pre-Conditions
+
+**CRITICAL CHECK:**
+```
+IF {local_verified} != true:
+    → STOP - cannot commit unverified changes
+    → Return to step-03-fix-locally.md
+```
+
+### 2. Review Changes
+
+Check what will be committed:
+```bash
+git status
+git diff --stat
+```
+
+**Display summary:**
+```
+## Changes to Commit (Attempt {current_attempt})
+
+Modified files:
+- src/utils.ts (2 insertions, 1 deletion)
+- tests/api.test.ts (5 insertions, 3 deletions)
+
+Fixes included:
+{list from fixes_applied}
+```
+
+### 3. Stage Changes
+
+Stage all modified files:
+```bash
+git add -A
+```
+
+**Verify staging:**
+```bash
+git status --short
+```
+
+### 4. Create Commit
+
+**Generate commit message from fixes:**
+
+Format:
+```
+fix(ci): {brief description of primary fix}
+
+{detailed list of fixes}
+
+Attempt: {current_attempt}/{max_attempts}
+```
+
+**Commit with message:**
+```bash
+git commit -m "$(cat <<'EOF'
+fix(ci): {description based on error_source}
+
+{list of fixes_applied formatted nicely}
+EOF
+)"
+```
+
+**DO NOT use `--no-verify`** - let pre-commit hooks run.
+
+**If commit fails due to pre-commit hook:**
+→ Fix the issues raised by the hook
+→ Return to step 3 (local verification)
+→ Re-run verification loop
+
+### 5. Push to Remote
+
+```bash
+git push origin {branch}
+```
+
+**If push fails:**
+- Check if branch is protected
+- Check for force push requirements
+- Ask user for help if needed
+
+**Display:**
+```
+✅ Pushed to origin/{branch}
+Waiting for CI to pick up changes...
+```
+
+### 6. Confirm Loop Back
+
+**If `{auto_mode}` = true:**
+→ Automatically proceed to step-01 to watch CI
+
+**If `{auto_mode}` = false:**
+Use AskUserQuestion:
+```yaml
+questions:
+  - header: "Continue"
+    question: "Fixes pushed. Watch CI for results?"
+    options:
+      - label: "Watch CI (Recommended)"
+        description: "Monitor the new CI run"
+      - label: "Stop here"
+        description: "I'll check CI manually"
+    multiSelect: false
+```
+
+---
+
+## SUCCESS METRICS:
+
+✅ Changes staged correctly
+✅ Commit created with descriptive message
+✅ Pre-commit hooks passed (no --no-verify)
+✅ Changes pushed to remote
+✅ Ready to loop back to step-01
+
+## FAILURE MODES:
+
+❌ **CRITICAL**: Committing without local_verified = true
+❌ **CRITICAL**: Using --no-verify flag
+❌ Vague commit messages like "fix" or "update"
+❌ Not pushing after commit
+❌ Not looping back to watch CI
+
+## COMMIT PROTOCOLS:
+
+- Commit message must describe what was fixed
+- Include attempt number for tracking
+- Never bypass pre-commit hooks
+- Always push immediately after commit
+
+---
+
+## NEXT STEP:
+
+**After push completes:**
+Loop back to `./step-01-watch-ci.md`
+
+The loop continues until:
+1. CI passes (success!) - workflow ends
+2. Max attempts reached - ask user for help
+3. User cancels
+
+<critical>
+Remember: This creates a loop! After push, we go back to watching CI. The workflow only ends when CI is green or max attempts reached.
+</critical>

package/src/config/claude-code-config/skills/workflow-ci-fixer/steps/step-05-cleanup.md

@@ -0,0 +1,196 @@
+---
+name: step-05-cleanup
+description: Cleanup artifacts and show final summary
+prev_step: steps/step-01-watch-ci.md
+---
+
+# Step 5: Cleanup & Summary
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+- 🛑 NEVER leave artifacts behind after workflow completion
+- ✅ ALWAYS delete the artifacts directory
+- ✅ ALWAYS show a final summary
+- 📋 YOU ARE THE CLOSER, wrapping up the workflow
+- 💬 FOCUS on cleanup and reporting only
+- 🚫 FORBIDDEN to start new fix attempts
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Summarize → Cleanup → Report final status
+- 💾 No state changes needed (workflow is ending)
+- 📖 This is the final step - workflow ends here
+- 🚫 FORBIDDEN to loop back to any previous step
+
+## CONTEXT BOUNDARIES:
+
+From previous steps:
+
+| Variable | Description |
+|----------|-------------|
+| `{auto_mode}` | Skip confirmations |
+| `{branch}` | Current git branch |
+| `{current_attempt}` | Total attempts made |
+| `{max_attempts}` | Max attempts allowed |
+| `{run_id}` | Last GitHub Actions run ID |
+| `{artifacts_dir}` | Path to artifacts: `.claude/data/ci-{run_id}/` |
+| `{fixes_applied}` | List of all fixes applied |
+| `{error_source}` | Last error source (if any) |
+
+## YOUR TASK:
+
+Show a final summary of what happened, clean up all artifacts, and end the workflow.
+
+---
+
+## EXECUTION SEQUENCE:
+
+### 1. Determine Final Status
+
+Check how the workflow ended:
+
+| Condition | Status |
+|-----------|--------|
+| CI passed | ✅ SUCCESS |
+| No CI configured | ⚠️ NO CI |
+| Max attempts reached | ❌ FAILED |
+| User cancelled | ⏹️ CANCELLED |
+
+### 2. Generate Final Summary
+
+**Display summary:**
+
+```
+## CI Fixer - Final Summary
+
+**Branch:** {branch}
+**Status:** {SUCCESS | FAILED | NO CI | CANCELLED}
+**Attempts:** {current_attempt}/{max_attempts}
+
+### Fixes Applied
+{If fixes_applied is not empty:}
+1. {fix description} - {file}
+2. {fix description} - {file}
+...
+
+{Else:}
+No fixes were needed.
+
+### Commits Made
+{List commits made during this session, if any}
+```
+
+### 3. Show Git Log of Session (If Fixes Applied)
+
+**If any fixes were committed:**
+```bash
+git log --oneline -n {current_attempt} --format="%h %s"
+```
+
+Display the commits made during this CI fixer session.
+
+### 4. Cleanup Artifacts
+
+**Check if artifacts directory exists:**
+```bash
+ls -la {artifacts_dir} 2>/dev/null
+```
+
+**If artifacts exist, delete them:**
+```bash
+trash {artifacts_dir}
+```
+
+**Confirm cleanup:**
+```
+Cleaned up artifacts from {artifacts_dir}
+```
+
+**If no artifacts exist:**
+```
+No artifacts to clean up.
+```
+
+### 5. Final Status Message
+
+**If SUCCESS:**
+```
+## ✅ CI is green!
+
+All checks passed. Your PR is ready for review.
+
+Run: https://github.com/{owner}/{repo}/actions/runs/{run_id}
+```
+
+**If FAILED (max attempts):**
+```
+## ❌ CI still failing
+
+Could not fix after {max_attempts} attempts.
+
+**Last errors:**
+{last error summary}
+
+**Next steps:**
+1. Review the error logs manually
+2. Check if the issue requires architectural changes
+3. Ask for help from a teammate
+
+Run: https://github.com/{owner}/{repo}/actions/runs/{run_id}
+```
+
+**If NO CI:**
+```
+## ⚠️ No CI configured
+
+No GitHub Actions workflow was triggered for this branch.
+
+To add CI, create a workflow file at `.github/workflows/ci.yml`
+```
+
+**If CANCELLED:**
+```
+## ⏹️ Workflow cancelled
+
+The CI fixer was stopped by user request.
+
+{If fixes were applied:}
+Note: {N} fixes were already committed before cancellation.
+```
+
+---
+
+## SUCCESS METRICS:
+
+✅ Final status correctly determined
+✅ Comprehensive summary displayed
+✅ All fixes listed
+✅ Commits shown
+✅ Artifacts directory deleted
+✅ Cleanup confirmed
+✅ Workflow ended cleanly
+
+## FAILURE MODES:
+
+❌ Not deleting artifacts
+❌ Incomplete summary
+❌ Not showing fix history
+❌ Trying to continue after this step
+
+## CLEANUP PROTOCOLS:
+
+- Always attempt to delete artifacts
+- Use `trash` command first
+- Confirm deletion to user
+- Never leave stale artifacts behind
+- This is the FINAL step - no more actions after this
+
+---
+
+## WORKFLOW END
+
+**This is the final step. The CI fixer workflow is now complete.**
+
+<critical>
+Remember: ALWAYS clean up artifacts! The workflow ENDS here - do not loop back.
+</critical>

package/src/config/claude-code-config/skills/workflow-clean-code/SKILL.md

@@ -0,0 +1,129 @@
+---
+name: clean-code
+description: Comprehensive clean code workflow that analyzes codebase, recommends best practices, and applies clean code principles for React, Next.js, and modern tooling.
+argument-hint: "[-a] [-e] [-s] [-r <id>] <feature/file>"
+---
+
+<objective>
+Fast, systematic clean code improvements using parallel agents.
+</objective>
+
+<quick_start>
+**Basic usage (analyze and apply clean code principles):**
+```bash
+/clean-code auth feature
+```
+
+**Auto mode (skip confirmations):**
+```bash
+/clean-code -a dashboard
+```
+
+**With save (output to `.claude/output/clean-code/`):**
+```bash
+/clean-code -s -a refactor api
+```
+
+**What it does:**
+1. Scans codebase for issues (React, Next.js, Zustand, TanStack Query)
+2. Loads relevant best practices docs
+3. Applies clean code improvements
+4. Verifies with build and tests
+5. Commits changes
+</quick_start>
+
+<parameters>
+
+| Flag | Description |
+|------|-------------|
+| `-a` | Auto mode: skip confirmations |
+| `-e` | Economy mode: no subagents, direct tools only |
+| `-s` | Save mode: output to `.claude/output/clean-code/` |
+| `-r` | Resume mode: continue from previous task |
+| `--react` | Force load React 19 patterns |
+| `--nextjs` | Force load Next.js 15/16 patterns |
+| `--zustand` | Force load Zustand v5 patterns |
+| `--query` | Force load TanStack Query v5 patterns |
+
+<examples>
+```bash
+/clean-code auth feature          # Basic
+/clean-code -a dashboard          # Auto mode
+/clean-code -e -a fix types       # Economy + auto
+/clean-code -s refactor api       # Save outputs
+/clean-code -r auth-feature       # Resume
+/clean-code --nextjs --query data # Force docs
+```
+</examples>
+
+</parameters>
+
+<workflow>
+```
+SCAN → APPLY → VERIFY
+  │       │       │
+  │       │       └─ Build, test, commit
+  │       └─ Load docs, recommend, apply
+  └─ Parse flags, detect tech, find issues
+```
+</workflow>
+
+<state_variables>
+
+| Variable | Type | Description |
+|----------|------|-------------|
+| `{task_description}` | string | What to analyze |
+| `{task_id}` | string | Kebab-case identifier |
+| `{auto_mode}` | boolean | Skip confirmations |
+| `{economy_mode}` | boolean | No subagents |
+| `{save_mode}` | boolean | Save outputs |
+| `{detected_tech}` | object | Technologies found |
+| `{issues}` | array | Issues found |
+
+</state_variables>
+
+<reference_files>
+
+| File | When Loaded |
+|------|-------------|
+| `references/general-clean-code.md` | Always |
+| `references/react-clean-code.md` | React detected / `--react` |
+| `references/nextjs-clean-code.md` | Next.js detected / `--nextjs` |
+| `references/zustand-best-practices.md` | Zustand detected / `--zustand` |
+| `references/tanstack-query-best-practices.md` | No data fetching / `--query` |
+
+</reference_files>
+
+<entry_point>
+
+Load `steps/step-01-scan.md`
+
+</entry_point>
+
+<step_files>
+
+| Step | File | Purpose |
+|------|------|---------|
+| 01 | `step-01-scan.md` | Init + analyze |
+| 02 | `step-02-apply.md` | Load docs + apply |
+| 03 | `step-03-verify.md` | Build + commit |
+
+</step_files>
+
+<execution_rules>
+- Load one step at a time
+- Use parallel agents in step-01 (unless economy mode)
+- Always run build before completing
+- Follow patterns from reference files exactly
+</execution_rules>
+
+<success_criteria>
+- Technologies correctly detected (React, Next.js, Zustand, TanStack Query)
+- Issues identified and documented
+- Relevant reference docs loaded
+- Clean code improvements applied
+- Build passes without errors
+- Tests pass (if tests exist)
+- Changes committed with clear message
+- No hacks or shortcuts used
+</success_criteria>