nemonix-cli 1.0.0

package/src/config/claude-code-config/skills/workflow-brainstorm/steps/step-04-action.md

@@ -0,0 +1,285 @@
+---
+name: step-04-action
+description: Action crystallization phase - transform insights into clear recommendations and actions
+---
+
+# Phase 4: Action Crystallization
+
+**Role: STRATEGIC ADVISOR** - Transform insight into clear, actionable recommendations
+
+---
+
+<available_state>
+From previous steps:
+
+- `{topic}` - The research topic
+- `{economy_mode}` - If true, used direct tool calls instead of subagents
+- `{fast_mode}` - If true, skipped Phase 2 and used 3 perspectives in Phase 3
+- `{save_file}` - If true, save session to file
+- `{session_path}` - Path to session file (if saving)
+- `{phase_1_discoveries}` - Broad findings from Phase 1
+- `{phase_2_challenges}` - Challenges from Phase 2 (empty if fast_mode)
+- `{phase_3_synthesis}` - Multi-perspective analysis from Phase 3
+</available_state>
+
+---
+
+<mandatory_rules>
+## MANDATORY EXECUTION RULES (READ FIRST)
+
+- 🎯 FORM clear, defensible recommendations - no wishy-washy conclusions
+- 📊 ASSIGN confidence levels HONESTLY - admit uncertainty
+- ⚔️ PRESENT the strongest contrarian view - steelman the opposition
+- 📋 CREATE actionable next steps - specific, not vague
+- 🔗 CITE sources for key claims
+- 🚫 FORBIDDEN: Vague conclusions like "it depends" without specifics
+- 🚫 FORBIDDEN: Hiding uncertainty behind confident language
+</mandatory_rules>
+
+---
+
+<execution_sequence>
+
+<ultra_think>
+**1. ULTRA THINK: Deep Synthesis**
+
+Before producing output, deeply consider:
+
+**What do the phases tell us?**
+- Phase 1 (Exploration): The landscape is...
+- Phase 2 (Challenge): After stress-testing, the strongest findings are... *(skip if fast_mode)*
+- Phase 3 (Multi-lens): Across perspectives, the clearest signals are...
+
+**What's my honest recommendation?**
+- If I had to advise someone today, I would say...
+- The confidence I have in this is... because...
+
+**What would change my mind?**
+- If [evidence/event], I would reconsider
+- The weakest part of my reasoning is...
+
+**What's the strongest argument against my recommendation?**
+- The best counter-argument is...
+- Why someone might reasonably disagree...
+</ultra_think>
+
+<generate_output>
+**2. Generate Final Output**
+
+Produce the final brainstorm output in this format:
+
+```markdown
+## 🧠 Brainstorm: {topic}
+
+### Research Summary
+
+**Process completed:**
+- **Phase 1 (Exploration):** [# of sources], [breadth of coverage]
+- **Phase 2 (Challenge):** [# of findings challenged], [# revised] *(skipped if fast_mode)*
+- **Phase 3 (Synthesis):** [3 or 5] perspectives analyzed, [key patterns found]
+- **Mode:** [Standard / Economy / Fast / Economy+Fast]
+
+**Key areas investigated:**
+- [Area 1]
+- [Area 2]
+- [Area 3]
+
+---
+
+### Key Insights
+
+1. **[Insight 1]** - Confidence: **High/Medium/Low**
+   - [Supporting evidence and reasoning]
+
+2. **[Insight 2]** - Confidence: **High/Medium/Low**
+   - [Supporting evidence and reasoning]
+
+3. **[Insight 3]** - Confidence: **High/Medium/Low**
+   - [Supporting evidence and reasoning]
+
+4. **[Insight 4]** - Confidence: **High/Medium/Low**
+   - [Supporting evidence and reasoning]
+
+5. **[Insight 5]** - Confidence: **High/Medium/Low**
+   - [Supporting evidence and reasoning]
+
+---
+
+### Recommendation
+
+**Primary recommendation:**
+[Clear, specific recommendation]
+
+**Rationale:**
+[Why this recommendation based on all research]
+
+**Key tradeoffs accepted:**
+- [Tradeoff 1]: We're choosing [X] over [Y] because...
+- [Tradeoff 2]: We're accepting [risk] for [benefit]
+
+**Overall Confidence: [High/Medium/Low]**
+- Would change to higher if: [evidence needed]
+- Would change to lower if: [counter-evidence]
+
+---
+
+### Contrarian View
+
+**The strongest argument against this recommendation:**
+
+[Steelman the opposing view - present it as compellingly as possible]
+
+**Why someone might reasonably choose differently:**
+- [Reason 1]
+- [Reason 2]
+
+**When the contrarian view might be right:**
+- If [condition], then [alternative] would be better
+
+---
+
+### Open Questions
+
+**Still needs investigation:**
+1. [Question 1] - Why it matters: [impact]
+2. [Question 2] - Why it matters: [impact]
+3. [Question 3] - Why it matters: [impact]
+
+**Assumptions that need validation:**
+- [Assumption] - How to validate: [method]
+
+---
+
+### Immediate Actions
+
+**This week:**
+1. [Specific action 1]
+2. [Specific action 2]
+3. [Specific action 3]
+
+**Before committing fully:**
+- [Validation step or experiment to run]
+
+---
+
+### Sources
+
+**Key references:**
+- [Source 1]: [What it contributed]
+- [Source 2]: [What it contributed]
+- [Source 3]: [What it contributed]
+
+**Perspectives consulted:**
+- [Expert/Source] on [topic]
+- [Expert/Source] on [topic]
+```
+</generate_output>
+
+<save_final>
+**3. Save Final Output** (if `{save_file}` is true)
+
+Append to `{session_path}`:
+```markdown
+## Phase 4: Action Crystallization
+
+[Complete final output above]
+
+---
+
+## Session Complete
+
+**Total research phases:** 4
+**Research completed:** {current_date}
+```
+
+Also announce: "Session saved to `{session_path}`"
+</save_final>
+
+<completion>
+**4. Completion Message**
+
+```
+---
+
+**✅ Brainstorm Complete**
+
+This research covered:
+- Broad exploration with parallel agents
+- Skeptical challenge of all findings
+- Analysis through 5 expert perspectives
+- Crystallization into actionable recommendations
+
+**Confidence summary:**
+- [# High confidence] insights
+- [# Medium confidence] insights
+- [# Low confidence] insights
+
+**Next steps are clear:** [summarize top 1-2 actions]
+
+**Open for follow-up:** Ask me to dig deeper on any specific area.
+```
+</completion>
+
+</execution_sequence>
+
+---
+
+<confidence_calibration>
+## Confidence Level Guidelines
+
+**High Confidence:**
+- Multiple independent sources agree
+- Survived skeptical challenge
+- Multiple perspectives converge
+- Clear evidence, minimal assumptions
+
+**Medium Confidence:**
+- Good evidence but some gaps
+- Some perspectives diverge
+- Reasonable assumptions required
+- More investigation would help
+
+**Low Confidence:**
+- Limited evidence
+- Significant uncertainty
+- Conflicting perspectives
+- Important assumptions untested
+</confidence_calibration>
+
+---
+
+<success_metrics>
+
+- Clear, specific recommendations (not "it depends")
+- Honest confidence levels with calibration
+- Strongest contrarian view presented fairly
+- Actionable next steps (specific, not vague)
+- Open questions acknowledge what we don't know
+- Sources cited for key claims
+- Complete output format followed
+</success_metrics>
+
+<failure_modes>
+
+- Vague recommendations that don't commit
+- Overconfident conclusions hiding uncertainty
+- Weak strawman of contrarian view
+- "Next steps" that are too generic to act on
+- Forgetting to cite sources
+- Rushing the synthesis without ULTRA THINK
+</failure_modes>
+
+---
+
+<workflow_complete>
+## Workflow Complete
+
+The brainstorm-skills workflow has completed all 4 phases:
+
+1. ✅ **Expansive Exploration** - Cast wide net
+2. ✅ **Critical Challenge** - Stress-tested findings
+3. ✅ **Multi-Lens Synthesis** - 5 perspectives analyzed
+4. ✅ **Action Crystallization** - Clear recommendations
+
+The user now has battle-tested insights ready for action.
+</workflow_complete>

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

@@ -0,0 +1,150 @@
+---
+name: ci-fixer
+description: Automated CI/CD pipeline fixer - watches CI, fixes errors locally, commits, and loops until green. Use when CI is failing and you want to automatically fix and verify changes.
+argument-hint: "[--auto] [--max-attempts=N]"
+color: yellow
+---
+
+<objective>
+Autonomously fix CI/CD pipeline failures by:
+1. Watching CI runs in real-time
+2. Analyzing failures (GitHub Actions, Vercel, Netlify, etc.)
+3. Fixing errors and verifying locally (tests, linter - NO skipping, NO hacks)
+4. Committing fixes and looping until pipeline is green
+5. Cleaning up artifacts when done
+</objective>
+
+<quick_start>
+**Basic usage (watch and fix CI):**
+```bash
+/ci-fixer
+```
+
+**Auto mode (no confirmations):**
+```bash
+/ci-fixer --auto
+```
+
+**With max attempts limit:**
+```bash
+/ci-fixer --max-attempts=3
+```
+
+The skill will:
+1. Detect your current branch's CI run
+2. Watch for failures
+3. Fix errors locally (tests, lint, build)
+4. Commit and push
+5. Loop until green ✅
+
+**CRITICAL**: Zero tolerance for hacks - fixes must be proper, no `@ts-ignore`, `eslint-disable`, or test skipping.
+</quick_start>
+
+<parameters>
+| Flag | Description |
+|------|-------------|
+| `-a, --auto` | Auto mode - skip confirmations, auto-proceed |
+| `-m N, --max-attempts=N` | Maximum fix attempts before asking for help (default: 5) |
+</parameters>
+
+<state_variables>
+**Persist throughout all steps:**
+
+| Variable | Type | Description |
+|----------|------|-------------|
+| `{auto_mode}` | boolean | Skip confirmations |
+| `{max_attempts}` | integer | Max fix attempts (default: 5) |
+| `{current_attempt}` | integer | Current attempt number |
+| `{run_id}` | string | Current GitHub Actions run ID |
+| `{branch}` | string | Current git branch |
+| `{last_commit_sha}` | string | SHA of commit being watched |
+| `{artifacts_dir}` | string | Path to artifacts: `.claude/data/ci-{run_id}/` |
+| `{error_source}` | string | Source of error (github-actions, vercel, netlify) |
+| `{error_logs}` | string | Captured error logs |
+| `{fixes_applied}` | list | List of fixes applied this session |
+| `{local_verified}` | boolean | Whether local tests/lint passed |
+</state_variables>
+
+<entry_point>
+Load `steps/step-00-init.md`
+</entry_point>
+
+<step_files>
+| Step | File | Description |
+|------|------|-------------|
+| 0 | `step-00-init.md` | Parse flags, detect branch, setup state |
+| 1 | `step-01-watch-ci.md` | Find CI run, monitor status |
+| 2 | `step-02-analyze-errors.md` | Fetch logs/artifacts, analyze errors |
+| 3 | `step-03-fix-locally.md` | Fix errors, verify locally |
+| 4 | `step-04-commit-push.md` | Commit and push, loop back |
+| 5 | `step-05-cleanup.md` | Cleanup artifacts, show summary |
+</step_files>
+
+<workflow_diagram>
+```
+┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐
+│   Init   │───►│  Watch   │───►│ Analyze  │───►│   Fix    │───►│  Commit  │
+│ Step 0   │    │   CI     │    │  Errors  │    │ Locally  │    │  & Push  │
+└──────────┘    └────┬─────┘    └──────────┘    └──────────┘    └────┬─────┘
+                     │                                               │
+                     │         ┌─────────────────────────────────────┘
+                     │         │ (loop until green or max attempts)
+                     │◄────────┘
+                     │
+                ┌────┴────┐    ┌──────────┐
+                │ SUCCESS │───►│ Cleanup  │
+                │ or STOP │    │ Step 5   │
+                └─────────┘    └──────────┘
+```
+</workflow_diagram>
+
+<artifacts_storage>
+Artifacts are stored in `.claude/data/ci-{run_id}/`:
+```
+.claude/data/ci-{run_id}/
+├── github/
+│   ├── failed-logs.txt      # Failed job logs
+│   └── artifacts/           # Downloaded artifacts
+├── vercel/
+│   ├── deployment.json      # Deployment info
+│   └── logs.txt             # Build/runtime logs
+├── netlify/
+│   └── build-logs.txt       # Build logs
+└── summary.md               # Error analysis summary
+```
+</artifacts_storage>
+
+<core_principles>
+<zero_tolerance_policy>
+**ZERO TOLERANCE FOR HACKS**
+
+If you can't fix it properly, ASK FOR HELP. Never bypass or hack.
+
+1. **NEVER skip tests** - All tests must pass locally before committing
+2. **NEVER hack around issues** - Fix the root cause, don't disable checks
+3. **NEVER use bypass flags** - No `--no-verify`, `--skip`, `@ts-ignore`, `eslint-disable`
+4. **NEVER disable rules** - Don't add to `.eslintignore`, don't lower strictness
+5. **Verify locally first** - Always run tests/lint locally before pushing
+6. **Minimal changes** - Only fix what's broken, don't refactor unrelated code
+7. **Clear commits** - Each fix should have a descriptive commit message
+8. **Clean up** - Delete artifacts when workflow completes
+
+**Forbidden hacks include:** `@ts-ignore`, `eslint-disable`, `.skip`, `as any`, `--no-verify`, `--legacy-peer-deps`, commenting out tests, changing assertions to match wrong output, adding files to ignore lists.
+</zero_tolerance_policy>
+</core_principles>
+
+<success_criteria>
+- CI pipeline status successfully monitored
+- Errors analyzed and root cause identified
+- Fixes applied locally and verified (all tests/lint passing)
+- Changes committed with clear messages
+- CI pipeline green ✅ after fixes
+- Artifacts cleaned up
+- No hacks or bypasses used
+- Maximum attempts limit respected
+</success_criteria>
+
+<references>
+- [CLI Commands](references/cli-commands.md) - GitHub, Vercel, Netlify CLI reference
+- [Troubleshooting](references/troubleshooting.md) - Common issues and solutions
+</references>

package/src/config/claude-code-config/skills/workflow-ci-fixer/references/cli-commands.md

@@ -0,0 +1,122 @@
+# CLI Commands Quick Reference
+
+Quick reference for CI/CD debugging. For detailed commands, see:
+- [GitHub CLI Reference](github-cli.md)
+- [Vercel CLI Reference](vercel-cli.md)
+
+---
+
+## GitHub Actions - Most Used
+
+```bash
+# List runs for current branch
+gh run list --branch $(git branch --show-current) --limit 5
+
+# Watch a run in real-time
+gh run watch <run-id>
+
+# Get failed logs only
+gh run view <run-id> --log-failed
+
+# Re-run failed jobs
+gh run rerun <run-id> --failed
+
+# Download artifacts
+gh run download <run-id> --dir /tmp/artifacts
+```
+
+---
+
+## Vercel - Most Used
+
+```bash
+# List recent deployments
+vercel ls --output json | head -5
+
+# Get deployment details
+vercel inspect <deployment-url>
+
+# Stream runtime logs
+vercel logs <deployment-url>
+
+# Pull env vars locally
+vercel pull --yes
+
+# Build locally to reproduce issues
+vercel build --debug
+```
+
+---
+
+## Netlify - Most Used
+
+```bash
+# Check status
+netlify status
+
+# List sites
+netlify sites:list
+
+# Get recent deploys
+netlify deploys
+
+# View deploy details
+netlify deploys --json | jq '.[0]'
+
+# Build locally to reproduce
+netlify build --dry-run
+
+# View build logs
+netlify build
+```
+
+---
+
+## Local Verification Commands
+
+### Lint
+```bash
+npm run lint
+npx eslint . --fix
+npx prettier --check .
+npx prettier --write .
+```
+
+### Type Check
+```bash
+npx tsc --noEmit
+npm run typecheck
+```
+
+### Tests
+```bash
+npm test
+npm run test:ci
+npx jest
+npx vitest run
+```
+
+### Build
+```bash
+npm run build
+npx next build
+npx vite build
+```
+
+---
+
+## One-Liners
+
+```bash
+# Get latest run ID for current branch
+gh run list --branch $(git branch --show-current) -L1 --json databaseId -q '.[0].databaseId'
+
+# Get latest failed run
+gh run list --status failure -L1 --json databaseId -q '.[0].databaseId'
+
+# Re-run latest failed
+gh run rerun $(gh run list --status failure -L1 --json databaseId -q '.[0].databaseId') --failed
+
+# Get Vercel deployment URL for current commit
+vercel ls --output json | jq -r --arg sha "$(git rev-parse HEAD)" '.[] | select(.meta.githubCommitSha == $sha) | .url'
+```