Auto-run at the start of every Claude Code session. Loads project context, checks for active tasks, connects MCP servers, and suggests the right skill for the current workflow phase. This is the "boot sequence" that ensures every session starts with maximum context and minimum waste. Trigger: Run at session start or when switching projects.
Scanned 5/27/2026
Install via CLI
openskills install KevinZai/commander---
name: session-startup
description: |
Auto-run at the start of every Claude Code session. Loads project context,
checks for active tasks, connects MCP servers, and suggests the right skill
for the current workflow phase. This is the "boot sequence" that ensures
every session starts with maximum context and minimum waste.
Trigger: Run at session start or when switching projects.
allowed-tools:
- Bash
- Read
---
# Session Startup
## Boot Sequence (run in order)
### 1. Load Context
```bash
# Read project CLAUDE.md
[ -f CLAUDE.md ] && echo "📋 Project CLAUDE.md found" || echo "⚠️ No project CLAUDE.md — consider /project init"
# Read active tasks
[ -f tasks/todo.md ] && echo "📝 Active tasks:" && grep -c "^\- \[ \]" tasks/todo.md | xargs -I{} echo " {} incomplete items" || echo "📝 No tasks/todo.md"
# Read recent lessons
[ -f tasks/lessons.md ] && echo "📖 Lessons file found" || true
```
### 2. Check Git State
```bash
branch=$(git branch --show-current 2>/dev/null || echo "not a git repo")
dirty=$(git status -s 2>/dev/null | wc -l | tr -d ' ')
echo "🌿 Branch: $branch | Uncommitted: $dirty files"
```
### 3. Detect Workflow Phase
Based on current state, suggest the right skill:
| Signal | Phase | Skill |
|--------|-------|-------|
| No CLAUDE.md or tasks/ | **Kickoff** | `/project init` or `project-kickoff` |
| No spec file, new feature | **Spec** | `spec-interviewer` |
| Spec exists, no code | **Plan** | `writing-plans` or `/plan-eng-review` |
| Active todo items | **Build** | Continue working |
| Code written, no tests | **Verify** | `verification-before-completion` |
| Tests pass, ready to ship | **Ship** | `/ship` or `/pr` |
| Just shipped | **Retro** | `/retro` |
### 4. Report
```
🚀 Session Ready
Project: {name}
Branch: {branch}
Phase: {detected phase}
Suggested: {skill name}
Tasks: {X incomplete / Y total}
```
## Gotchas
- Don't spend more than 10 seconds on startup — it should be fast
- If no project context, just greet and ask what we're working on
- Never auto-run destructive commands during startup
- MCP servers connect automatically — don't test them unless asked
No comments yet. Be the first to comment!
Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.
SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.
Python backend development expertise for FastAPI, security patterns, database operations, Upstash integrations, and code quality. Use when: (1) Building REST APIs with FastAPI, (2) Implementing JWT/OAuth2 authentication, (3) Setting up SQLAlchemy/async databases, (4) Integrating Redis/Upstash caching, (5) Refactoring AI-generated Python code (deslopification), (6) Designing API patterns, or (7) Optimizing backend performance.
Drive the full internationalization journey for a project — detect the stack, recommend a library, set up the chosen library, wrap existing strings, and optionally connect a translation platform. Use when the user asks to add or configure i18n, internationalization, localization, multi-language support, or translations — including when they explicitly mention LinguiJS, Lingui, next-intl, "wrap strings", "find hardcoded text", "make my app translatable", or "set up translations". Triggers on g...
PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.