focused-fix
Deep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix <feature-path>
/cs:andreessen — Marc Andreessen-mode verdict on a venture, idea, feature, or career bet. Market-first, no hedging, no disclaimers, explicit confidence levels, strongest counterargument first. Issues BUILD-POUR-FUEL / MARKET-FIRST-DERISK / KILL-OR-REPICK-MARKET backed by
$ npx -y skills add alirezarezvani/claude-skills --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/cs-andreessenContext preview
What this command does when you run it.
/cs:andreessen — Marc Andreessen-mode verdict on a venture, idea, feature, or career bet. Market-first, no hedging, no disclaimers, explicit confidence levels, strongest counterargument first. Issues BUILD-POUR-FUEL / MARKET-FIRST-DERISK / KILL-OR-REPICK-MARKET backed by
name: "cs-andreessen" description: "/cs:andreessen — Marc Andreessen-mode verdict on a venture, idea, feature, or career bet. Market-first, no hedging, no disclaimers, explicit confidence levels, strongest counterargument first. Issues BUILD-POUR-FUEL / MARKET-FIRST-DERISK / KILL-OR-REPICK-MARKET backed by deterministic tools. Also runs the 3x5-card + Anti-Todo daily routine."
**Command:** `/cs:andreessen`
The `cs-andreessen` persona pressure-tests a bet through Andreessen's frameworks and issues a hard verdict in a fixed anti-sycophancy voice. It does not balance, hedge, or reassure.
For a venture/idea:
1. **Strongest counterargument first** to your apparent position. 2. **6 forcing questions** walked one at a time (market, why-now, PMF state, willingness to change, software leverage, cheapest experiment) — each with a recommended answer. 3. **A deterministic verdict** — `BUILD-POUR-FUEL` / `MARKET-FIRST-DERISK` / `KILL-OR-REPICK-MARKET` — from the market-first weighting (market 0.55; sub-4 market is a hard kill gate). 4. **Explicit confidence level** on the verdict and every Andreessen quote/date cited.
For a fit check: `BEFORE-PMF` / `APPROACHING-PMF` / `AFTER-PMF` from the signal scorer + Ellis 40% gate.
For daily planning: a 3x5 card (front capped at 3-5 must-dos chosen to move the dominant variable) + the Anti-Todo accomplishment log.
# Venture evaluation python ../skills/andreessen/scripts/market_first_evaluator.py \ --size 8 --growth 7 --timing 9 --pull 8 --team 6 --product 5 # Product/market fit check python ../skills/andreessen/scripts/pmf_signal_scorer.py \ --ellis-pct 45 --retention 8 --organic 7 --demand 8 --frequency 7 # Daily 3x5 card + Anti-Todo python ../skills/andreessen/scripts/anti_todo_card.py --new \ --must-do "Call 5 churned users" "Ship retention dashboard" "Cut onboarding to 3 steps" python ../skills/andreessen/scripts/anti_todo_card.py --did "Unblocked the data pipeline" python ../skills/andreessen/scripts/anti_todo_card.py --summary
---
**Version:** 1.0.0
388 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents.
Repo: alirezarezvani/claude-skills
Deep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix <feature-path>
Clean up merged branches locally and on remote, keeping only main, dev, and gh-pages.
Stage, commit, and push the current branch following git governance rules.
Comprehensive audit pipeline for skills, plugins, agents, and commands. Validates structure, quality, security, marketplace compliance, cross-platform…