Use when shipping installers, setup scripts, portable bundles, bootstrap flows, or “works on a fresh machine” claims.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add ShugokiFable/Ultimate-AI-Starter-Bundle --skill fresh-install-proof --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Fresh Install Proof?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/shugokifable-fresh-install-proof-a7a4a10b)More formats (shields.io, HTML) on the badges page.
---
name: fresh-install-proof
description: Use when shipping installers, setup scripts, portable bundles, bootstrap flows, or “works on a fresh machine” claims.
---
# Fresh Install Proof
## Core rule
An installer is proven from **empty** state, not from the developer machine that already has dependencies and config.
## Required matrix
Test a disposable user/home with no prior product state. Include a destination containing **spaces** and **Unicode** characters. Exercise missing runtimes, missing config files, read-only/locked files where relevant, offline-vs-online modes, and an **idempotent** second install.
A passing fresh-install proof requires:
- one documented entrypoint;
- dependencies installed or a functional automatic fallback;
- no required manual “now edit/copy/approve this” step when automation is supported;
- failure returns non-zero and never prints a success banner;
- re-running preserves user settings and repairs partial state;
- final doctor verifies installed state, not merely source files.
## Evidence
Record the exact command, clean-state assumptions, exit code, installed paths, and doctor result. A test against an already-configured profile is a regression test, not fresh-install proof.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
