by jmassengille · Agent Tool · ★ 53
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/jmassengille/sketch2prompt.gitTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 53 |
| Forks | 9 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67/100 |
| Open Issues | 2 |
| Last Updated | 2026-01-29 |
| Created | 2025-12-16 |
| Platforms | node |
| Est. Tokens | ~662k |
sketch2prompt Freeze your intent before AI starts guessing. The Problem AI coding assistants are powerful, but they're working blind. Give them a vague prompt and they'll hallucinate architecture, invent inconsistent conventions, and create sprawl that's painful to refactor. The issue isn't the AI—it's underspecified intent.
Looking for a sketch2prompt alternative? If you're comparing sketch2prompt with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
MCP Fusion - The framework for AI-native MCP servers.
📜 An MCP server for conversation history search and retrieval in Claude Code
Comprehensive MCP server providing real-time framework documentation access for Claude Code with intelligent c
An LLM council that reviews your coding agent's every move
Automatic context preservation for Claude Code. Never lose work to compaction again. 7 hooks, 187 semantic pat
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: