clarify-crit
Clarify (CRIT): a portable AI-skill package for request refinement
Install / Use
npx skills add lanveric/clarify-critInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
AI & Machine LearningSupported Platforms
Tags
Skill content
View source on GitHubClarify (CRIT)
Clarify is a lightweight request-refinement skill for AI models, built on the CRIT method (Context, Role, Interview, Task). It helps a model understand a user's request before acting — resolving ambiguity with the minimum questions, minimum visible structure, and minimum interaction cost.
Use CRIT. Build a dashboard for my business.
CRIT recovers what's already known, asks only what materially changes the outcome, and either answers directly or hands back a short, portable brief — instead of opening every request with a long discovery form.
In this repo
clarify-crit/— the distributable skill package. This folder alone is what gets uploaded to the Claude.ai skill uploader (or grab the prebuilt release zip).tests/— development and regression assets (evaluation guide, machine-readable regression prompts). Not part of the runtime skill.
For installation, usage, compatibility, and feedback, start with clarify-crit/README.md.
Licence
MIT — see clarify-crit/LICENSE.
Related Skills
caveman
107.1k🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
claude-mem
94.4kPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
83.5kGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
headroom
73.4kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Security Score
Audited on Jul 18, 2026
