Input Refiner
v2026.3.26Rewrite vague or unstructured user input into a clear, organized, and execution-ready form based on context, preserving the original intent.
⭐ 0· 63·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (rewriting/vettting user input) match the SKILL.md instructions. No unrelated binaries, env vars, or config paths are requested—everything required is consistent with an in-conversation text-refinement utility.
Instruction Scope
Runtime instructions are limited to collecting the user's original input and nearby conversational context, inferring a target format, and producing structured rewrites. The skill does not instruct the agent to read files, access system config, call external endpoints, or exfiltrate data beyond conversation context.
Install Mechanism
No install spec and no code files—this is an instruction-only skill. That is the lowest-risk install profile and matches the skill's simple text-processing purpose.
Credentials
The skill requests no environment variables or credentials. Its declared inputs (conversation text, nearby context, language preference) are proportionate to a text refinement task.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills. Autonomous invocation is allowed by default, which is normal; there is no additional privileged access.
Assessment
This skill appears coherent and low-risk: it only rewrites conversation text, requires no installs or credentials, and stays within scope. Before using it, be aware that it will draw on nearby conversation context to clarify intent — avoid including secrets or sensitive PII in messages you ask it to refine. Also review refined outputs before sending them to external systems, since any automated rewriting can subtly change emphasis or detail even when it attempts to preserve intent. If you want stricter limits, restrict the skill to operate only on explicit user-provided text (not surrounding messages) or require confirmation before using inferred context.Like a lobster shell, security has layers — review code before you run it.
latestvk97dnq7eknadtf0bsx5yeqzdhh83m159
License
MIT-0
Free to use, modify, and redistribute. No attribution required.