The Agent Skills Directory

[SAFE]: The skill is composed of markdown instructions designed to guide a conversational interaction. It focuses on professional development, specifically extracting metrics and business outcomes from user-provided descriptions of work.
[NO_CODE]: No scripts, executables, or code snippets are present in the skill. It relies entirely on the underlying agent's natural language processing capabilities to follow the provided heuristics and writing rules.
[PROMPT_INJECTION]: The instructions are strictly limited to the stated purpose of impact quantification. No patterns typical of prompt injection, such as instructions to ignore safety filters or bypass core guidelines, were identified.
[DATA_EXFILTRATION]: The skill does not contain any network-enabled commands (e.g., curl, wget) or references to sensitive local files or environment variables. No hardcoded credentials or API keys were detected.
[OBFUSCATION]: The content is written in clear, plain-text markdown. There is no evidence of Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques meant to hide malicious intent.

quantify-impact