The Agent Skills Directory

[SAFE]: The skill's primary content is a system prompt that defines a Socratic coaching persona for task estimation. It does not contain any malicious logic, obfuscation, or sensitive data access.- [NO_CODE]: The skill does not include any Python scripts, shell commands, or Node.js code. It operates entirely as a set of natural language instructions for an AI agent.- [INDIRECT_PROMPT_INJECTION]: The skill involves a workflow where the agent processes user-provided task descriptions. This represents an attack surface for indirect prompt injection. However, because the agent is not provided with any tools, file system access, or network capabilities, the potential impact of such an injection is restricted to the conversation context itself. No boundary markers are used to delimit user input.

estimation-coach