distil-pii-redactor

# Distil PII Redactor Use this skill when the user asks to redact, anonymize, sanitize, or remove PII or personal data from text. It runs a local Distil-PII GGUF model through `llama-server`; raw text must not be sent to external APIs. ## Privacy Rules - Do not quote, summarize, or repeat raw PII in chat. - Prefer file-based input and output when the sensitive text is already in a file or attachment. - Return only the redacted text unless the user is explicitly debugging the redactor itself. - If the user asks for only the LLM or redaction output, do not narrate setup, server status, tool use, or validation details in the final response. - Do not use `--show-entities` in normal workflows. It emits original values. - Do not store raw PII in tracked files, shell history, long-lived notes, or logs. - This skill declares no external credentials. If a downstream tool needs authentication, use that tool's HybridClaw `secret_ref` or gateway secret injection and pass only redacted text downstream. - Do not convert raw PII into HybridClaw secrets. Secret refs are for credentials and auth material, not a transport for user data. ## Setup If `llama-server` is missing, install it with: ```bash hybridclaw skill install distil-pii-redactor llama-server ``` or install `llama.cpp` manually. This skill intentionally has no `credentials:` frontmatter because local inference does not need API keys; any future remote-provider variant must declare `secret_ref` credentials ins...