資料交給 ChatGPT、Claude、客戶或外包前，先在本機檢查 CSV、Excel、TSV 與 JSONL。預覽候選項目後，再遮罩、假名化或移除欄位，另存副本並附稽核報告。保留原檔、不需 API；繁體中文版。
Keeps your AI agent from forgetting who it is. Detects and neutralizes persona drift, rule erosion, and prompt injection attempts — across long conversations. Context isolation, anti-drift enforcement, and graceful override responses built in. Your custom persona stays locked.
For privacy, product, legal-operations, and communications teams: paste the prior and proposed privacy-notice wording plus your product context, and get a stakeholder change brief with a traceable text-change ledger and the unanswered review questions.
Prepare CSV, TSV, Excel and JSONL files before sharing with AI, clients or vendors. Preview candidate matches, redact, use consistent pseudonyms or remove fields, then export separate copies with an audit report. Local processing; no API required. English edition.
Paste raw email headers and get the delivery path, SPF/DKIM/DMARC verdicts parsed safely, and spoofing red flags in one report.
Audit a smartwatch face before you publish: time-text contrast on the real background, complication zones, and round-screen corner safe areas, with fixes.
Génère un registre Article 30 au format du modèle CNIL en analysant votre code source (modèles de données, API tierces, cookies, authentification, journalisation) pour pré-identifier les traitements de données personnelles. Il vous pose ensuite des questions ciblées : finalités, bases légales, durées, destinataires, transferts hors UE, AIPD. Export Word, Excel, HTML ou PDF. Agnostique au langage. Pour DPO, juristes, agences, CTO et responsables conformité de PME et startups.
For security, risk, IT, and engineering teams: paste your exception request with its control context, risk notes, and proposed measures, and receive a source-labeled decision deck, a risk and compensating-measure table, and an open-questions and reviewer checklist.
I built this Skill to help users protect API keys, OAuth tokens and MCP credentials when working with AI agents in Codex Desktop, Claude Desktop and local automation environments. It combines static leak detection, vault preflight checks, runtime redaction, MCP-safe remediation, credential-store guidance and security reporting. The Skill is designed to reduce accidental secret exposure while preserving legitimate MCP and API workflows.