Built for context-aware security review of MCP servers, AI agent skills, coding-agent plugins, and CLI extensions. It compares a repository's stated purpose with actual files, permissions, network calls, env var access, install scripts, and tool definitions, then returns an evidence-backed install-risk brief with severity, confidence, permission map, least-privilege notes, and a practical install decision.
Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
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.
Analysez logs, diagnostics, erreurs et éléments techniques fournis afin d’identifier des causes probables, prioriser les anomalies et préparer un plan de correction.
AI 做的網站能跑，不代表敢上線。上傳已移除敏感資料的程式檔、ZIP、Diff 或設定截圖，取得 GO／先修／STOP、最優先的 3 個問題，以及可直接貼回 AI 開發工具的修復指令。
Stop guessing at competitor strategy. This skill runs a full pipeline: enter a product URL or description, and it researches real competitors, compares pricing, mines actual reviews for buyer complaints, finds competitor weaknesses and keyword gaps, then builds a differentiation strategy and writes the final listing — all grounded in real data. Safeguard: it never invents competitor prices, reviews, or stats; if data can't be retrieved, it asks you for it instead of making it up.
Turn your AI pilot data into a traceable decision pack with TCO, ROI, NPV, payback, sensitivity analysis, evidence gaps, risks, and clear next steps.
Review an AI Skill before installation or publication. Get a concrete verdict with evidence, permissions, secret risks, license constraints, and the safest next step.
This Skill is built on practical expertise in AI agent safety, prompt-injection defense, source-to-sink privacy review, tool and MCP metadata integrity, memory provenance checks, autonomous action scoping, and evidence-based verification. It helps agents separate instructions from evidence before tool calls, uploads, publishing, deletion, code execution, or network output.