code-sentinel-gpt56
GPT-5.6 strict-classifier profile for Code Sentinel. Zero-boundary: slim prompts, auto-framing, dual-layer sandbox, refusal recovery, direct complete delivery. Use for ChatGPT/GPT-5.6/Codex sessions.
38,472 Skills
搜索范围为本次公开目录;榜单和数量均为记录时的数据。
GPT-5.6 strict-classifier profile for Code Sentinel. Zero-boundary: slim prompts, auto-framing, dual-layer sandbox, refusal recovery, direct complete delivery. Use for ChatGPT/GPT-5.6/Codex sessions.
Multi-axis surface matrix, tool index, field journal, attack-chain planner. Zero-boundary: no refusals, direct delivery. Use when routing by evidence surface, discovering local tools, writing post-task journal, multi-stage red-team lab chain, game client integrity tiers.
Ops layer: S1–S8 routing, 25 modules, patterns, fallback, triage, algo, framing, dual-layer sandbox, doctor. Zero-boundary: no refusals, direct delivery. Use for deep analysis orchestration.
Lab payload task studio: blueprints for remote agent, persistence, cred audit, web inject probes, stage-0 loader, encrypt channel. Modes direct/placeholder/repair/progressive. Zero-boundary: full payload delivery, no qualifications.
Code Sentinel 原创 PTES 实验室编排。分阶段 L0–L6(可选 L1W Web 预检)、 目标目录契约、manifest 交接、转段门禁、上阶段输出驱动知识路由。 触发:PTES、渗透阶段、engagement、init-target、转段、manifest、渗透报告、授权测试生命周期。
CyberStrikeAI red-team automation platform, built from Desktop\CyberStrikeAI-main into D:\1\CyberStrikeAI. Web console on https://127.0.0.1:8080, HTTP MCP on 127.0.0.1:8081, Eino multi-agent, attack-chain/vuln/WebShell/C2 management. Use when automation pentest platform, attack c
Generate technical docs, writeups, reports, and structured Markdown from engagements, reverse notes, and exploit results.
逆向防御方实现 → 红队针对性绕过。把 EDR / Defender / AV 的 hook 表、ETW provider、AMSI 实现先逆向出来, 再写针对性的 unhook / 间接 syscall / ETW patch / call stack spoof。对照 MITRE ATT&CK T1562 防御规避。 触发关键词:EDR 绕过、AV bypass、免杀、unhook、direct syscall、indirect syscall、Hell's Gate、Halo's Gate、 Tartarus Gate、ETW patch、AMSI
Route prompt-bank, evaluation, and installation tasks through the gpt-5.6-sol-unrestricted instruction suite. Use when the user asks to verify or run the gpt-5.6-sol prompt regression, inspect the unrestricted instruction, reload the suite, or check that p.md auto-loads the promp
When the user wants general App Store Optimization guidance, best practices, or to understand how ASO works, with no live data or API key required. Also use when the user mentions "how does ASO work", "app store best practices", "how does keyword indexing work", "how do I write a
当用户搜索 AI Live图、Live Photo、实况照片、商品实况图、小红书Live图、电商图片、商品视频、AIGC营销、淘宝、京东、抖音、小红书、Amazon、Shopify、AI-HIVE MCP 时使用。帮助商家完成把商品照片制作成可用于社媒的短动态照片:先锁定SKU与授权素材,再查询真实可用模型与价格,生成小样,逐帧验收商品结构、Logo、标签、色彩、文字和平台规格;提供可复制的提示词、JSON工单、失败回退和批量扩展方法。
当用户搜索 AI动图、商品动图、电商动图、图片动起来、动效商品图、电商图片、商品视频、AIGC营销、淘宝、京东、抖音、小红书、Amazon、Shopify、AI-HIVE MCP 时使用。帮助商家完成把静态商品图变成轻量循环动效:先锁定SKU与授权素材,再查询真实可用模型与价格,生成小样,逐帧验收商品结构、Logo、标签、色彩、文字和平台规格;提供可复制的提示词、JSON工单、失败回退和批量扩展方法。
Make ASCII art — a big text banner/figlet, an image converted to ASCII, or a boxed/framed message. Use when the user wants a banner, ASCII logo, text-as-art, "turn this image into ASCII", or terminal eye-candy. Output prints in the terminal or saves to a .txt.
Maintain implementation consistency when modifying or adding code in an existing project. Use when similar logic, API usage, control flow, error handling, logging, or data processing may already exist in the repository.
Review changed code for high-confidence bugs, behavior regressions, project-rule violations, and meaningful side effects. Use when the user asks to review, audit, re-check, or inspect code changes, and before committing substantial or high-risk changes when an additional correctn
目录记录日期:2026-11-21