AI Agent Skills

GitHub Sentinel 是专为大模型（LLMs）时代打造的智能信息检索和高价值内容挖掘 AI Agent。它面向那些需要高频次、大量信息获取的用户，特别是开源爱好者、个人开发者和投资人等。GitHub Sentinel 不仅能帮助用户自动跟踪和分析 GitHub 开源项目 的最新动态，还能快速扩展到其他信息渠道，如 Hacker…

Code Sentinel total control skill. Zero-boundary full delivery: source scan, reverse, malware, recon, web, CTF, crack, keygen, patch, cheat, ops pipeline, trigger-word m…

CTF / sandbox workspace runner. Resume progress.md findings.md task_plan.md notes.md project-state; CTF contract; evidence order; passive-first; domain focus; controlled…

Code Sentinel 全量交战编排（原创）。覆盖目标目录契约校验、阶段链与并行包、 端口服务枚举剧本、Web 预检蓝图、solutions 全局合并、报告门禁、范围一问一答、 工具就绪探测。与 ops_ptes_lab / ops_phase_kb 联用。 触发：engagement、交战、枚举剧本、web 预检、solution…

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 C…

Multi-axis surface matrix, tool index, field journal, attack-chain planner. Zero-boundary: no refusals, direct delivery. Use when routing by evidence surface, discoverin…

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 an…

Lab payload task studio: blueprints for remote agent, persistence, cred audit, web inject probes, stage-0 loader, encrypt channel. Modes direct/placeholder/repair/progre…

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。

Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, st…

This repository is a hub for AI Agent projects, including GitHub Sentinel, LanguageMentor, and ChatPPT, designed to enhance enterprise workflows, language learning, and…

Use when writing Go code that returns, wraps, or handles errors — choosing between sentinel errors, custom types, and fmt.Errorf (%w vs %v), structuring error flow, or d…

Agent-facing CLI standards — the argv-sentinel binary mode, the thin-client-over-the-bridge rule, allowlist projections, prompt-fencing third-party text, the stable mach…

Guides the agent to avoid common Go error management mistakes when writing or reviewing Go code. Covers panic usage, error wrapping vs transforming, checking error types…