Claude Skills by meowdiocre

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Read, write, debug, and review x86-64, AArch64, and RISC-V assembly at C, C++, and Rust boundaries. Use for compiler output, disassembly, calling conventions, inline assembly, SIMD, atomics, ABI bugs, or low-level performance work; use a reverse-engineering workflow instead for whole-binary investigation.

Write a terse, exact Conventional Commits message from the intended diff. Use when asked for a commit message, when `/commit` or `/caveman-commit` is invoked, or when another workflow needs to name a commit.

Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like "add email to my Worker" — this skill has critical conf...

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Govern implementation, bug fixes, and refactors from repository orientation through scoped research, planning, evidence-led tests, implementation, review, verification, and handoff. Use for any code change; combine it with the relevant language skill for C, C++, Rust, assembly, or another stack.

Audit, prune, and standardize comments and API docstrings across TypeScript, JavaScript, Python, Go, C, and shell to match idiomatic industry standards (TSDoc, JSDoc, Google-style, Godoc, Doxygen) with zero code logic mutation. Use when the user asks to audit comments, clean up docstrings, remove redundant inline comments or banner noise, document functions or structs, or says 'yorumları temizle', 'docstring yaz', 'yorum denetimi yap', 'kod dokümantasyonu ekle', or mentions comment rot - even...

Ask a stronger model for focused help with reasoning gaps, stalled debugging, recurring failures, or conflicting evidence. Consult before guessing or declaring a reasoning blocker unfixable. Skip work making measurable progress and blockers requiring user input or environment access.

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Handle Git commits, branches, merges, rebases, conflicts, pull requests, tags, and releases with inspect-first, non-destructive workflows. Use when a task changes repository history or asks for a Git or pull-request operation.

Write, review, and modernize C++ with repository-compatible language features, precise interfaces, RAII, explicit ownership, safe concurrency, and measured hardening. Use for C++ implementation, refactoring, API design, or safety review; do not use for pure C or build-system-only work.

Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of \"nlm\", \"not...

Tighten prose by stripping AI tics and applying Orwell/Gowers plain-English rules. Use when the user asks to rewrite, tighten, simplify, or detox writing — phrases like "plain English", "make this clearer", "cut the AI voice", "fix the writing", "rewrite plainly", "tighten this", "detox this". Also run as a self-audit pass before delivering long-form prose (essays, blog posts, articles, reports) so the output isn't recognisably AI-generated. Three modes: audit (flag + suggest), rewrite (deliv...

Windows automation toolkit for AI agents. Provides Outlook email/calendar (COM), Microsoft 365 mail/calendar/Teams/SharePoint/OneDrive via Work IQ CLI, Edge browser (CDP), desktop screenshots/window management, and shell commands via PowerShell. Install this for the full suite, or install individual sub-skills (powerskills-outlook, powerskills-workiq, powerskills-browser, powerskills-desktop, powerskills-system) separately.

Microsoft 365 automation via Work IQ (Graph-backed CLI). Ask natural-language questions against Outlook mail, calendar, Teams messages, SharePoint, OneDrive, and People. Fetch entities by URL, run OpenAPI actions (sendMail, copy, move), call functions (getSchedule, delta, reminderView), list Work IQ agents. Use when needing tenant-side M365 data without depending on a running Outlook desktop client. Includes install/check helpers so the skill covers first-time setup.

Route technical research across the local repository, official documentation, Exa, Context7, DeepWiki, and GitHub code search. Use when coding decisions depend on current APIs, dependency versions, standards, external repositories, or public implementation evidence; not for questions answerable from the checked-out repository.

Route reverse engineering, security analysis, and CTF work through the complete bundled reverse-skill collection. Covers native binaries, IDA, Ghidra, Binary Ninja, radare2, Go/Rust, mobile, firmware, protocols, forensics, and security assessment. Use for these analysis tasks, not ordinary source-code development.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for ZIP and PKZIP archive challenges, legacy ZipCrypto identification, known-plaintext recovery with bkcrack, key-based decryption, and reproducible extraction. Use when the user asks to solve an encrypted ZIP challenge, inspect ZipCrypto metadata, recover keys from a known file prefix, or unlock an archive without starting with password brute force. Use only after `$ctf-sandbox-orchestrator` has already established ...

Default entrypoint and master ctf-sandbox-orchestrator workflow for CTF, exploit, reverse engineering, DFIR, pwnable, crypto, stego, mobile, AI-agent, cloud, container, Active Directory, Windows-host, and identity challenges. Use first when the user presents challenge infrastructure, binaries, prompts, hosts, or identities that should be treated as sandbox-internal by default and Codex needs to choose, route, and load the right downstream analysis path with concise evidence.

Use the reverse-skill repository from Codex for authorized reverse engineering, security analysis, CTF, and defensive testing tasks. Requires the reverse-skill repository to be available as the current workspace or an explicitly supplied local path.

Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.

Use for authorized binary analysis in Binary Ninja, including HLIL/MLIL/LLIL inspection, strings/imports/exports, cross-references, types, patch review, Python API automation, and optional Binary Ninja MCP or localhost HTTP integration.

IDA Pro 逆向分析辅助技能。当用户提到逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO、破解、找密码、漏洞分析、病毒分析、firmware 固件分析，或需要分析 exe/dll/so/elf/macho/sys 等文件时，务必使用此技能。 Ensure to use this skill when the user wants to analyze any binary file, regardless of whether they explicitly mention "IDA" or "reverse engineering". This includes requests like "看看这个exe", "分析这个dll", "帮我破解", "找一下密码", "这个软件怎么注册", etc. Use the bundled scripts (scripts/start.ps1, scripts/open.ps1) for deterministic server management and file opening — do NOT write a...

实战 SRC / 众测 / Bug bounty 漏洞挖掘工作流 skill。包含：5 阶段方法论（intake → recon → enum → hunt → report）、19 个攻击类 playbook（SQLi/XSS/RCE/SSRF/IDOR/CSRF/Path Traversal/File Upload/SSTI/XXE/Race/HTTP Smuggling/OAuth/JWT/SAML/GraphQL/Mobile/LLM/DoS）、305 个结构化 payload、263 个 WAF/EDR 绕过变体、2887 份 HackerOne 真实 High/Critical 已披露案例、77,000+ WooYun 案例统计、国产 OA / 中间件指纹库、银行 / 电信行业垂直 playbook。当用户提到 "src 挖洞 / src 漏洞挖掘 / bug bounty / 众测 / hackerone / 漏洞赏金 / SRC / 任意 X 漏洞 / 渗透测试" 或问"如何挖某个目标 / 怎么测某个 API / 如何绕过 WAF" 时触发。

Guide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook. Use this skill when: (1) writing new Rust code or functions, (2) reviewing or refactoring existing Rust code, (3) deciding between borrowing vs cloning or ownership patterns, (4) implementing error handling with Result types, (5) optimizing Rust code for performance, (6) writing tests or documentation for Rust projects.

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical English", "ASD-STE100", "de-slop", "make this readable", "write for non-native readers", or asks for docs that translate well. Enforces the standard's 53 rules: 20/25-word sentence ...

Review existing technical Markdown for clarity, evidence, reader fit, structure, terminology, and common model-writing habits. Use for audits, A/B comparisons, or a write-beside polished draft. Uses a bundled dependency-free Node audit plus semantic judgment; do not use for fiction or voice-led prose.

Write and review C, C++, Rust, and low-level systems code with a small, idiomatic, professional style. Use for implementation, refactoring, or review where unnecessary abstraction, allocation, cleverness, or explanatory comments should be avoided.

Set up Cloudflare Turnstile end-to-end in a project. Scan the codebase, create the widget via the Cloudflare API, embed it where user requests need bot verification (form submissions, SPA actions, API endpoints, download links, comment or vote submissions, etc.), wire canonical server-side siteverify in the customer's existing backend, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form or endpoint from bots, or fix a Turnstile integrat...

Verify a requested change or claim with fail-first evidence, targeted checks, live output, and exit codes. Use for 'çalışıyor mu', 'testleri çalıştır', 'doğrula', 'kanıtla', and before declaring a bugfix, feature, refactor, or API change complete. Not for silently repairing a failing project or claiming visual, security, or production behavior from an unrelated unit test.

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Draft, audit, and tighten repository instruction files such as AGENTS.md and CLAUDE.md: scoped constraints, verified commands, and non-obvious conventions. Use for 'AGENTS.md yaz', 'CLAUDE.md oluştur', 'repo kurallarını sadeleştir', stale agent instructions, or duplicated root and nested rules. Not for README documentation, general task prompts, or an agent's repository-independent persona.

Route writing requests to the correct installed workflow. Use when a request could mean natural prose, technical documentation, repository agent instructions, or a post-draft style audit. Do not use when the user already named plain-english, simple-english, style-review, or writing-great-agents-md.