Read an electrical plan (napkin photo, PDF, or text) like a senior estimator and turn it into an accurate, code-grounded work estimate. Use WHEN analysing an electrical object to decide how many circuits are needed and — critically — which CABLE GAUGE each run needs based on what it feeds, because the install price…
Audit AI agent skills for security vulnerabilities. Use when scanning installed skills against the OWASP Agentic Skills Top 10, checking skills before running them, gating CI/CD on skill safety, or generating audit reports (text, JSON, SARIF, HTML) for stakeholders.
A guide for structuring iOS applications using clean architecture, an approach that separates user-interface code, business rules, and external services. It also covers local Swift packages and package dependencies.
Zotero koleksiyonları ile Google NotebookLM defterleri arasında iki yönlü senkronizasyon sağlar. Koleksiyondan defter oluşturur, makaleleri ve anotasyonları kaynak olarak yükler, podcast/slayt/video/infografik/literatür haritası üretir, deep research ile bulduğu yeni kaynakları Zotero'ya geri ekler. Kullanıcı bir…
Plan an Odoo module version upgrade (e.g. 16.0 to 19.0, 17.0 to 19.0) by first checking the Odoo Apps Store for a free ready-made replacement, then auditing the manifest, models, views, data records (cron/server actions), security, SCSS/CSS and JS on two axes — what changed upstream in the real odoo/odoo and…
Act as the architectural brain of a multi-agent engineering operation — investigate an unfamiliar, large, or legacy codebase, model how it really works, diagnose root causes instead of symptoms, design the minimal architecturally-correct change, decompose it into scoped task contracts with a dependency DAG, persist…
CFAR rationality technique for installing reliable automatic behaviors by pairing specific triggers with specific actions. Based on implementation intentions research (0.65 SD effect size). Use when the user: (1) wants to build a new habit or change a behavior, (2) knows what they should do but keeps forgetting or…
A structured review of a coding-agent skill file, usually named SKILL.md. It checks the file against published standards and produces a scored report with specific fixes.
Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Covers harness choice, context discipline, cleanup, review loops, launch pressure, and security basics.
A security review method for an external coding-agent skill file. It looks for prompt injection, credential theft, unsafe code execution, misleading names, and social-engineering tactics before installation.
Discover, install, and run reusable AI prompt skills from the BetterPrompt registry via the CLI (betterprompt / bp). Use when a user needs to find a prompt skill, generate AI output (text, images, video), or manage their skill library. Covers installation, auth, skill discovery, generation, and output review for…
Automated lifecycle management for non-bundled Hermes skills. Scans all skill directories, migrates orphans to userskills/, registers in userskills.json, detects merge candidates via multi-dimensional similarity, and optimises SKILL.md format. No SOUL framework dependency — works on any standard Hermes Agent…
Search Israeli movie showtimes, ratings, and cinema info from seret.co.il. Use when user asks about movies playing in Israel, Israeli cinema showtimes, "ma makrineem hayom", "sratim hadashim", "seret", movie tickets in Israel, what's showing in theaters, or upcoming Israeli film releases. Fetches real-time data from…
Extract EastMoney sector fund-flow data from data.eastmoney.com/bkzj using browser-harness and Chrome CDP network interception. Use when Codex needs EastMoney industry sector list data, sector fund-flow rankings, or historical sector fund-flow detail data, especially requests mentioning bkzj, hy.html…
Generic poller for any remote review / CI system (Gerrit, GitHub PR, Jenkins, custom HTTP). Memory-first → user-ask. Plugin-shipped, called by submitter step 6.
Run user-created frontend/backend/WebSocket services and expose them through Cloudflare by default when the user asks to start, deploy, preview, share, or make the service accessible. Local-only is allowed only when explicitly requested.
Build a professional, precise visual identity (brand identity) for a project, startup, or business — logo direction, color system, typography, application mockups — via a structured 9-stage agency workflow ending in two polished deliverables — a Brand Identity Guide and a Design Language System (built with the docx…
CTF pwn solving workflow for Codex with tmux-CLI-driven persistent-GDB live debugging: protection checks, libc/loader matching, IDA or idalib reverse engineering, pwntools wrappers, mandatory GDB-pwndbg inferior-tty step debugging, heap/stack/libc state inspection, and exploit strategy selection by primitive, glibc…
★not rated 5 3mo agoA84 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: