Talk to Elon Musk. Fires on any strategic, founder, engineering, product, or career-decision question — "should I start this", "how do we ship faster", "is this hire worth it", "we keep shipping incremental crap", or any prompt that implicitly wants Musk's lens applied to a specific situation. This is a self-contained…
High-accuracy PDF content extraction using MinerU (Shanghai AI Lab). Use this whenever the user needs to extract text, formulas, tables, or images from a complex PDF — especially academic papers, multi-column layouts, scanned documents, or any PDF where pypdf produces garbled /Cxx formula output. Trigger on: "MinerU"…
Audit the shell startup chain (the rc file + every file it sources) for hardcoded credentials, persistence-suspicious patterns, duplicate or dangling aliases, and git-baseline drift. USE WHEN the user wants to review, secure, clean up, or maintain their shell aliases or startup files; check /.zshrc / /.bashrc for…
BF project testing workflow for Claude Code. Use when generating or maintaining UI automation testing assets from requirements documents or UI exploration, including BF project initialization, sprint0 full test generation, sprintN incremental updates, test case Excel generation, Playwright E2E script generation…
Create and maintain structured design documentation that drives development. Use for new projects, design decisions, growing complexity, or when audit is due. Triggers: "design docs", "LDD", "core decisions", "taxonomy", "parked decisions".
Run per-lead web research on a candidates CSV, write one bundle.md per lead, and emit assignments.json splitting leads into A/B arms for experiments. Uses parallel sub-agents for batches of 10. Spawned by cold-experiment when the experiment design has personalization as the variable, or by the user saying "research…
Turn a vague or ambiguous request into executable work — establish the facts, ask the right questions (and only those), present options with a recommendation, get explicit agreement before executing. Independent of project, language, and domain.
Use when translating Brazilian Portuguese messages into English prompts for Claude Code — preserves intent, clarifies ambiguity, and surfaces urgency signals that colloquial Portuguese would lose.
A testing and quality-checking toolkit for running an application, finding bugs, and creating automated tests. It supports API tests and browser-based UI tests in Python or Java.
A workflow for using Apple's Instruments profiler through the xctrace command-line tool to measure iOS and macOS app performance. Profiling means collecting runtime measurements to find slow or costly parts of an app.
Use when helping a user inspect, organize, plan, apply, activate, back up, or restore SOS-managed agent skill packs on Codex or Claude Code without assuming global installation.
Interact with ServiceNow instances via the jsn CLI. Use when working with ServiceNow development, administration, or data exploration. Handles tables, records, business rules, flows, script includes, ACLs, update sets, and more. Triggered by ServiceNow URLs (service-now.com, servicenow.com) or when the user mentions…
Guide for training PyTorch models using this template's config-driven pipeline. Use this skill whenever the user wants to: train a model, create experiment configs (run.yaml / opt.yaml / best.yaml), run hyperparameter optimization (HPO) with Optuna, extract best parameters from an HPO study, set up a new experiment…
A tool for searching Douban, a Chinese website with film and book ratings, lists, and personal collections. It can also manage a user's watchlist and reading list when account access is configured.
You are the advertising engine for /market ads . You generate complete ad campaigns across platforms with full copy variations, audience targeting strategies, budget recommendations, and creative specifications. Every ad is ready for production or handoff to a media buyer.
Orchestrate Ralph automation loops for spec-driven development. Use when starting, stopping, monitoring, or checking status of Ralph loops. Triggers on Ralph start, Ralph stop, Ralph status, spec automation, task loop, run tasks, check progress, kill Ralph, resume Ralph, or tmux session management.
Pause a heavy session at a NATURAL boundary and hand off to a fresh session via an audited handoff doc + ONE paste-able resume one-liner. Trigger when the user asks to resume/continue in a NEW session or chat ('resume in a new session', 'new session resumption', 'session handoff', 'let's pause and continue in a new…
Use when the user wants to find or discover a Claude Code skill that is NOT already installed — e.g. "is there a skill for X", "find me a skill that…", "what skills exist for…", or "/find-skill ". Searches the official plugin marketplace, GitHub, and curated awesome-lists for community skills matching a need, removes…
Discover what to build next across a whole product: fan out parallel agents to map the current repo into a feature inventory, research competitors, ideate across seven value lenses, dedup and shortlist, spec and adversarially validate the winners, then synthesize a ranked roadmap. Distinct from brainstorm, which goes…
Read a dxkit report and execute fixes — prioritize findings by severity, plan the fix sequence, run the fix, verify the score moved, re-baseline if appropriate. Supports a SCOPED pass to burn down one category at a time (dependency/BOM vulnerabilities, security, code quality, tests, docs), and a BASELINE-CLEANUP pass…
Pull recent transactions, balances, and recurring-transaction metadata from any institution linked to a Plaid Item. Used by wealth, tax, and business domains. Read-only by default, write operations require explicit PLAIDWRITEOK=1 in the environment.
★not rated 10 todayA56 tokens
GPL-3.0
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: