Total 40,623 skills
Showing 12 of 40623 skills
Write property-based tests using Hegel. Triggers on: "property-based tests", "PBT", "hegel tests", "test with random inputs", "generative tests", "test properties", "randomized testing"
Installs or updates Codex CLI, Gemini CLI, and Claude Code. Use when CLI agents need installation or update.
Human reviewer self-review for backend PRs — naming, complexity, DB schema, test design, type precision. Use when user says "review my PR", "check my PR", "human review", or wants design/readability feedback. Applies to any TypeScript backend; pair with pr-review-frontend for full-stack PRs.
Checks manual test scripts for harness adoption, golden files, fail-fast, config sourcing, idempotency. Use when auditing manual test quality.
Creates missing instruction files (CLAUDE.md, AGENTS.md, GEMINI.md), audits token budget, prompt cache safety, cross-agent consistency. Use after setup or when instruction files need alignment.
Google Ads math and forecasting calculations. Activate when the user asks about budget projections, ROAS calculations, CPA targets, conversion forecasts, impression share opportunity, or any PPC-related math. No API credentials needed — works with numbers the user provides.
Watch and analyze YouTube videos using Gemini's video understanding API. Pass any YouTube URL to get summaries, timestamps, Q&A, or detailed analysis of video content — audio and visual.
Scaffold the Antithesis harness: initialize the working directory, write Dockerfiles and docker-compose.yaml with build directives, and prepare to submit your first Antithesis test run.
QQBot Scheduled Reminder. Supports creation, query, and cancellation of one-time and recurring reminders. Used when communicating via QQ channel and involving reminders/scheduled tasks.
Guide for Writing and Optimizing AGENTS.md, following the principle of progressive disclosure. This skill must be loaded when users create, modify, or refactor AGENTS.md, discuss AI agent instruction structures, rule placement, or mention terms like "progressive disclosure", "modularity", "AGENTS.md best practices". Even if users simply say "help me write an AGENTS.md", "optimize this configuration file", or "split the rules", this skill should be used.
Local-first architecture decision framework for web applications. Covers when to go local-first vs server-based vs hybrid, sync engine selection (ElectricSQL, Zero, PowerSync, Replicache, LiveStore, Triplit), client-side storage options (IndexedDB, OPFS, SQLite WASM, PGlite), and conflict resolution strategies (LWW, CRDTs, server-wins, field-level merge). Use when deciding whether to adopt local-first architecture, choosing a sync engine, selecting client storage, or designing conflict resolution strategies.
Route spec content into the correct delta spec file. Reads .spec-driven/specs/INDEX.md first, then decides whether to update an existing spec file, create a new spec file, create a new category, modify requirements, or remove specific requirements.