Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
A skill for turning a topic or article into a series of Chinese Xiaohongshu posts, where Xiaohongshu is a social platform built around image-and-text notes. It plans and generates 5–18 vertical cards, including a cover, content cards, and a summary.
Detect and redact PII from text files. Supports 15 categories including credit cards, SSNs, emails, API keys, addresses, and more — with zero dependencies.
CLI multiplexer for delegating coding tasks to professional AI coding tools (Claude Code, Codex, Gemini CLI, OpenCode). Use this skill when: Delegating complex coding tasks to specialized AI coding agents Running parallel coding sessions across multiple git worktrees Resuming previous coding sessions to maintain…
Win32 FFI binding lifecycle for @bun-win32/ packages (Win32 DLL bindings via bun:ffi on Windows). Use when generating a new package from a DLL, auditing FFI↔TS↔header consistency, applying the SAL vocabulary (Optional / Nullable , nameout / nameinout), or understanding the bootstrap→catalog→stub→audit→nullcheck…
Use when debugging Vite + Vue local pages with vite-plugin-vue-mcp-next MCP, including DOM, screenshots, console logs, network requests, Vue components, router, or Pinia state.
Safely inspect and archive explicitly selected or clearly disposable Paseo agents and test workspaces. Use when the user asks to preview cleanup candidates, reduce agent-list clutter, or archive explicit test, validation, fixture, or temporary sessions. Ordinary idle agents are resumable and are never auto-archived…
Cut a new release by tagging a version and publishing via GitHub, which triggers the PyPI Trusted Publishing and docs-deploy workflows. Use when asked to "make a release", "cut a version", or "publish".
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…
Analyze ArduPilot DataFlash .bin log files or MAVLink .tlog telemetry logs. Use when the user provides a .bin or .tlog log file path or asks to analyze flight log data.
Enforce exact, pinned package versions across a JavaScript/TypeScript repo and its agent tooling. Scans package.json dependencies, npm scripts, MCP server configs (.mcp.json, Claude/Cursor settings), and CI workflows for unpinned specs (^, , , latest, missing versions on npx). Pins everything to exact versions…
Design thinking with forcing questions, anti-sycophancy, adversarial review. Reads past decisions and mistakes to avoid re-debating and front-load failure patterns.
Run Salesforce Code Analyzer on Apex, Trigger, Flow, or metadata files. Use after writing or modifying .cls, .trigger, .xml, or flow files. Also use when asked to scan, lint, or check code quality.
Operate the belt CLI to evaluate headless coding agents (Claude Code, Cursor, Codex, Gemini, and others) end to end. Use when the user asks to write or run eval scenarios, compare agents, score outputs with rules or LLM judges, register a new agent adapter, interpret reports or benchmark cards, or set up evals in CI.…
A one-time deployment tool that adds a project governance system built around AGENTS.md, project instructions, documentation, hooks, continuous integration, and maintenance scripts.
Full workflow for translating an academic paper PDF into a polished, self-contained HTML with a three-way view toggle (Chinese-only / bilingual / original-only). Covers document triage (native vs OCR'd-scan vs no-text-layer scan), column-aware text extraction, glossary building with web-verified standard term…
Use this skill when the user wants shorter, more direct responses. Activate on: "crisp mode", "go crisp", "/crisp", "be brief", "less tokens", "cut the fluff", "shorter answers", "stop being verbose", "drop the filler", "skip the pleasantries", "no fluff", "just the answer". Do NOT activate for: "explain in detail"…
Best practices for building and maintaining applications with PowerSync: Cloud and self-hosted setup, sync configuration, client SDK usage, backend integration (Supabase, custom Postgres, MongoDB, Azure DocumentDB, MySQL, MSSQL), schema changes, watch and reactive queries (useQuery), attachments, the upload queue, and…
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: