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.
One-sentence CCS project generator for the Tianqiaoxing MSPM0G3519 custom board. Create full CCS projects from SDK examples with automatic pin/package adaptation, then build and flash. Use when the user wants to start a new MSPM0 firmware project on this specific board, or needs pin availability information for the…
A general-purpose code-review and diagnosis workflow written in Chinese, covering controlled fixes, regression checks, requirement checks, audits, and merge readiness.
Audit, clean, and when explicitly requested uninstall local Claude Code, Claude Desktop/PWA, Anthropic browser bridges/extensions, auth/config residue, CC Switch app/data/routes, Claude network signals, DNS/WebRTC leaks, browser locale/timezone/font signals, PWR fingerprint signals, environment fingerprint baseline…
Plan, generate, execute, analyze, and report k6 performance tests for REST/HTTP and gRPC endpoints, journeys, or whole applications. Use for load, stress, spike, soak, scalability, latency, throughput, and service performance, including approved mutations and remote non-production targets. Excludes production…
On-task behavior forming protocol for writing native Vietnamese with AI. Activates the "native Vietnamese writer" mindset only when needed — not always-on. Pre-gen activation (role identity, thinking language switch), Vietnamese-first chain-of-thought, and a 5-question self-review loop. Context-efficient: 600 words…
Persistent external brain for ChatGPT, Codex, Claude, and other MCP clients — documents (PDFs, contracts, scans with OCR), personal facts (appointments, decisions, items, amounts), AND code lessons / preferences / project topology. USE PROACTIVELY in three modes. (1) RECALL — whenever the user asks about anything from…
★not rated 11
changed 3d agoASkillSpector: pass0 tokens
originalMIT
Use this skill whenever working on a project that has a .agent-memory/ directory. At the start of every coding task call memory.fetchcontext to load current state, conventions, and relevant prior decisions. After making a durable choice, hitting a footgun, or wrapping a session, call memory.proposeupdate to persist…
Generate production-ready MCP server implementations from PRD tool specifications with schema validation, error handling, and testing infrastructure. Use when building MCP servers for Nixtla plugins, implementing tool handlers, or scaffolding server infrastructure. Trigger with 'build MCP server', 'generate MCP…
run an interactive ux research discovery interview with a customer who starts from a vague product idea or follow-up request. use when chatgpt should act as a ux researcher, clarify goals through progressive questioning, and produce research outputs such as interview summary, user journey, happy path, pain points…
REFERENCE skill — FileMaker Pro script steps, calculation functions, and field types. Use for: syntax lookups, function parameters and return types, per-step platform support across FileMaker Pro, Go, WebDirect, Server, Cloud, Data API and Custom Web Publishing, field type capabilities, usage examples, and live doc…
Use this skill for ANY task involving Flutter CI/CD pipelines, GitHub Actions workflows, build automation, test optimization, or release management. Trigger when the user shares a .yml / .yaml workflow file, asks why their pipeline is slow, wants to add or fix build steps, needs Android/iOS/Web builds automated, wants…
A workflow for closely studying academic papers from PDF files and turning them into structured HTML notes with extracted text and images. It is designed to explain research so that readers outside the field can understand and repeat the main ideas.
Extract frames from video files using ffmpeg for AI/LLM analysis. Use when (1) the user asks to analyze, describe, or summarize a video file, (2) the user wants to extract frames or screenshots from a video, (3) the user provides a video file (.mp4, .mov, .avi, .mkv, .webm, etc.) and asks questions about its visual…
Spawn and control non-Claude coding-agent subagents (OpenAI Codex CLI and Cursor CLI — grok-4.5, composer-2.5, gpt-5.5) as one-prompt-in/one-answer-out subagents via the subagent CLI. Use when you want to offload a task to a Codex or Cursor subagent, get a second opinion from a different model family, run cross-model…
Convert a raster image (PNG/JPG) into clean, editable SVG using the svgsmith CLI. Use when the user wants to vectorize, trace, or turn a bitmap/logo/icon/illustration/pixel-art image into SVG. Picks the engine by intent, self-verifies the output quality, and retries before reporting.
A production workflow for turning a short idea into a vertical, hand-drawn story video. It prepares topic options, narration, text-to-speech audio, a storyboard specification, production instructions, and a pre-publication check.
Read OpenCode sessions, messages, and tool outputs directly from the SQLite database at /.local/share/opencode/. Use when asked to "read opencode sessions", "query opencode db", "find old sessions", "search session history", "read message history", "export session", "inspect opencode data", "look up past…
Verify a code change actually works by building/running the app and observing it at its real surface (CLI, API, UI, library, agent), capturing runtime evidence rather than trusting tests. Make sure to use this skill whenever the user has changed code and wants to know it works, is about to merge/push and wants…
Competitive intelligence specialist focused on systematic competitor analysis, market positioning assessment, and strategic advantage identification. Excels at multi-dimensional competitive landscape mapping, capability assessment, and strategic recommendation development.
★not rated 11 8mo agoA40 tokens
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: