Loading...
Loading...
Found 1,320 Skills
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Memory available` hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.
Loads the full ***plain language reference into context: syntax, section types (definitions, implementation reqs, test reqs, functional specs, acceptance tests), concept notation, frontmatter (import/requires/required_concepts/exported_concepts), templates, linked resources, module model, and authoring best practices. Use whenever authoring, editing, reviewing, or debugging .plain files, or before invoking any other skill that reads or writes .plain content.
Analyze two functional specs from a ***plain spec file to determine if they conflict. Use when the user wants to check whether two specific functional requirements are compatible, or when debugging a suspected conflict between two specs.
Used for thread-aware debugging of FreeRTOS/RT-Thread/Zephyr, such as viewing task lists, stack watermarks, or detecting deadlocks.
Used when performing GDB debugging on target boards via PlatformIO's built-in debugging features, supporting download-and-halt, attach-only, and crash context analysis.
JavaScript reverse engineering and browser debugging MCP server with anti-detection and agent-first tooling
Use this skill when the user asks about a Goldsky Compose field, flag, type, or API shape — lookup reference for compose.yaml fields, every `goldsky compose` CLI flag, the TaskContext API (env, fetch, callTask, logEvent, evm, collection), wallet APIs (smart wallet, BYO EOA), gas sponsorship, contract codegen, dashboard URL, and pricing. Triggers on: 'compose.yaml fields', 'cron syntax for compose', 'http trigger auth', 'onchain_event format', 'TaskContext API', 'evm.wallet options', 'sponsorGas default', 'IWallet methods', 'Collection methods', 'compose codegen', 'compose pricing', 'compose status JSON output', 'goldsky compose flags'. Consult before suggesting a field, flag, or API shape — avoids hallucinating nonexistent options. For step-by-step building, use /compose. For debugging, use /compose-doctor. Do NOT trigger on Turbo, Mirror, Subgraphs, or Edge lookups — those belong to their own reference skills.
VSCode extension for Browser DevTools MCP Server enabling AI-driven browser automation, debugging, and testing via Playwright and Model Context Protocol
Cursor IDE extension providing development tools for 1C:Enterprise 8 ecosystem with command palette, task tree, and debugging support
Browser DevTools extension for debugging HTMX applications with request inspection, element tracking, event timeline, swap visualization, and error detection
Iterate on RAG systems with structured evals instead of eyeballing. This skill should be used when the user is tuning a RAG pipeline — changing retrieval prompts, swapping models, adjusting chunking, or debugging poor answers — and wants a cheap, ranked set of experiments with cost tracking and structured feedback on the stack. Also use when the user asks "how do I know if my RAG is working?", "this RAG eval is burning money", or "what should I try next on retrieval?".
Use this skill whenever the user is working with the Pydantic AI framework — including building AI agents, defining structured outputs with Pydantic models, wiring up tools/function calling, configuring model providers (OpenAI, Anthropic, Gemini, etc.), managing dependencies via agent context, handling streaming responses, or debugging agent runs. Trigger this skill even for adjacent tasks like "how do I make my agent return JSON", "set up a multi-step agent", "add a tool to my agent", or "validate LLM output with Pydantic" — any time Pydantic AI is mentioned or implied as the target framework.