Loading...
Loading...
Found 5,651 Skills
Start here for first-time CARTO use — install the CLI, authenticate, switch profiles, understand JSON output and async job patterns. Also orients on the two parallel access paths into the CARTO platform (CLI for authoring/scripting, MCP server for inline interactions in chat hosts) and which skills cover each.
Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now or I'm stuck or I don't know what to do
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.
After the task execution is completed, prompt the user to open a new Agent to review the uncommitted git code. Athletes should not act as referees; proceed with the wrap-up only after the review is approved.
Use when an approved Spec Kit `spec.md` must be translated into technical design artifacts (`plan.md`, `research.md`, `data-model.md`, `contracts/`, `quickstart.md`) before `spec-kit-tasks`, or when `plan.md` is missing/outdated after spec or constitution changes.
(macOS, requires schedule-manager) This skill is for users who want to write diary entries or daily logs. Trigger phrases include "Help me write a diary", "Record today", "Write a diary", "Today's diary". It integrates with Reminders for task review and planning.
Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false
[Tooling & Meta] Compress conversation context to optimize tokens
Task Capture Assistant - A pure task execution recording tool focused on real-time capture with zero-friction startup. Follows the principle of "Separation of Capture and Processing": only records, no review during startup. Triggers: /task-capture, /capture, /record
Automate Apaleo tasks via Rube MCP (Composio). Always search tools first for current schemas.
Use when creating custom React Flow nodes, edges, and handles. Covers custom node components, resizable nodes, toolbars, and advanced customization.
Automate Coinranking tasks via Rube MCP (Composio). Always search tools first for current schemas.