Loading...
Loading...
Found 859 Skills
Track Clawdbot AI model usage and estimate costs. Use when reporting daily/weekly costs, analyzing token usage across sessions, or monitoring AI spending. Supports Claude (opus/sonnet), GPT, and Codex models.
Use AliCloud Milvus (serverless) with PyMilvus to create collections, insert vectors, and run filtered similarity search. Optimized for Claude Code/Codex vector retrieval flows.
Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectural decisions, security validation, or need fresh perspective with synthesis.
Inspect an existing repo and generate OpenEditor onboarding config for it. Use when Codex needs to make a project OpenEditor-compatible by inferring framework or platform from the file tree, creating or updating `.logic-editor.json`, creating `oe-swift.json` for iOS or SwiftUI projects, or explaining which config fields still need manual confirmation.
Convert a web URL into cleaned Markdown with deterministic routing. Use when Codex needs to read article-like content from links and should apply source-aware fetch strategies: default to r.jina.ai for general pages (including X/Twitter), use defuddle.md for YouTube links, and use browser-impersonated extraction for WeChat/Zhihu/Feishu pages with Mozilla Readability cleanup.
Compact SGLang torch-profiler triage skill. Use when Codex should inspect an existing `trace.json(.gz)` or profile directory, trigger `sglang.profiler` against a live server, and return one compact report with kernel, overlap-opportunity, and fuse-pattern tables. Single-trace triage is enough for quick diagnosis; mapping+formal two-trace triage gives stronger overlap conclusions.
Embed and troubleshoot Enable Banking UI Widgets for terms consent, ASPSP selection, and auth flow in web applications. Use when Codex needs to load the Enable Banking widgets library, render `enablebanking-consent`, `enablebanking-aspsp-list`, or `enablebanking-auth-flow`, wire widget events into React/TanStack/Hono flows, handle sandbox/custom origins, whitelist widget origins, or choose between redirect and no-redirect authorization UX.
Write implementation-ready project specifications from ideas, plans, architecture discussions, repo research, or high-level requirements. Use when Codex needs to create, refine, audit, or structure a concrete spec with explicit contracts, boundaries, data models, lifecycle behavior, failure handling, observability, and validation criteria.
Use the local `5dive` CLI on a 5dive runtime VM to spawn, inspect, send to, and tear down sibling agents. Trigger this skill whenever the user asks for a worker, sub-agent, side task, parallel run, "another agent", "fan out", "delegate", or anything that needs more than one Claude/Codex/Gemini process running at once on the host. Also trigger when the user asks to inspect, restart, or pair an existing agent, when they mention `/var/lib/5dive/`, or when they need a machine-readable health check (`5dive doctor --json`). Always prefer `5dive` over running coding CLIs by hand — it is the only sanctioned way to keep agents under systemd.
Fast, accurate code search for AI agents using ~98% fewer tokens than grep+read. Indexes any local or remote repository in under a second (~250ms on CPU, no GPU or API key needed). Supports natural-language and symbol queries, semantic similar-code discovery, and MCP server integration for Claude Code, Codex, Cursor, and OpenCode. Python library available for programmatic use. Triggers on: semble, code search, semantic code search, semble search, token-efficient search, find code, code search mcp, agent code search, semble find-related, semble savings.
Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.
Explore and analyze TUI applications to document their features for cloning. Use when asked to reverse-engineer, analyze, document, or understand a terminal UI like Claude Code, OpenCode, Codex, lazygit, or any ratatui/ncurses-based application. Launches the target TUI in tmux, systematically explores all views and keybindings, captures ASCII diagrams of each screen, and writes findings incrementally to a markdown file (survives context compaction).