2.2K skills · sorted by relevance
Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.
Patterns for vibe coding that produce production-quality output instead of garbage. Covers prompt engineering for AI coding, verification without reading every line, accept/reject/refine decision framework, architectural guardrails, context management (CLAUDE.md, .cursor/rules), TDD-driven vibe coding, screenshot-driven development, diff review discipline, and the anti-patterns that destroy quality. Activate on: "vibe coding", "AI coding quality", "Claude Code workflow", "AI-assisted development", "how to use AI for coding", "coding with AI", "agentic engineering workflow", "AI code quality", "vibe code without garbage", "production quality AI code", "CLAUDE.md setup", "cursorrules setup", "pre-commit hooks for AI", "TDD with AI", "test-driven vibe coding". NOT for: multi-person collaborative coding sessions (use cooperative-vibe-coding), building AI/LLM applications (use ai-engineer), prompt engineering for non-coding LLM use cases (use prompt-engineer).
The English summary is being prepared. Showing the original description.
Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.
Run AI coding command-line tools on behalf of worker agents using their prepared prompts and workspaces. Detect available tools, configure delegation, return results, and apply supported execution controls such as time budgets and permission settings.
Design the operating layer around a coding agent so it can read and edit code, run checks, and correct errors. Define completion criteria, permission boundaries, feedback, and recovery methods, and assess which tasks suit autonomous execution.
Cooperative vibe coding across machines — real-time collaborative development with humans and AI agents. Covers current tools (Live Share, Code With Me, Zed, Cursor multiplayer, tmux), git-based async patterns, AI agent coordination, and the aspirational future of multi-human multi-agent development. Activate on: "pair programming", "vibe coding together", "collaborative coding", "mob programming", "remote pairing", "code together", "multiplayer coding", "Live Share", "Code With Me", "ensemble programming", "cooperative development". NOT for: building a real-time collaboration ENGINE (use real-time-collaboration-engine), git workflow mechanics (use git-best-practices), single-user AI coding assistance (use prompt-engineer).
The English summary is being prepared. Showing the original description.
Mint a new YYYY-MM-DD-exact-coding-baseline snapshot under research/workflow-dev/export/. Detects the current best correctness- oriented workflow from research/workflow-dev/workflow-construction.md (or takes an explicit source-workflow argument) and transforms it from a lab workflow into a consumer-ready one on three axes: strips lab-only measurement content, re-enables human-in-the-loop checkpoints, and converts auto-loading config into an explicitly-invoked skill. Supports both promoted EXACT Coding lines: Opus/Hybrid and SOL/Predictive TDD. Exports Claude Code, pi, OpenCode, cursor-agent and, for SOL, Copilot. Trigger when the user says "exact-coding baseline export", "neue exact-coding baseline", "exact-coding-baseline-export", or asks to refresh the baseline snapshot.
The English summary is being prepared. Showing the original description.
Cooperative vibe coding across machines — real-time collaborative development with humans and AI agents. Covers current tools (Live Share, Code With Me, Zed, Cursor multiplayer, tmux), git-based async patterns, AI agent coordination, and the aspirational future of multi-human multi-agent development. Activate on: "pair programming", "vibe coding together", "collaborative coding", "mob programming", "remote pairing", "code together", "multiplayer coding", "Live Share", "Code With Me", "ensemble programming", "cooperative development". NOT for: building a real-time collaboration ENGINE (use real-time-collaboration-engine), git workflow mechanics (use git-best-practices), single-user AI coding assistance.
The English summary is being prepared. Showing the original description.
Delegate repository analysis and coding tasks to Gemini CLI without an interactive session. The skill reads its structured results, summarizes responses and errors, and supports comparing Gemini’s work with another coding agent.
Manage Hindsight memory for coding sessions: retrieve past decisions, store documents and initiative plans, correct outdated information, and configure memory by project. It also explains automatic conversation capture and helps investigate memory configuration problems.
Hardware-offloaded erasure coding with DOCA Erasure Coding (Reed-Solomon, doca_ec) on a BlueField DPU, ConnectX NIC, or host: generating parity for data blocks, rebuilding lost blocks from the survivors, and refreshing parity after a change. Trigger on "one data block changed, how do I refresh parity without re-encoding", "a disk failed and 2 parity blocks are gone, can I rebuild", "RAID-6 resilience across 12 disks", "my doca_ec_task_create returns NOT_PERMITTED", or "is this N+K layout still recoverable", even without naming DOCA Erasure Coding. Covers bringing up a doca_ec context, the create / recover / update tasks, matrix type / N / K / block size, doca_ec_cap_* queries before sizing, doca_mmap src/dst permissions, and DOCA_ERROR_* from doca_ec_task_*. Refuse and route elsewhere for non-Reed-Solomon codes (fountain / LDPC / raptor), pure-replication designs, network FEC, or other DOCA accelerator libraries (SHA / Compress / AES-GCM / DMA).
The English summary is being prepared. Showing the original description.
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 78 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "auto research", "switch model", "hand off a session", "session handoff", "switch engine", "continue on codex", "continue on claude", "move this session to another engine", "multi-agent coding", "coding session", "session inbox", "grok session", "grok build", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness", "clawo runs", "run ledger", "session cost", "coding-agent token usage", "spend cap", "budget limit", "maxBudgetUsd", "durable workflow", "resume a run", "verify a coding run", "acceptance contract", "evidence bundle", "did the agent's tests actually pass", "protected tests", "agent edited the tests", "human gate", "repair loop", "clawo workflow", "clawo verify", "clawo solve", "clawo fanout", "fix and verify", "solve from the terminal".
The English summary is being prepared. Showing the original description.
Research AI coding assistant products, audiences, user stories, social proof, hacks, and unmet needs for apps like Cursor, Claude Code, Codex, Warp Code, Devin, Windsurf, GitHub Copilot, Cline, Aider, and homegrown agent stacks. Use when designing or positioning agentic developer tools, Port Daddy Agent Harbor, swarm consoles, background coding agents, or competitive/product research for AI software engineering. NOT for implementing the coding agent runtime, generic market research, or UX mockups without developer workflow evidence.
The English summary is being prepared. Showing the original description.
Coordinate coding projects through Claude DevFleet by splitting work into dependent tasks and dispatching Claude Code agents in separate Git working directories. Monitor progress, manage automatic task sequencing, and review structured reports of changes, tests, and errors.
Delegate repository analysis and coding tasks to Antigravity CLI without an interactive session. The skill checks structured results and errors, and supports comparing its work with results from another coding agent.
Run OpenCode without an interactive interface to analyze a repository or perform requested coding work. Collect its structured output, summarize results and tool errors, or use its response to compare coding agents.
Apply consistent names to SGLang speculative decoding code, which verifies draft tokens to generate text. Distinguish tokens with or without the bonus token, counts, counters, and arrays when adding identifiers, renaming code, or reviewing changes.
Prepare coding tasks for delegation to an authorized agent’s AI command-line tool. Set up and synchronize the workspace, write precise change requests, then review returned changes and run relevant checks before reporting completion.
Use when the user asks to "generate daily paper", "search arXiv for EEG papers", "find EEG decoding papers", "review brain-computer interface papers", or wants to create paper summaries for EEG/brain decoding/speech decoding research. This skill automates searching arXiv for recent papers on EEG decoding, EEG speech decoding, or brain foundation models, reviewing paper quality, and generating structured Chinese/English summaries.
The English summary is being prepared. Showing the original description.
[omh] Coding owner already chosen, handoff pending: prepares the handoff for the coding agent you already chose, composing its prompt from that agent's own installed skills; never selects the owner and never executes the work itself. Use when the user says: ulw-maestro, coding handoff, prepare the handoff, prepare a coding handoff, hand off the coding work, external executor handoff, handoff prompt, delegation prompt.
The English summary is being prepared. Showing the original description.
Implement Swift Codable models for JSON and property-list encoding and decoding with JSONDecoder, JSONEncoder, CodingKeys, and custom init(from:) or encode(to:). Use when parsing API responses, remapping keys, flattening nested JSON, handling date or data decoding strategies, decoding heterogeneous arrays, or integrating Codable with URLSession, SwiftData, or UserDefaults.
The English summary is being prepared. Showing the original description.
Run Codex CLI, Claude Code, or other coding agents as background processes for programmatic control. Use when a user asks to run a coding agent, delegate a task to another AI, spawn a sub-agent, run Claude Code in the background, or orchestrate multiple coding agents on separate tasks.
The English summary is being prepared. Showing the original description.
Use before non-trivial coding work to pick a task-appropriate working mode — debug, fix, review, test-first, refactor, optimize, migrate, upgrade, integrate, spike, or unstuck — then follow its checklist. Modes are procedures, not personas. Not needed for trivial one-line edits or non-coding tasks.
The English summary is being prepared. Showing the original description.
Acelere a inferência de LLMs usando especulative decoding, múltiplas cabeças Medusa e técnicas de lookahead decoding. Use ao otimizar velocidade de inferência (aceleração de 1,5-3,6×), reduzir latência em aplicações em tempo real ou fazer deploy de modelos com recursos computacionais limitados. Cobre modelos draft, atenção em árvore, iteração de Jacobi, geração paralela de tokens e estratégias de deploy em produção.
The English summary is being prepared. Showing the original description.