Results for “loop”

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.

PASS/FAIL eval rubrics and alignment loops for Sid Orchestra (global). Use when the user says sid evals, @sid-evals, grade this, eval gate, alignment score, or wants to stop AI slop. Works in any workspace; bootstraps EVALS.md from ~/.cursor/skills/sid-orchestra/templates if missing.

Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.

Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

Run three agents as a newsroom — a Writer, an Editor, and a Fact-checker — that draft, critique, and verify in parallel and argue until the writing survives with zero flags. This is the level above a single self-review loop, for the pieces that matter most. Best run in Claude Cowork against the user's files. Use for high-stakes writing the user wants bulletproof: a newsletter, a launch post, a client email, a public announcement. Trigger whenever the user says 'run the team', 'use the swarm', 'writer editor fact-checker', 'spawn agents to work on this', or wants the strongest possible version of a piece. For a lighter single-agent loop, use red-pen instead.

Runs a two-wave validation pipeline (deterministic checks then rule-based checks) before every git commit, writing a sentinel file that a pre-commit hook enforces. Includes optional quick mode (first wave only) and a fix loop with up to three iterations.

Use when planning a KDD project calendar across the venue's two submission cycles per year, including cycle choice, abstract-then-paper deadline pairs a week apart, rebuttal capacity planning, the Resubmit-to-next-cycle loop, ADS evidence lead times, and ACM e-rights/TAPS camera-ready scheduling for SIGKDD.

Composite skill — query, capture, improve, and persist knowledge in one workflow. Chains recall (RAG query) → sync-memories (write durable note) → rag-curate (improve weak retrievals) → handoff (durable snapshot if session-ending). Use when the work involves "what did we decide", "remember this", "save where we are", or any closing checkpoint.

Token budget analytics and ROI scoring for AI agent actions. Track token cost per fix, detect wasteful loops, auto-route to fast tier when burn rate is too high. Integrates with token-budget-guard.sh hook. Triggered by /cost-report, "how much did that cost", "token usage", "am I wasting tokens".

Marketing skills router: match marketing intent to a sub-skill, then Read its Entry file under skills/<name>/ (e.g. ads/ads.md). Covers CRO, copywriting, SEO/AEO, paid ads, ad creative, analytics, email/SMS, pricing, launches, video/image generation, and growth loops. Use for any marketing request — campaigns, content, optimization, measurement.

FLOW framework integration — evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts.

Run metric-driven iterative optimization loops -- define a measurable goal, run parallel experiments, measure each against hard gates or LLM-as-judge scores, keep improvements, and converge on the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation.

Audits game user experience across HUD clarity, menu navigation, tutorial effectiveness, control responsiveness, camera systems, feedback loops, loading screens, and settings completeness. Detects game engine (Unity UGUI/UI Toolkit, Unreal UMG, Godot Control, web-based), maps all UI screens and input contexts.

Routes a research topic through a structured two-phase workflow: generate an extensible outline, then fan out parallel web-search agents to investigate each item into validated JSON, producing a complete markdown report with table of contents.

Use for writing, reviewing, debugging, or testing bounded retry policies in Python with Tenacity, including retry predicates, stop and wait strategies, jitter, exception propagation, callbacks, Retrying, and AsyncRetrying. Do not use for generic loops, scheduled jobs, domain polling without a retryable operation, or operations whose side effects are not safe to repeat.

Stop vibe-coding with a spec → plan → TDD loop before writing a line. Use for any non-trivial feature, refactor, or bug fix on web, React Native, or Capacitor. Use when asked to "build", "implement", "add a feature", "this keeps breaking", "do it properly", or when LLM output keeps being wrong.

You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.

Rewrite any prompt, instruction, task description, or spec into a "genie-proof" version — instructions so explicit, literal, and loophole-free that even a maliciously literal genie (or an LLM, contractor, or junior dev) could not misinterpret them. Use this skill whenever the user asks to genie-proof, tighten, harden, de-ambiguate, or "make bulletproof" a prompt or instruction; whenever they complain that an AI/model/person "didn't do what I meant," "took me too literally," or "found a loophole"; or whenever they hand over a vague prompt and ask to make it precise, explicit, unambiguous, or idiot-proof. Also trigger on phrases like "wish to a genie," "monkey's paw," "lawyer-proof this prompt," or "leave nothing to interpretation."

Close the post-launch improvement loop for any shipped app. Use when asked to "improve the app after launch", "fix the top issues", "post-launch polish", "what should I fix next", "production issues", "iterate on feedback", "post-release improvements", "what is broken in prod", "ship a polish pass", or "make it better.

Product marketing strategy, positioning, and competitive intelligence for B2B SaaS. Use when defining ICP, developing positioning (April Dunford method), creating messaging hierarchy, building competitive battlecards, planning sales enablement, sizing market opportunity (TAM/SAM/SOM), mapping PMF spectrum, designing growth loops, writing PR/FAQ working backwards docs, or creating a product marketing context document.

FLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW knowledge base (30 blog-applicable prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "blog flow", "evidence-led blogging", "find optimize win", or wants stage-specific blog prompts.

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

Mega-composite — full greenfield feature development from idea to live. Chains research-and-decide (validate the idea + capture decision) → scope-and-execute (analysis + plan + implement) → design-build (if UI involved) → fix-the-suite (if tests need work) → merge-confidently → ship-it → knowledge-loop. The single command for "build feature X end-to-end."

Sid Orchestra — portable multi-agent swarm for any Cursor workspace. Run IDs, lock leases, plan critic, canary harness, PASS/FAIL evals, anti-hallucination. Use when the user says sid orchestra, @sid-orchestra, sid swarm, sid evals, or wants research→plan→build→review with a bus and loop. Available globally from ~/.cursor/skills.

Structured deep research workflow with human-in-the-loop control. Use /research to generate research outline, /research-deep for parallel web search across items, /research-report to compile markdown reports. Supports academic research, benchmark research, technology selection, market analysis, and due diligence. Triggers: 'deep research', 'research topic', 'benchmark comparison', 'technology survey', 'market analysis'. Requires: WebSearch capability.

Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. Covers supervisor, swarm, and hierarchical multi-agent patterns; subgraph composition; state management (checkpointers/stores); persistence; evals; and production debugging. Reach for this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Deploy MATLAB-generated code to embedded hardware using Embedded Coder. Use when configuring code generation for microcontrollers (STM32, Raspberry Pi, ARM Cortex), setting up PIL/SIL verification, disabling dynamic memory allocation, or configuring hardware-specific code generation settings. Covers ERT-based configurations, processor-in-the-loop testing, memory constraints, and the MEX→SIL→PIL verification progression.

Node.js performance profiling with V8 CPU profiler, heap analysis, and perf_hooks. Use for identifying bottlenecks and memory leaks. USE WHEN: user mentions "Node.js performance", "profiling", "memory leak", asks about "V8 profiler", "heap snapshot", "CPU profile", "perf_hooks", "event loop lag", "Node.js optimization" DO NOT USE FOR: Java/Python profiling - use respective skills instead

Restructure existing code without changing its behavior, through a test-gated refactoring loop: a named target, a green suite over that target before any edit, a planned sequence of small named refactorings, and the full suite re-run after every step. Use when the user wants to refactor, restructure, clean up, simplify, or improve the design of existing code, or to apply refactoring recommendations from a code-review or architectural-analysis report. This skill changes code; it does not review code (use code-review), assess architecture (use architectural-analysis), or build new behavior test-first (use tdd). Do not use it on code inside an active tdd loop; the refactor step of tdd owns that cleanup. Runs its planned sequence to completion without pausing for review; to review each named refactoring as it lands, use pairing.

Expert skill for building web-based game engines and games using HTML5, Canvas, WebGL, and JavaScript. Use when asked to create games, build game engines, implement game physics, handle collision detection, set up game loops, manage sprites, add game controls, or work with 2D/3D rendering. Covers techniques for platformers, breakout-style games, maze games, tilemaps, audio, multiplayer via WebRTC, and publishing games.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.