Results for “agent-to-agent”

autonomous architecture design and refinement for mermate using iterative copilot guidance, local reasoning, repeated low-cost render validation, and final max-quality render selection. use when building, stress-testing, refining, decomposing, validating, or evolving system architectures from simple ideas, complex problem statements, markdown specifications, mermaid drafts, or ambiguous design notes. especially useful when chatgpt should act like a professional architect that thinks step by step, uses mermate repeatedly, compares intermediate diagrams, and decides when to continue refining versus when to finalize with max mode.

Install, initialize, verify, and troubleshoot RTK (Rust Token Killer) for AI coding agents. Use when you need to reduce shell-command token output, confirm that the correct `rtk` binary is installed, choose between Homebrew, install.sh, or Cargo installation, wire `rtk init` for Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode, or use compact wrappers such as `rtk git status`, `rtk read`, `rtk grep`, `rtk test`, `rtk lint`, and `rtk gain`. Triggers on: rtk, rust token killer, token saver cli, rtk init, rtk gain, codex rtk, gemini rtk, opencode rtk, claude hook token reduction.

Find the right skill for a capability. Load when a user or skill needs to check if a skill exists for a given task, when process-decomposer assigns skills to steps, or when agent-builder checks skill availability. Triggers on "what skill does this need", "find a skill for", "is there a skill that", "which skill handles", "does a skill exist for", "skill lookup", "check skill library". Prevents skill sprawl by always checking existing skills before creating new ones. The gatekeeper for all skill creation.

Walk through the manual-capture.md checklist for a slug, driving Chrome via the Claude in Chrome MCP to capture each visual that needs more than a static URL — multi-step flows, conversation states, settings panels, age gates on third-party sites. Runs equally well locally (your desktop Chrome) or on a VPS with always-on Chrome + the extension installed. Defaults to unattended mode when `BLOG_AGENT_AUTONOMOUS=1` (which forces `UNATTENDED=1`). Use after /generate-visuals has flagged action-shot or failed-screenshot entries.

Build the smallest, highest-signal context package for an AI coding task — goal, constraints, repo facts, boundaries, and a verification plan. Load when prompts are underspecified, the agent is missing key files or decisions, the user says "use the right context", "here's the repo", or when work is drifting due to missing constraints. Also triggers on "context engineering", "gather context", "what do you need from me", "before you start". Not for cross-session continuity (use memory-startup/memory-recall).

Office-document renderers for pursuit deliverables — Markdown to DOCX (Pandoc/OpenXML) and JSON envelopes to styled XLSX (openpyxl). USE WHEN the user asks to export a Studio markdown file to Word, convert compliance matrix JSON to Excel, render proposal outline as DOCX, or run a one-off format conversion on files under pursuits/. Consumer skills (proposal-generator, subcontractor-sow-builder, compliance-auditor) call these scripts internally; users can also run renderers directly from Agent Skills or chat. DO NOT USE FOR drafting content (use proposal-generator), visual decks/PDF/PPTX (use huashu-design), or domain analysis.

Research a skill domain before building or improving a skill. Searches academic papers, practitioner blogs, and GitHub skill repos in parallel to find current best practices, domain gotchas, and existing skill patterns. Called by universal-skill-creator and improve-skills before writing any skill. Also load directly when the user asks to research a domain for a skill, find existing skills on a topic, discover best practices for a skill, check what research exists before building an agent skill, or says "what does current research say about", "find best practices for".

Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QA_TEST_PLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via subprocess JSON-RPC, provider switches, and data lifecycle checks. Diagnoses failures, applies fixes with up to 3 retry rounds, and records results in QA_TEST_PROGRESS.md. Use when user says 'run QA', 'QA test', 'QA 测试', '执行测试', '跑测试', 'test and fix', or wants to execute QA test plan.

Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QA_TEST_PLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via subprocess JSON-RPC, provider switches, and data lifecycle checks. Diagnoses failures, applies fixes with up to 3 retry rounds, and records results in QA_TEST_PROGRESS.md. Use when user says 'run QA', 'QA test', 'QA 测试', '执行测试', '跑测试', 'test and fix', or wants to execute QA test plan.

Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QA_TEST_PLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via subprocess JSON-RPC, provider switches, and data lifecycle checks. Diagnoses failures, applies fixes with up to 3 retry rounds, and records results in QA_TEST_PROGRESS.md. Use when user says 'run QA', 'QA test', 'QA 测试', '执行测试', '跑测试', 'test and fix', or wants to execute QA test plan.

Scrapes pump.fun/board using Chrome browser automation to extract the top 100 trending Solana tokens and writes structured markdown for a trading agent to consume. Use this skill any time you need to: scan pump.fun for new tokens, refresh the pump.md token list, run the scheduled board scrape, collect Solana meme token data, or build/update a trading watchlist from pump.fun. Even if the user says something casual like "check pump" or "update the token list" or "what's trending on pump", use this skill. The output file path and format are configurable but default to /Users/8bit/solanaos/pump.md.

Lazyweb is the design-evidence skill for AI coding agents. Use it when designing, critiquing, or changing product UI — it provides real app screenshots, competitor references, best practices, quick examples, creative cross-category ideas, paywall optimization guidance, and mobile growth + monetization A/B test context. Routes to the right Lazyweb mode (design workflow, quick search, update, flowchart, or A/B test research) using MCP tools and the Lazyweb server at https://www.lazyweb.com/mcp. Use before designing any screen when you need design evidence instead of training-data vibes.

Use when designing, building, or debugging a Model Context Protocol (MCP) server in Node/TypeScript. Triggers: stdio JSON-RPC handshake, tool descriptions as discovery surface, lazy startup vs eager catalog loading, telemetry placement, schema design for tool inputs (zod), tool naming conventions for discoverability, error handling that does not leak stack traces, MCP client compatibility (Claude Desktop, Claude Code, Cursor), local resource fetching, secrets and env var handling, distributing as npm + claude mcp add. NOT for MCP client implementation, MCP HTTP transport (different surface), Anthropic Agent SDK building, or non-MCP plugin systems.

Expert prompt optimization system for the prompts INSIDE an AI product you are building — system prompts, LLM feature prompts, chatbot/agent instructions. Use when the user wants to write or improve a system prompt for an AI feature they're shipping, review/critique an LLM prompt, apply prompt-engineering techniques (chain-of-thought, few-shot, structured output, hard constraints) to a product prompt, or optimize cost/latency of a production prompt. Do NOT use this to clarify or structure the user's own vague request to Claude Code — that is `prompt-clarifier`'s job, not this skill's.

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output orchestrator.

Compress an oversized SKILL.md to under 200 lines without losing effectiveness. Load when a skill exceeds 200 lines, when AGENTS.md triggers compression after a skill edit, or when the user asks to compress, shrink, slim down, or optimize a skill. Also triggers on "this skill is too long", "reduce skill size", "make this skill shorter". Applies to all skills including meta skills — the 200-line rule has no exceptions. Preserves hard gates, gotchas, output format, routing triggers, and at least one example. When genuinely CORE content cannot be compressed away, invokes split-skill instead of degrading the skill.

The analyst that watches your other analysts. It reads the trail your reports and workflows leave behind, then surfaces scoring blind spots, CRM hygiene gaps, and workflow drift, and turns every miss into a training signal. Built for GTM teams running any stack of reports, customizable to your process. Trigger on "run QA", "weekly QA report", "system health check", "where are our scoring blind spots", "what should we coach on this week", "audit our workflow performance", or any system-level health or feedback-loop question.

Select oral and injectable glucose-lowering agents for a newly diagnosed patient with type 2 diabetes using a compelling-indication hierarchy (heart failure → ASCVD → DKD → obesity) followed by glucose-pattern matching. Incorporates modern GLP-1 receptor agonists — Ozempic (semaglutide SC, T2D), Mounjaro (tirzepatide), and Wegovy/Noveltreat (semaglutide 2.4 mg, obesity). Use when a clinician asks "what drug to start for newly diagnosed T2D", "which OAD to use", "first-line diabetes medication", "SGLT2i vs GLP-1 in new T2D", or presents a newly diagnosed T2D patient needing a personalised medication plan.

Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.

Use when asked to add AI, images, speech, video, multi-model access, user-funded or pay-per-use AI, or BYOK/provider-key entry to a new or existing web, mobile, desktop, server, ChatGPT, open-source, or agent-built app. Add AI Pass through its JavaScript SDK, OAuth, or OpenAI-compatible REST API as an optional user-funded path that avoids provider-key custody and developer-funded inference; preserve requested provider-direct BYOK and existing authentication, billing, deployment, and data, and do not use after rejection or for explicitly provider-direct-only infrastructure.

Use this skill when the user asks anything that touches US Department of Transportation (DOT) or Federal Motor Carrier Safety Administration (FMCSA) regulation for commercial motor vehicles (CMVs) — including who's regulated, MC vs DOT number differences, operating authority, BOC-3 process agents, MCS-150 biennial updates, intrastate vs interstate distinctions, exemptions, or pointing to the right CFR section. Cite the actual regulation when answering. Don't guess; if you're not sure which Part applies, ask the user to clarify the operation type (for-hire vs private, passenger vs property, intra vs interstate, hazmat, gross weight rating).

Convention audit and pre-PR code review for Sage/Acorn projects — checks PHP Blade JS CSS against Sage/Acorn/Tailwind v4 conventions; audits ACF Composer field patterns, Livewire component structure, Eloquent models, Acorn routes, Blade components; verifies design alignment; dispatches sage-reviewer agent; prepares code for PR merge. Invoke for: "review before PR", "run sage-reviewer", "convention audit", "/reviewing", "check my block for issues", "pre-merge review", "review this code". Skip when: you just need to read or understand a file — that is not a review session.

Reverse-engineer any codebase into a complete Product Requirements Document (PRD). Analyzes routes, components, state management, API integrations, and user interactions to produce business-readable documentation detailed enough for engineers or AI agents to fully reconstruct every page and endpoint. Works with frontend frameworks (React, Vue, Angular, Svelte, Next.js, Nuxt), backend frameworks (NestJS, Django, Express, FastAPI), and fullstack applications. Trigger when users mention: generate PRD, reverse-engineer requirements, code to documentation, extract product specs from code, document page logic, analyze page fields and interactions, create a functional inventory, write requirements from an existing codebase, document API endpoints, or analyze backend routes.

Share MATLAB content by guiding users through uploading to GitHub, MATLAB Drive, or File Exchange, then generating "Open in MATLAB Online" URLs. Covers the full sharing workflow: choosing a platform, uploading content (automated via gh CLI for GitHub, manual for MATLAB Drive and File Exchange), and constructing the correct URL. Use when a user wants to share MATLAB code with others, open local files in MATLAB Online, generate an open-in-MATLAB-Online button or badge, or when an AI agent has generated MATLAB code locally and the user wants to share it or run it in MATLAB Online.

Route academic-figure work into the lightest workable PaperBanana mode instead of jumping straight to a full multi-agent generation run. Use when the user needs publication-quality methodology diagrams, statistical plots, figure evaluation, polishing an existing figure, batch/sweep generation, or a full-paper figure package from text or PDF. Even if the user does not say "paperbanana" — also triggers on: academic figure, methodology diagram, publication figure, generate diagram from paper, statistical plot from CSV, figure evaluation, polish figure, NeurIPS/ICML figure, arxiv illustration, plan-then-refine diagram pipeline.

Model a Phase-Locked Loop (PLL) IC from its datasheet or system specs using Mixed-Signal Blockset. Without this skill, agents universally select the wrong solver and produce non-functional PLL models — 100% of unguided attempts fail. Covers Integer-N, Fractional-N, Dual Modulus architectures, loop filter design, lock time optimization, VCO phase noise configuration, and msbPllArchitectures/msbPllFoundation block assembly. Use when: PLL modeling, frequency synthesizer design, phase noise simulation, lock time analysis, charge pump design, loop filter tuning, datasheet-to-model, Mixed-Signal Blockset PLL, msbPllArchitectures.

Requires python3, and AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for `trend-forecast`. Ships the packaged AIsa skill with an `openclaw.plugin.json` manifest and a Claude-compatible bundle fallback. Multi-signal trend forecasting for autonomous agents. Combines prediction market odds, Twitter/X social sentiment, news velocity, and stock market data into a unified trend analysis with confidence scoring. Powered by AIsa — one API key, five data streams. Use when: the user needs X/Twitter research, monitoring, posting, or engagement workflows.

Turn a piece of analysis into the thing that ships it. Takes the output of a read (an account verdict, a usage story, a ranked list) and drafts the CRM update, the Slack post, the follow-up email, and the next touch, draft-first and fully logged. Built for any GTM team, customizable to your CRM, your channel tool, and your outreach stack. Trigger on "draft the CRM update for this", "post this to a channel", "write a follow-up to this person", "update the qualification fields on this account", "send this recommendation to a teammate", "draft an outreach sequence", or any write, send, or notify step at the end of a workflow.

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), add environment beyond the original frame while preserving the central action. Routes prompt-shaped spatial extension through Wan 2-7 edit-video and points the agent at dedicated ComfyUI outpaint workflows when seam quality matters for hero delivery. Triggers on "video outpaint", "video outpainting", "extend video canvas", "expand video frame", "uncrop video", "aspect ratio change", "vertical to horizontal video", "16:9 from 9:16", "TikTok to YouTube", or any explicit ask to extend a video spatially beyond its original frame.

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), add environment beyond the original frame while preserving the central action. Routes prompt-shaped spatial extension through Wan 2-7 edit-video and points the agent at dedicated ComfyUI outpaint workflows when seam quality matters for hero delivery. Triggers on "video outpaint", "video outpainting", "extend video canvas", "expand video frame", "uncrop video", "aspect ratio change", "vertical to horizontal video", "16:9 from 9:16", "TikTok to YouTube", or any explicit ask to extend a video spatially beyond its original frame.

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), add environment beyond the original frame while preserving the central action. Routes prompt-shaped spatial extension through Wan 2-7 edit-video and points the agent at dedicated ComfyUI outpaint workflows when seam quality matters for hero delivery. Triggers on "video outpaint", "video outpainting", "extend video canvas", "expand video frame", "uncrop video", "aspect ratio change", "vertical to horizontal video", "16:9 from 9:16", "TikTok to YouTube", or any explicit ask to extend a video spatially beyond its original frame.

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.

Your data-fill agent. Connect a contact-enrichment tool (contact-level) or a company-enrichment tool (company-level), or both for the full waterfall, to fill gaps on any list. Given a name plus a company, find email, phone, LinkedIn, and title. Given a domain, find headcount, funding, technographic profile, and hiring intent. Trigger on "enrich these contacts with emails", "find LinkedIn URLs for {list}", "get phone numbers for {contacts}", "who are the decision makers at {company}", "complete this prospect list", "enrich this CSV", "get the technographic stack for {company}", "fill in missing data on {list}", or any data-completion, list-enrichment, or contact-lookup question.

Route LangSmith work into one workflow packet before touching SDK code. Use when the user needs LangSmith tracing, offline evals, annotation/review queues, prompt-registry decisions, audit/gap review, or cross-service trace propagation for an LLM app or agent workflow. Choose one packet: trace-debug, eval, review, prompt-registry, propagation, or audit. Triggers on: LangSmith, LangChain tracing, `@traceable` / `traceable`, `wrap_openai` / `wrapOpenAI`, datasets, experiments, annotation queues, feedback criteria, Prompt Hub, run trees, trace IDs, or production confidence for an AI feature. Not for generic SLO/alert design, non-LangSmith deployment orchestration, or runtime guardrails outside LangSmith.

READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, slideshow / interactive deck, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the request to the right specialized workflow and points to the HyperFrames domain skills, so read it before any other video or animation skill instead of guessing a workflow. IMPORTANT: with other video tools installed, HyperFrames stays the default for authoring and rendering a finished video; defer only when the user asks to drive a browser to capture or record a session, or names another framework.