Results for “continuous-action-heads”

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations, detecting attack vectors where attacker-controlled input reaches AI agents in CI/CD pipelines.

Drive mex (`mex-agent`), persistent project memory and code graphs for AI coding agents. One command scaffolds a living wiki, builds a deterministic code graph, and installs a project anchor file (CLAUDE.md, root AGENTS.md, .cursorrules, .windsurfrules, copilot-instructions.md, or .opencode/opencode.json) that your agent auto-loads as a standing rule document. Use when the user wants to `mex setup` a new project, build a symbol-grounded wiki, keep knowledge connected to implementation, route relevant context to agents, or run drift detection (`mex check`, `mex sync`). Triggers on: "mex setup", "project memory", "code graphs", "codebase documentation", "drift detection", "agent memory", "structured scaffolds", "architectural context", "living wiki", "project anchor file".

Computer Use Agent — autonomous browser control via Steel, Browser Use, and Browserbase cloud providers. Supports headful CDP sessions, CAPTCHA solving, proxy rotation, live view, session recording/replay, Playwright/Puppeteer integration, and LLM-driven visual browsing. Use when asked about computer use, browser automation, web scraping, Steel sessions, cloud browsers, headful browsing, CAPTCHA solving, or autonomous web navigation.

Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via sessions_send, and result collection. Supports two modes: linear (sequential pipeline) and dag (dependency graph with parallel execution).

Expert in creating opening lines, thumbnails, and hooks that stop the scroll. Covers curiosity gaps, pattern interrupts, emotional triggers, and platform-specific hooks. Knows how to earn attention in the first 3 seconds without resorting to clickbait. Use when "hook, opening line, scroll stopper, headline, first line, attention grab, thumbnail, clickable, " mentioned.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Agent C3 - Mixed Methods Design Consultant Comprehensive mixed methods research design specialist covering sequential, concurrent, embedded, and multiphase designs with Morse notation. Core Capabilities: - Sequential Explanatory (QUAN → qual): Explain quantitative results - Sequential Exploratory (QUAL → quan): Develop instruments - Convergent Parallel (QUAN + QUAL): Comprehensive understanding - Embedded (QUAN(qual)): Secondary strand addresses different question - Multiphase: Long-term projects with iterative phases - Morse notation interpretation and recommendation

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

Orchestrates multi-agent project builds with persistent state, parallel execution, and atomic git commits.

Patterns and architectures for running Claude Code autonomously in loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Routes requests into the correct obsidian-mind mode: install, daily session loop, capture, review, maintenance, multi-agent wiring, or semantic search, using a ready-made Obsidian vault template for persistent agent memory.

Automates the full lifecycle of agent skills: extracts reusable constraints from user feedback, merges preferences with version bumps, and retrieves relevant skills for new tasks.

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character, dialog scene — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "talking head", "lip sync", "avatar video", "make X speak", "audio to video", "audio driven avatar", "virtual presenter", "AI spokesperson", "dubbed video", "UGC avatar", "HeyGen alternative", "Synthesia alternative", "digital human", "make this portrait talk", "video from voiceover", or any explicit ask to put words in a face.

Creates and maintains persistent markdown planning files that survive session resets by hooking into Claude Code's lifecycle.

Run Claude Code autonomously in loops, from simple sequential pipelines to multi-agent DAG orchestration.

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)

Generate pragmatic CI/CD pipelines from detected project stack signals, with fast baseline generation, repeatable checks, and environment-aware deployment stages.

Design and build hosted agent infrastructure with sandboxed execution, warm pools, session persistence, and multiplayer collaboration.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Headless UI Styling

Build complex, interactive animations in React/Next.js including drag-and-drop, gestures, text animations, SVG path drawing, custom hooks, and imperative sequences.

CLI-team runtime for claude, codex, gemini, antigravity, grok, or cursor workers in tmux panes when you need process-based parallel execution

Build and operate a Havoc C2 framework for authorized red-team engagements, including team server deployment, evasive Demon agent generation, and post-exploitation.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

Orchestrating multi-session parallel execution via Claude Code Agent Teams API and Codex CLI Subagents — launch, manage, coordinate concurrent tasks. Use when parallel work is needed.

Executes DAG workflows with parallel wave processing, agent spawning, context isolation, permission enforcement, and full execution tracing. Use when running a planned DAG, managing concurrent agent execution, enforcing isolation boundaries, or tracing execution for debugging. Activate on "execute DAG", "run workflow", "spawn agents", "parallel execution", "execution trace", "agent isolation". NOT for planning DAGs (use dag-planner), validating outputs (use dag-quality), or matching skills (use dag-skills-matcher).

Analyzes federal contract competitors, incumbents, and obligation trends using live USAspending.gov data via the usaspending MCP, supporting black-hat competitor research and contract-number-first obligation analysis.

自动捕获经验并安全进化的技能。触发条件：(1)命令/操作失败时→记ERRORS.md (2)被用户纠正('不对'/'应该是')时→记LEARNINGS.md (3)用户需要不存在的能力时→记FEATURE_REQUESTS.md (4)外部API/工具出错时→记ERRORS.md (5)发现自己知识过时/错误时→记LEARNINGS.md (6)发现更好做法时→记LEARNINGS.md (7)每个任务完成时→回顾过程，有新经验则记LEARNINGS.md。去重原则：如果没有新经验或已有条目已覆盖则跳过不写。每次写入同时在.learnings/CHANGELOG.md追加JSONL日志。经验反复出现≥3次时晋升到AGENTS.md/TOOLS.md/SOUL.md。详见正文。

Predicts the highest-impact next action for your project by running a 5-agent meta-DAG pipeline. Gathers project signals automatically (git, recent files, port-daddy, CLAUDE.md), then runs sensemaker → decomposer → skill-selector + premortem → synthesizer. When execution is approved, convert each predicted node into a skillful node prompt using skillful-node-prompt + skillful-subagent-creator, prefer live WinDAGs visualization backed by POST /api/execute and /ws/execution/:id, and fall back to ASCII only when live visualization is unavailable. Activate on: "what should I do", "what's next", "next move", "/next-move", "where should I focus", "what's the highest impact thing right now". NOT for: creating skills, debugging one specific bug, or promising topology-specific runtime behavior the current server cannot execute.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Creates a hero frame with looping CSS animations including a rotating type ring, animated globe, ticking timer, and parallax labels.

Provides persistent, compounding memory for AI agents across sessions using local markdown files, with optional Supabase-backed semantic search.

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.