AI & ML

x-cmd Bundle

通过 Chrome/Chromium CDP 做浏览器自动化 —— open、snapshot、click、screenshot。用于测试 Web 应用、移动布局与自动化交互，无需 Playwright/Puppeteer。

mturac Bundle

Build an evidence-backed ecc install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ecc should be trimmed to what a project actually needs instead of loading the full bundle.

mturac Bundle

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

mturac Skill

API、エージェント、およびLLMエンドポイントのアクセス制御と認可パターン。

mturac Skill

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

mturac Skill

オブザーバビリティ、セキュリティ境界、およびライフサイクル管理を備えた長寿命エージェントワークロードを運用します。

jcdavis131 Bundle

Designs and wires Anthropic prompt caching for Messages API calls — automatic vs explicit breakpoints, prefix ordering, TTL, minimum token thresholds, and cache-invalidation traps. Use when building Claude API integrations, agent loops, multi-turn chats, large tool/system prompts, or when the user mentions prompt caching, cache_control, or cache_read_input_tokens.

jcdavis131 Skill

In a multi-agent fleet, verify a piece of work is in your designated lane before doing it, and state the check out loud. Defer to the owning agent when the work belongs to another lane. Use whenever the repo has documented agent/team role boundaries (AGENTS.md, .cursor/rules/, .claude/TEAM.md, fleet-team rules) and the task touches a shared area.

jcdavis131 Skill

Give every autonomous agent three guardrails — a per-team allowlist (what it can do), bounded loops (can't run forever), and full transcripts (auditable). Use when building an autonomous agent, a recurring agent loop, or any agent that runs without per-step human approval.

jcdavis131 Skill

Surface the real cost (wall-clock time and tokens/context) of long-running steps so the user can spot a runaway step and the agent can self-calibrate. Use when a step takes materially longer than a typical edit — a long build, a long test run, a multi-minute wiring task, a heavy generation.

jcdavis131 Skill

Keep heavy, pin-pulling adapters out of a project's universal lockfile by declaring them as opt-in extras installed only where needed. Use when adding a dependency with heavy or conflicting transitive pins (LLM libs, PDF/OCR libs, ML frameworks), when a shared environment must stay coherent for training/inference, or when an adapter is only needed by one workspace.

jcdavis131 Skill

Build agents where the deterministic duties are the load-bearing backbone (always execute, reliable, auditable) and the LLM only adds an optional judgment layer on top — ranking, curation, synthesis. The agent must do its core work with the LLM layer off; the LLM only makes the work better. Use when designing or building an autonomous agent, a recurring agent loop, or any system where reliability matters more than cleverness.

kinkwanc22 Bundle

1000-2000字重写 for short Douyin copy rewriting. Use for 短重写, 1000-2000字重写, 原文开头保留无痕衔接, 保留结构框架但表达重组, 更狠更有压迫感的男性情感口播稿, and isolated Gemini prompt-file rewriting that must not modify the original douyin-copy-production-workflow-custom Gemini session.

kinkwanc22 Bundle

Use when the user asks to reverse gender roles in a Chinese relationship, Ryan-style, Douyin, emotional口播, 两性博弈, or 男拿捏女 script by using the configured Gemini API in an isolated new-chat request, sending a fixed Ryan female-emotional-mentor prompt, and rewriting it into a TTS-ready female-audience script about reading male psychology.

kinkwanc22 Bundle

Windows/macOS 本地视频字幕整合包。用户要求给视频加字幕、识别视频语音、生成 SRT/ASS、烧录硬字幕、内嵌字幕、video subtitle、burn subtitles 时使用。通过本地 whisper.cpp 模型和 ffmpeg 处理重活，Agent 只负责读取转写字幕并生成 corrections.txt 纠错表。

kinkwanc22 Bundle

Generate or edit images through the TeamoRouter GPT Image 2 and GPT Image 2.5 Sunburst APIs. Use when a user or agent asks to call TeamoRouter, gpt-image-2, Sunburst, gpt-image-2.5-sunburst, this local image API wrapper, 本地 image2, or 本地 image2.5.

kaiohenricunha Skill

Batch-review multiple PRs in parallel: dispatch one sub-agent per PR in an isolated worktree, aggregate results into a summary table. Triggers on: "review all PRs", "check my PRs", "PR status".

kaiohenricunha Skill

Discover, search, and manage Claude Code agents. Use when you want to find available agents, list installed agents, or refresh the agent catalog. Triggers on: "search agents", "list agents", "find agent", "what agents", "agent catalog".

devguyrash Bundle

Operate ChatGPT in a user-authorized interactive browser across models, reasoning levels, Projects, ordinary or temporary chats, attachments and pasted context, apps and custom GPTs, response waiting, and thread hygiene. Use when an agent is asked to interact with ChatGPT through a browser; do not use for OpenAI API calls, ordinary web browsing, non-ChatGPT browser tasks, or generic second-model review unless the user specifically requests ChatGPT in the browser.

devguyrash Bundle

Write, revise, or assess AI prompts and execution plans, and arrange the instructions, context, and handoffs needed to carry out a task.

hhqc-369 Skill

Route Seedance 2.0 video-prompt writing requests to dexhunter/seedance2-skill. Use for camera language, reference syntax, prompt structure, ads, drama, music video, educational video, and other Seedance prompt design.

xaiht Bundle

Create, edit, validate, and package new Tlamatini skills (SKILL.md packages).

xaiht Skill

Run whichever SAST, secret-scanning, and dependency-audit tools are installed (bandit, semgrep, ruff, eslint, gitleaks, pip-audit) over a path, then return aggregated findings, severity counts, and a prioritised remediation summary.

xaiht Skill

Configure the API key (or other credential) for a registered ACPX agent_id (claude/codex/cursor/gemini/qwen/copilot/pi/droid/iflow/kilocode/kimi/kiro/opencode/tlamatini) end-to-end across data.keys, config.json (top-level + acpx.agents.<id>.env), regen_secrets.py, and verification via acp_doctor.

xaiht Bundle

Sweep the whole codebase and keep the SELF-MODIFY source snapshot complete — so the TlamatiniSourceCode/ tree that a `--self-modify` build ships carries every source/build asset Tlamatini needs to read, modify, and REBUILD herself, with heavy media/secrets correctly omitted+redacted and omitted binaries listed in the restore manifest. Invoke whenever you add/rename a new agent, source file, top-level dir, dependency, build input, prompt/identity file, migration, static/template asset, or any rebuild input — and ALWAYS after a feature like Blenderer or the self-update capability lands. Owns copy_source_assets.py and audits it against five invariants with a runnable sweep that GENERATES a snapshot and proves a rebuild's inputs all survive. Sibling of tlamatini-self-update-inclusion (which guards the runnable release).

xaiht Bundle

The authoritative reference for adding a NEW external MCP server to Tlamatini universal MCP client layer. Covers the full lifecycle: catalog import, transport selection, activation, runtime provisioning, diagnosis, verification, and troubleshooting. READ THIS BEFORE calling external_mcp_import, before editing external_mcps.json, or before activating a new server.

xaiht Skill

Validate a .flw workflow file: check connection topology, terminal agents, Parametrizer single-lane queue, missing connectors, dangling target_agents.

xaiht Skill

Enumerate every @csrf_exempt-decorated view in Tlamatini/agent/views.py and classify whether each one really needs the exemption.

xaiht Skill

Turn a one-sentence objective into a downloadable .flw workflow that wires the right Tlamatini visual agents and connections.

xaiht Skill

Replay the most recent global execution planner trace from tlamatini.log and explain why each capability got the score it did.

xaiht Skill

Tighten Django ALLOWED_HOSTS from the wide-open '*' default to a specific list, with a backup of settings.py.

izzyfresh Bundle

Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations.

izzyfresh Skill

Skill: Model Selection and Validation Rules

izzyfresh Skill

How to use tools in CX Agent prompts.

izzyfresh Skill

This skill provides instructions for interacting with Looker, BigQuery, and Dataplex via MCP in this environment.

izzyfresh Skill

Rules regarding deprecated and supported agent platforms.