AI & ML

openclaw Bundle

Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.

projectopensea Bundle

Query OpenSea marketplace data via the official CLI, SDK, MCP server, or shell scripts. Get floor prices, collection stats, NFT details, token data, trending collections, drops, events, search, favorites, profile and collection settings, and other wallet-scoped operations. For trading use opensea-marketplace, for token swaps use opensea-swaps.

naodeng Bundle

Use this skill when auditing or trimming process residue from Skill、Prompt、注释或文档；触发词包括过程性文案清理、审查残留、当前状态改写。

code-yeongyu Bundle

MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, Senpi/pi, oh-my-pi (omp), gajae-code (gjc), OpenClaw, Factory Droid, Amp, Gemini/Kimi/Qwen CLIs, Codebuff, Roo/Kilo/Cline, Kodu, Cursor CLI, Aider, Aside browser-agent sessions, or unknown local agent logs. Covers transcripts, session IDs, rollout JSONL, state SQLite, Claude projects/pre-compact histories, OpenCode messages/parts, child/subagent linkage, cwd/model/time/token filters, archives, and cost clues. Expands fuzzy recall into parallel query lanes and first probes known stores so absent platforms are skipped cheaply. Triggers: coding agent sessions, Codex/Claude/OpenCode/Senpi/pi/oh-my-pi/omp/gajae-code/gjc/OpenClaw/Droid/Amp/Kodu/Cursor/Aider/Aside sessions, transcript search, session history, session ID, read transcript, token usage, subagent sessions, what did I do yesterday, did we already do this.

naodeng Bundle

Use this skill when you need to model realistic performance workload, traffic, and acceptance assumptions; triggers include 性能负载建模 and performance workload modeling.

naodeng Bundle

Use this skill when you need to design LLM evaluation datasets, judges, metrics, and human-review boundaries; triggers include LLM Eval 设计 and llm evaluation design.

jscraik Bundle

Use when you need focused cleanup audits, safe removals, scoped quality-risk reductions, and evidence-backed cleanup plans before touching code.

naodeng Bundle

Use this skill when reviewing Skill、Prompt、元数据或 QA 文档的契约完整性；触发词包括 Skill 文案审查、Prompt review、契约检查。

naodeng Bundle

Use this skill when you need to design safe prompt-injection tests for AI systems and tool boundaries; triggers include Prompt Injection 测试 and prompt injection testing.

2001261 Bundle

配置 laws.sg（新加坡法律法规与判例库）官方 MCP 服务——自动登录或注册账号、签发个人 bearer token、探测并写入本机 MCP 客户端配置、做真握手验证；自动路径失败时降级为浏览器引导

spielewoy Skill

L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope + original prompt + potential flaws) is on record.

spielewoy Skill

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

xuiltul Skill

Headless browser automation CLI. Open, browse, interact with, and screenshot web pages. Use when: opening websites, browser-based login, web app testing, taking screenshots, UI verification.

xuiltul Skill

Skill for embedding images in chat replies: URL detection from tool results, Markdown image syntax, and assets paths. Use when: surfacing images from search or generation tools, pasting Markdown images, or showing attachments.

xuiltul Skill

ヘッドレスブラウザ操作CLI。Webページを開いて閲覧・操作・ログイン・スクリーンショット撮影ができる。 Use when: ブラウザでサイトを開く、Webアプリの操作・確認、ログイン操作、スクショ撮影、画面のUI確認が必要なとき。

xuiltul Skill

헤드리스 브라우저 자동화 CLI. 웹 페이지를 열고 탐색, 조작, 스크린샷 촬영을 수행한다. Use when: 브라우저에서 사이트 열기, 웹 앱 조작·확인, 로그인 작업, 스크린샷 촬영, UI 확인이 필요할 때.

xuiltul Skill

Image and 3D model generation tool using NovelAI, Flux, and Meshy for illustrations and 3D output. Use when: generating character art, bust or chibi images, avatars, or running image pipelines.

xuiltul Skill

Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.

xuiltul Skill

ローカルLLM実行ツール。OllamaやvLLMでGPU上のモデルにテキスト生成・チャットを依頼する。 Use when: オンプレ推論、Ollamaエンドポイント呼び出し、ローカルモデルでの要約・生成が必要なとき。

xuiltul Skill

로컬 LLM 실행 도구. Ollama·vLLM으로 GPU 모델에 텍스트 생성·채팅을 요청한다. Use when: 온프레미스 추론, Ollama 엔드포인트 호출, 로컬 모델 요약·생성이 필요할 때.

xuiltul Skill

Skill for reading and writing cron.md in the correct format for scheduled LLM or command tasks. Use when: editing cron.md, adding or changing cron schedules, or removing periodic jobs.

xuiltul Skill

Audio transcription tool. Converts audio files to text with Whisper and optional LLM post-processing. Use when: transcribing meetings, podcasts, or extracting text from recorded audio files.

xuiltul Skill

cron.mdを正しいフォーマットで読み書きするスキル。定時タスクの追加・更新・削除手順を提供する。 Use when: cron.mdの編集、cron式の追加、LLM型・コマンド型タスクの追加・削除、定時ジョブのメンテナンスが必要なとき。

xuiltul Skill

音声文字起こしツール。Whisperで音声ファイルをテキスト化し、必要に応じLLM後処理する。 Use when: 会議録音の転写、ポッドキャストの書き起こし、音声ファイルからテキスト抽出が必要なとき。

xuiltul Skill

cron.md를 올바른 형식으로 읽고 쓰는 스킬. 정기 태스크 추가·수정·삭제 절차를 제공한다. Use when: cron.md 편집, cron 식 추가, LLM·커맨드형 작업 추가·삭제, 정기 작업 점검이 필요할 때.

xuiltul Skill

음성 문자 변환 도구. Whisper로 오디오를 텍스트로 바꾸고 필요 시 LLM 후처리한다. Use when: 회의 녹음 전사, 팟캐스트 텍스트화, 녹음 파일에서 본문 추출이 필요할 때.

idwong Bundle

威胁建模与安全设计评审（STRIDE）：画数据流与信任边界 → 逐边界过 STRIDE → 写成攻击者视角的滥用用例 → 每条威胁配一条**可验证的缓解措施 + 测试用例编号** → 残余风险登记。产出落 `dev/design/`。 它在**写代码之前**发现问题：越权设计、凭据流转、多租户隔离、幂等与重放、文件上传、日志与留存、 第三方数据外发——这些在静态代码审计阶段发现时，改的成本已经翻了十倍。 触发词：「威胁建模」「安全设计评审」「STRIDE」「攻击面」「攻击面分析」「滥用用例」「这个设计安全吗」 「数据流图」「信任边界」「多租户隔离怎么做」「上传功能安全吗」「合规要求怎么落到设计里」「等保 / GDPR 怎么对」， 或 `dev-master` 阶段 3 概要设计完成、进详细设计之前。 不适用：写完代码后的静态安全审计与密钥扫描（`pm-ai-ship-audit`）、渗透测试与漏洞验证（不在本库）、 发布期的回滚与应急（`release-rollout`）、功能测试用例（`pm-test-cases`）。

xuiltul Skill

Full animaworks CLI reference: server, Anima lifecycle, models, tasks, config, RAG, assets, external tools. Use when: looking up subcommands, starting or stopping the server, or managing Anima, models, tasks, logs, config, indexes.

xuiltul Skill

animaworksコマンドの完全リファレンス。サーバー操作・Anima管理・モデル・タスク・設定・RAG・資産・外部ツールのCLI書式をまとめる。 Use when: サブコマンドの書式確認、サーバー起動停止、Anima作成・モデル変更・タスク追加・ログ・設定・インデックス操作が必要なとき。

xuiltul Skill

animaworks CLI 완전 레퍼런스. 서버·Anima·모델·태스크·설정·RAG·에셋·외부 도구 호출 구문을 정리한다. Use when: 서브커맨드 확인, 서버 시작·중지, Anima 생성·모델 변경·태스크·로그·설정·인덱스 조작이 필요할 때.

xuiltul Skill

Runs external AI agent CLIs via Bash in non-interactive mode. Delegates coding with codex exec or cursor-agent. Use when: offloading complex implementation, code review, multi-file edits, or spawning a subagent from Bash.

xuiltul Skill

外部AIエージェントCLIをBashで非対話実行するスキル。codex execやcursor-agentでコーディング作業を委譲する手順を提供する。 Use when: 複雑な実装の委譲、コードレビュー、複数ファイルの一括変更、Bashからサブエージェントを起動するとき。

xuiltul Skill

외부 AI 에이전트 CLI를 Bash로 비대화 실행하는 스킬. codex exec·cursor-agent로 코딩 작업을 위임한다. Use when: 복잡한 구현 위임, 코드 리뷰, 다중 파일 변경, Bash에서 서브에이전트 시작이 필요할 때.

mingdui Bundle

端到端 QA 验收编排器。当用户要求做功能验收、回归测试、质量检查、或对某个模块/流程/branch/PR进行系统化测试时触发。 作为顶层路由器，按阶段调度子 skill（上下文收集 → 风险分析 → 用例设计 → 脚本生成 → 执行与修复 → 代码审查 → 报告生成）。 你自己不写测试代码也不直接判断质量——你把每个阶段交给专职子 skill 处理。 用例确认是流程中唯一的强制人工门禁，其余阶段自动衔接。 不适用：单次手动测试、纯开发/代码生成任务、无明确验收范围的技术问答。

xuiltul Skill

Supervisor tools for subordinate Anima: disable/enable, model changes, restart, delegation, state reads, and audits. Use when: pausing a subordinate, changing main or background models, restarting processes, delegating tasks, or org dashboards.

clueless-creations Bundle

Explicitly delegate bounded classification, filtering, routing, and rubric scoring to TypeSafe Jev through Vercel AI Gateway. Use only when the user asks for fast-decision, Jev delegation, or an external quick judgment; keep reasoning and actions in the host agent.