В каталоге 183 730 навыков в 14 категориях.
Attach new behaviour to objects at runtime by wrapping them in decorator objects.
NestJS decorator usage: built-in route/param/class decorators, custom decorators via `createParamDecorator` and `SetMeta...
Before producing significant creative, analytical, or critical output, diagnose what register the task requires — not 'w...
Judge whether the public PROSE reads professionally — tone, brand-voice, clarity, credibility — and record a content-pin...
Decrypt MCP tokens for remote sessions
Decrypts statically embedded malware configuration blobs by trying common schemes (single-byte and multi-byte XOR, RC4,...
Dedicated server skill for deployment, scaling, and orchestration.
Use when building dedicated servers — headless export, server architecture, lobby management, and deployment
Find and merge duplicate or near-duplicate notes anywhere in a vault (rules, concepts, people, leads) with a determinist...
The cite-don't-restate pass for every phase artifact. Before writing each section, check overlap with prior-phase artifa...
Deduplicate and decontaminate text corpora for LLM training: MinHash/LSH near-duplicate detection, n-gram and embedding-...
Batch analysis of hundreds of fuzzer divergences using parallel subagents - categorize, deduplicate, identify unique bug...
Ledger-first dedup of a skills/ or prompt-directory tree. Use when the user asks to dedup skills, find rules repeated ac...
Merge two open `<issue-tracker>` issues that describe the same root cause, preserving both reporters' context. Proposes...
DEPRECATED: This skill has been replaced by memory/check_seen and memory/mark_seen tools. Use fetch-rss-feeds or other c...
Event deduplication with canonical selection, reputation scoring, and hash-based grouping for multi-source data aggregat...
The Sovereign Asset Title & Ownership Protocol. A high-fidelity cognitive framework for the immutable registration, ver...
Drafts a recordable U.S. Deed of Gift for voluntary, no-consideration transfers of real or personal property. Enforces p...
Drafts combined Deed of Trust and Security Agreement instruments creating real property and UCC Article 9 personal prope...
Requires curl and network access to deed.page; no account or API key. Free plan: 25 public sites, 25 MB each; paid plans...
Deel integration via Apideck's HRIS unified API — same methods work across every connector in HRIS, switch by changing `...
Deel integration. Manage hris data, records, and workflows. Use when the user wants to interact with Deel data.
Automate Deel tasks via Rube MCP (Composio). Always search tools first for current schemas.
Runs an iterative auto-fix loop on a chosen target — review, refactor, or coverage — dispatching the base skill into fre...
Advanced problem-solving skill using sequential thinking. Use for complex architectural decisions, debugging hard proble...
Investiga documentación oficial y valida soluciones en internet antes de implementar.
Research a question across web and academic sources and produce a cited report.
---name: deep-visual-proteomics-agent
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md...
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral),...
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, Todo...
Analytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Prov...
Investigate a game from raw logs, trace bugs to source code, and file detailed issues. Use for deeper debugging than exp...
Structured multi-step reasoning for complex problems using MCP. Use this skill when facing architectural decisions, perf...
Execute high-density analysis on complex ideas/tasks. Move from 'Vague' to 'Verified' by producing: constraints -> core...
Deep exploration and synthesis workflow using parallel task agents with dynamic planning and hub-and-spoke coordination....
Reusable deep exploration and synthesis workflow. Use when asked for "deep analysis", "deep understanding", "analyze cod...
Perform complex fault analysis requiring multi-step diagnostics and subtask decomposition. Use when user asks to "troubl...
Tiefenanalyse eines Problems gemäß der OBERSTEN DIREKTIVE. Verfolgt den vollständigen Datenfluss React-View→tauri-api.ts...
Deep codebase analysis that extracts learnings from documentation. Creates context entries and learnings from docs/ with...
Deep consistency audit of the entire repository infrastructure. Launches 4 parallel specialist agents to find factual er...
· Run 5-wave repo audits, persist findings, and generate phased tasks. Triggers: 'deep audit', 'full audit', 'comprehens...
Use when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is costly, w...
รัน build แบบลึก ครอบคลุมหลาย target, platforms, bundle analysis, และ performance smoke test
Guide for running deep code scanning with LLM-generated symbol descriptions.
Hotspot-first, multi-pass code review for pull requests, branches, pasted diffs, and work-in- progress changes. Models b...
Review a repository snapshot or code change for evidence-backed correctness, security, compatibility, and regression ris...
MUST CHECK FIRST before DeepWiki or any external research. Local-first codebase documentation wikis. **Priority order f...
Deep Confidence Harness — a thinking, planning, and execution framework that forces structured reasoning before acting....
Cross-channel research on any topic. Searches Obsidian, Jira, Confluence, Slack, Gmail, and GitHub in parallel, then syn...
Prompt này yêu cầu AI đóng vai trò chuyên gia chiến lược marketing và nghiên cứu hành vi khách hàng để phân tích insight...
Multi-agent investigation for stubborn bugs. Use when: going in circles debugging, need to investigate browser/API inter...
Debug อย่างละเอียดหลายมิติ ตั้งแต่ reproduce จนถึง prevent recurrence
Runs a checkpoint-gated decision process for consequential, forward-looking design choices. Optional --circuit skips int...
Cross-runtime 2-stage pipeline for Claude Code, Codex/OMX, and Gemini/Antigravity/OMA: trace causal hypotheses, inject e...
Use this skill when requirements are incomplete, conflicting, or too vague to begin implementation safely.
Rigorous multi-agent deep-dive analysis for complex investigative tasks — auditing codebases, evaluating strategies or s...
2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection
Use when a learner has surface understanding and needs to explore mechanism, tradeoffs, edge cases, and production impli...
Perform exhaustive analysis of a critical IOC. Use when an IOC needs Tier 2+ investigation beyond basic enrichment - inc...
Write a financial and operations deep dive for a small business that has shared its real numbers — P&L, revenue by line,...
Deep executor mode for complex goal-oriented tasks
プロジェクト内/外部対象に対する構造化された深層分析を提供する読み取り専用ユーティリティスキル。 スキル、機能、OSS、ライブラリ、技術コンセプトなど「これは何？」に対する一貫した回答を提供する。 例: - /deep-explain f...
Deprecated name. Use plan-review; load this notice only when deep-grill is explicitly requested.
코드베이스 인덱싱 및 구조 분석. 프로젝트를 스캔하여 모듈별 요약, 의존성 그래프, 진입점 맵을 생성하고 project context를 풍부하게 합니다. Use when onboarding to a new codeb...
Ambiguity gating — detects vague feature requests and forces structured requirements gathering with scoring across scope...
Socratic deep interview with mathematical ambiguity gating before explicit execution approval
Socratic deep interview with mathematical ambiguity gating before execution
소크라테스식 인터뷰를 통해 모호한 요구사항을 명확한 스펙으로 만드는 스킬. 사용자가 "/deep-interview"를 입력하거나, 요구사항 정리/기능 정의/문제 분석을 요청할 때 사용한다. PRD가 빈약하거나, 요청...
Mathematically rigorous Socratic interview system that drives ambiguity below 20% before any code is written. One questi...
Ask one focused question per round about a vague request, score the ambiguity, and write a spec that lit-plan can use. U...
Socratic deep interview with mathematical ambiguity gating before autonomous execution
"What is REALLY at stake here? And for whom?" - STOP. When the matter involves trustworthiness, purchasing decisions, "w...
深度调查模式：可以深入调查和分析确定目标的详细信息，并提供完整综合报告
Deep Learning expertise from Google DeepMind - creators of AlphaGo, Transformers, and BERT. Master neural network archit...
Build and train deep neural networks including CNNs, RNNs, Transformers, and advanced architectures. Use for image class...
Neural networks, CNNs, RNNs, Transformers with TensorFlow and PyTorch. Use for image classification, NLP, sequence model...
Build and train neural networks with PyTorch - MLPs, CNNs, and training best practices
Study companion and working knowledge base for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press,...
Universal links and deep linking skill for implementing iOS Universal Links, Android App Links, custom URL schemes, and...
| ID | flutter-deep-linking |
Deep links, universal links and app links in React Native. Use when links do not open the app, for apple-app-site-associ...
Professional Deep Linking Expert skill. Build performance-tuned, secure, and intuitive mobile applications for iOS and A...
Deep linking with Universal Links (iOS) and App Links (Android). Platform setup, domain verification, GoRouter integrati...
Generate deep linking infrastructure with URL schemes, Universal Links, and App Intents for Siri/Shortcuts. Use when han...
Universal Links, App Links, and URL scheme configuration.
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by...
Measures module depth, whether the interface is simple relative to the implementation behind it. Use when a module's int...
Closed-loop depth mining. Mines zone, validates with experts, forges build-ready agent prompts. Use when user says /deep...
Research-validated planning — research → plan → verify cycle for high-confidence implementation plans
Use when starting a new feature or idea that needs thorough pre-execution planning. Use instead of calling /product-revi...
Structured clarification before decisions. Use when user is in PLANNING mode, explicitly asks to plan or discuss, or whe...
Canonical analyze + plan — วิเคราะห์ลึกแล้ววางแผน implementation-ready ในคำสั่งเดียว
Deep prospect real estate leads to identify decision-makers when skip tracing fails. Use when user provides a property a...
Reduce redundant tokens in parallel reasoning by 80% while maintaining accuracy via dynamic pruning of equivalent reason...
Use when a project-local paper dossier should produce graph delta JSON proposals and run through the human-gated delta l...
使用 Playwright 读取公开网页或登录后网页的最终 HTML。适用于用户想要网页 HTML、需要在手动登录后继续读取页面，或希望分析登录后最终渲染内容的场景。优先使用本地 exe；如果只有 skill 且没有 Python，则优先运...
Read, study, and answer questions about long books and papers without loading the whole text into one context window, ke...
Reads an entire file and produces a structured content map showing sections, entities, claims, and gaps. Use when needin...