В каталоге 183 730 навыков в 14 категориях.
[レビュー] Deep Review - 設計/セキュリティ/RDD整合の深掘りチェック
Multi-pass code review with security, quality, structural analysis, and validation
Deep code review — runs the built-in /code-review together with /codex-review, which carries the depth. Use when: (1) Us...
Comprehensive single-document review combining pessimistic and optimistic analysis with improvements. Modifies content.
Deep code review for pull requests, tuned to match CodeRabbit and Greptile depth but reported short. Checks two things s...
對 staged changes 執行三維度平行審查（安全、效能、風格），合成優先排序的發現摘要。
Run a deep code review across the manifold-csg crates
Deep investigation skill for PRs and bug fixes that go beyond surface review. Use this when a standard code review isn't...
Clause-by-clause contract risk analysis with severity scoring, financial exposure estimates, and prioritized remediation...
다중 전략 코드베이스 심층 탐색 워크플로우. Grep, SemanticSearch, Glob를 병렬로 실행하여 심볼, 패턴, 의존성을 종합적으로 분석. Use when performing deep codebase a...
【深度调研专用】当需要系统性调研、多产品对比、深度分析、技术选型、趋势分析时必须使用本技能。触发关键词：调研、对比、分析、评估、选型、趋势、综合报告、多源验证。通过 3 层深度搜索（阅读多个网页）+ 多源交叉验证，提供比普通 WebSear...
Monitor search agent reasoning quality via hierarchical uncertainty detection. Fast consistency checks identify anomalie...
Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide or scoped-path Codex Sec...
Perform fine-grained semantic relationship analysis; use when asked to compare meaning, resolve ambiguity, or map concep...
A deeply nested skill for testing 4+ level namespace generation.
最好的找Skill的方式，能够基于你的任务，去寻找最匹配的高质量Skill。以下三种情况下都应使用本技能：① 用户主动要找 Skill，或者需要借助他人经验时——当用户说"找个 xxx 技能""股票分析别人怎么做的""找一找有没有现成的技能...
Generate comprehensive multi-approach strategies before execution. Extract domain knowledge, create alternative approach...
Multi-perspective structural analysis for complex social, economic, philosophical, and systemic questions — produces str...
Transform a long private conversation, voice transcript, mentor chat, interview, or two-person deep talk into a privacy-...
Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging,...
Structured deep-reasoning workflow inspired by public Gemini Deep Think descriptions and research patterns such as multi...
Orchestrate one or more thinking frameworks to work through any problem, decision, document, or idea rigorously. Diagnos...
Deploy meta-cognition and recursive systems thinking mode. Use when need to question the question, find root causes of r...
Trace ลึกตาม execution flow, logs, metrics, หรือ distributed trace
Multi-angle release quality verification using parallel expert review teams
Master the art of focused, distraction-free work. Enter flow states reliably, protect your attention, and produce your b...
Autonomous goal-completion skill for complex, multi-step engineering and research work. Activate when the user says "wor...
Use when someone wants to plan a deep work day, time-block their calendar or task list, budget or cut shallow work, prot...
Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules...
当需要进入并维持高度专注的深度工作状态时
当需要进入并维持一段高度专注、无干扰的工作状态以处理复杂任务时
Focus blocks, distraction management, and flow state triggers for cognitively demanding work
马斯克时间盒管理法：时间固定，范围可变。用 MVU 驱动 AI 在限定时间内最大化交付完成度，而非完美主义。触发词：时间盒、启动任务、mvu、限时完成。
DeepAgent-style memory folding for VCO sessions: compress long context into structured working/tool memory without using...
DeepAgent-style tool discovery for VCO: propose a minimal skill/tool chain (with verification points) and reduce confirm...
LangChain Deep Agents framework for building autonomous coding agents. Use for agent harness, backends, subagents, human...
使用 Deep Agents CLI - 终端界面、持久化内存（AGENTS.md）、项目约定、技能目录和 CLI 命令。
Deep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep...
Deep Agents CLI reference and usage guide. Use when the user wants to: (1) Launch or configure the deepagents terminal c...
使用 FilesystemMiddleware 实现虚拟文件系统、后端（State、Store、Filesystem、Composite）和 Deep Agents 的上下文管理。
在 Deep Agents 中实现人工审批工作流，使用 interruptOn 参数对敏感工具操作进行人工干预。
deepagents framework integration patterns for agent creation, planning, filesystem operations, and subagent orchestratio...
在 Deep Agents 中实现长期内存，使用 StoreBackend、CompositeBackend 和 InMemoryStore 进行跨会话的持久化数据存储。
理解 Deep Agents 框架 - 它们是什么、如何使用 createDeepAgent 创建，以及 agent harness 架构，包括内置的规划、文件系统和子代理中间件。
在 Deep Agents 中创建和使用自定义技能，实现渐进式披露、SKILL.md 格式和 Agent Skills 协议。
在 Deep Agents 中使用 SubAgentMiddleware 启动子代理进行任务委托、上下文隔离和专门工作。
Using TodoListMiddleware for task planning and tracking progress with the write_todos tool in Deep Agents for complex mu...
Use DeepAPI for supported scraping, research, and email workflows with explicit credentials and approval.
Use DeepAPI for all regular web searches (POST /v1/search/web) and for any deep research you perform (POST /v1/research/...
Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifac...
Help developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Codex needs to...
Prepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update CHANGELOG...
Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architectu...
Use only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after implementa...
DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepCha...
Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pre...
Kit de ferramentas de machine learning molecular. Predição de propriedades (ADMET, toxicidade), GNNs (GCN, MPNN), benchm...
Deep learning for drug discovery. 60+ models (GCN, GAT, AttentiveFP, MPNN, ChemBERTa, GROVER), 50+ featurizers, Molecule...
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditi...
Builds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold o...
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend at up to 1...
Lead a team of Claude Code members driven by DeepSeek (or another Anthropic-compatible provider) to build or change a pr...
Full specialist analysis via parallel agent dispatch. Researcher, Architect, and PM produce a prioritized report of what...
Meta-research под вопрос или решение: веб-поиск, источники, Q&A отчёт с цитатами по файлам для повторного использования....
Targeted deep research to fill a specific gap in an existing thesis. Use when user says "deepen", "flesh out", "expand o...
Use when improving module design without changing behavior ('deepen this', /ck:deepen).
Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the sp...
Hold an ask to the bar a top professional in its field would set — a deeper ask, never a bigger one. Use when an ask is...
Use when a person asks to design a new module's interface or to rework an existing module so that it hides much behind l...
Enhance an existing plan with parallel research, per-section analysis, and updated beads tasks.
Enhance an existing marketing plan with parallel research. Use when the agent has a draft plan (brand strategy, campaign...
Reframe a task or rewrite a prompt for greater rigor when asked for a deeper approach, expert methods, or more ambitious...
Deepen a task by examining its intended outcome, strengthening its methods, and borrowing useful techniques from other f...
Comprehensive 6-phase research funnel — 8-10 parallel survey agents sweep wide, a synthesizer compiles evidence, deep-di...
DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration
Basic usage guide for the DeepFace library (face recognition, verification, analysis).
Run a tabletop drill of a voice-clone or deepfake fraud attempt — the 'CEO needs this wire today' call — against your ac...
Automate Deepgram tasks via Rube MCP (Composio). Always search tools first for current schemas.
Configure Deepgram CI/CD integration for automated testing and deployment. Use when setting up continuous integration pi...
Diagnose and fix common Deepgram errors and issues. Use when troubleshooting Deepgram API errors, debugging transcriptio...
Implement speech-to-text transcription workflow with Deepgram. Use when building pre-recorded audio transcription, batch...
Optimize Deepgram costs and usage for budget-conscious deployments. Use when reducing transcription costs, implementing...
Collect Deepgram debug evidence for support and troubleshooting. Use when preparing support tickets, investigating issue...
Configure enterprise role-based access control for Deepgram integrations. Use when implementing team permissions, managi...
Create a minimal working Deepgram transcription example. Use when starting a new Deepgram integration, testing your setu...
Install and configure Deepgram SDK/CLI authentication. Use when setting up a new Deepgram integration, configuring API k...
Configure Deepgram local development workflow with testing and iteration. Use when setting up development environment, c...
Set up comprehensive observability for Deepgram integrations with metrics, traces, and alerts. Use when implementing mon...
Execute Deepgram production deployment checklist. Use when preparing for production launch, auditing production readines...
Implement Deepgram rate limiting and backoff strategies. Use when handling API quotas, implementing request throttling,...
Apply production-ready Deepgram SDK patterns for TypeScript and Python. Use when implementing Deepgram integrations, ref...
Apply Deepgram security best practices for API key management and data protection. Use when securing Deepgram integratio...
Select and tune a Deepgram TTS voice - curated voice list, full Aura voice catalog via API key, and tuning parameters
Receive and verify Deepgram webhooks (callbacks). Use when setting up Deepgram webhook handlers, processing transcriptio...
深度代码库初始化，生成分层 AGENTS.md 文档
Create or refresh hierarchical AGENTS.md documentation for Claude Code, Codex/OMX, Gemini, and Antigravity/OMA projects,...
Initialize project harness — AGENTS.md as table of contents, ARCHITECTURE.md as domain map, structured docs/ knowledge b...
코드베이스를 인덱싱하고 계층형 AI-CONTEXT.md 파일을 생성하는 스킬. "/deepinit"을 입력하거나, "코드베이스 문서화해줘", "AI 가이드 만들어줘", "AI-CONTEXT.md 생성해줘" 같은 요청...
Deep codebase initialization with hierarchical AGENTS.md documentation
Translate text with DeepL: translate between 30+ languages, list languages, check usage. Trigger phrases: deepl, transla...