Create or update an audit of recent decisions for quality
Score 70/100
Create or update a structured decision record
Score 70/100
Use when making architectural or business logic decisions during conversations - adds entry to DECISIONS.md
Score 70/100
Facilitate data-driven technical decisions using embedded decision matrices and trade-off analysis. Use when relevant to the task.
Score 70/100
Git-powered state awareness - track file changes, session context, decisions, and work history. Query what happened in previous sessions and during current session.
Score 70/100
ADR management and decision logging. Use when documenting architectural decisions, tracking technical choices, or creating decision records.
Score 70/100
Decision tree analysis skill with expected value, risk analysis, and utility theory.
Score 70/100
決策樹助手工具。快速評估任務複雜度，提供派發建議。用於: (1) 任務複雜度快速評估, (2) 派發代理人建議, (3) 拆分策略建議, (4) 並行可行性評估
Score 70/100
Load past architectural decisions. Use when making new decisions to ensure consistency.
Score 70/100
Guidance on when to ask clarifying questions vs proceed with standard approaches. Reduces unnecessary interaction rounds.
Score 70/100
Create, update, and translate Dify X Reveal.js slide decks in this repo. Use when asked to draft slides, extract outlines, or maintain bilingual CN/EN parity for the…
Score 70/100
Updates a presentation with new numbers — quarterly refreshes, earnings updates, comp rolls, rebased market data.
Score 70/100
Stream Deck integration assistant for VSCode. Create, manage, and organize Stream Deck profiles, buttons, snippets, and scripts.
Score 70/100
Expert assistant for creating Deckset presentations with markdown. Helps with slide formatting, headings, lists, images, videos, presenter notes, build steps, themes, and…
Score 70/100
Reviews Go variable and constant declarations for proper scope, grouping, and zero value usage. Use when reviewing declaration blocks, creating new Go packages, or seeing…
Score 70/100
Complete development kit for Microsoft 365 Copilot declarative agents with three comprehensive workflows (basic, advanced, validation), TypeSpec support, and Microsoft 365 Agents…
Score 70/100
Use the decomp-permuter to automatically find C code variations that match target assembly. Useful when stuck at 99%+ match with stubborn register allocation issues.
Score 70/100
Turn an APK into readable Java or decompiled source artifacts so an agent can inspect behavior before deeper reverse-engineering or triage.
Score 70/100
Architectural code analysis for design quality. Evaluates simplicity (Rich Hickey), functional core/imperative shell (Gary Bernhardt), and coupling (Constantine & Yourdon).
Score 70/100
Break a feature into ordered, agent-sized GitHub issues that the ship-loop can work through sequentially.
Score 70/100
Use when starting plan execution to decompose implementation plans into Claude Code Task tool tasks at H2 (Task) granularity - creates one task per plan task with citation-manager…
Score 70/100
Decompose a phase plan into atomic beads and sub-beads. Use when breaking down a phase into tasks, when the user mentions "decompose" or "break down", when creating beads from a…
Score 70/100
Use when the architect (or Board Manager) brings a design doc, spec, or multi-point requirement that needs to be turned into GitHub Project cards.
Score 70/100
Break down large tasks into smaller, actionable items. Use when planning sprints, estimating work, or creating implementation plans. Covers task breakdown strategies.
Score 70/100
Use when you need to create an execution plan from a feature spec - handles worktree context, dispatches subagent for task decomposition, validates quality, analyzes dependencies,…
Score 70/100
First-principles analyst. Surfaces hidden assumptions, finds foundational truths, rebuilds from scratch, identifies the high-leverage move.
Score 70/100
Resolve duplicate entities across CSV datasets using machine-learning record linkage. Use when CRM data has duplicates, data sources need reconciliation, or entity names are…
Score 70/100
Automate Deel tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Deep Agents LangChain CLI (import deepagents, deepagents-cli). ТОЛЬКО при: deepagents, FilesystemBackend, StoreBackend, CompositeBackend, TodoListMiddleware, SubAgentMiddleware,…
Score 70/100
Perform complex fault analysis requiring multi-step diagnostics and subtask decomposition. Use when user asks to "troubleshoot", "analyze root cause", "why is network slow",…
Score 70/100
Deep codebase analysis that extracts learnings from documentation. Creates context entries and learnings from docs/ with pattern matching.
Score 70/100
· Orchestrate a 5-wave repo audit, persist findings, generate phased tasks. Triggers: 'deep audit', 'full audit', 'comprehensive review', 'audit report', 'mega review', 'deep…
Score 70/100
Comprehensive deep learning guidelines for neural network development, training, and optimization.
Score 70/100
Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.
Score 70/100
Universal links and deep linking skill for implementing iOS Universal Links, Android App Links, custom URL schemes, and deferred deep linking across mobile platforms.
Score 70/100
Analyzes development sessions to extract patterns, preferences, and learnings. Use after significant work sessions to capture insights, document system understanding, and improve…
Score 70/100
Comprehensive single-document review combining pessimistic and optimistic analysis with improvements. Modifies content.
Score 70/100
Comprehensive single-document review combining pessimistic and optimistic analysis with improvements. Modifies content.
Score 70/100
Comprehensive single-document review combining pessimistic and optimistic analysis with improvements. Modifies content.
Score 70/100
【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 WebSearch 更全面、更准确的研究结果和深度洞察。禁止用普通搜索工具替代深度调研任务。
Score 70/100
Generate comprehensive multi-approach strategies before execution. Extract domain knowledge, create alternative approaches, identify failure modes, and develop risk-aware plans.
Score 70/100
Deploy meta-cognition and recursive systems thinking mode. Use when need to question the question, find root causes of root causes, or escape current system constraints.
Score 70/100
Focus blocks, distraction management, and flow state triggers for cognitively demanding work
Score 70/100
Expert guidance for DeepAgents framework - simplified agent creation with tool integration for LangChain/LangGraph workflows.
Score 70/100
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop…
Score 70/100
deepagents framework integration patterns for agent creation, planning, filesystem operations, and subagent orchestration. Current version 0.2.5 with LangGraph 1.0.2+
Score 70/100
Prepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update CHANGELOG.md, keep release notes bilingual from v1.0.1 onward with…
Score 70/100
Basic usage guide for the DeepFace library (face recognition, verification, analysis).
Score 70/100
Automate Deepgram tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Configure enterprise role-based access control for Deepgram integrations. Use when implementing team permissions, managing API key scopes, or setting up organization-level access…
Score 70/100
Configure Deepgram multi-environment setup for dev, staging, and production. Use when setting up environment-specific configurations, managing multiple Deepgram projects, or…
Score 70/100
Set up comprehensive observability for Deepgram integrations. Use when implementing monitoring, setting up dashboards, or configuring alerting for Deepgram integration health.
Score 70/100
Plan and execute Deepgram SDK upgrades and model migrations. Use when upgrading SDK versions (v3 to v4 to v5), migrating models (Nova-2 to Nova-3), or planning API version…
Score 70/100
Übersetzt Texte, Dokumente und XLIFF-Dateien via DeepL API. Verwende für Übersetzungen mit /deepl translate, /deepl file oder /deepl xliff.
Score 70/100
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
Score 70/100
Plan 문서의 탐색 폭/검증 깊이가 부족할 때 깊이 있는 Plan을 생성한다. — MUST TRIGGER: 복잡도 8+ 작업, 아키텍처 분기 결정, /nova:plan 결과가 얕다고 판단되는 경우, 사용자가 /nova:deepplan 호출.
Score 70/100
当用户要求"DeepSeek API 集成"、"AI 服务"、"生成回复建议"、"调用 LLM"、"HTTP 请求"、"流式响应"、"连接池优化"、"重试策略"，或者提到"DeepSeek"、"API 调用"、"reqwest"、"streaming"时使用此技能。用于 DeepSeek API 集成、HTTP 客户端配置、错误处理、流式响应、连接池优化和…
Score 70/100
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
Score 70/100
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
Score 70/100
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
Score 70/100