В каталоге 183 730 навыков в 14 категориях.
Internal skill used by ds-plan at Phase 2 exit gate. Dispatches a reviewer subagent to verify PLAN.md quality before imp...
Files a short, clear pull request for the current branch. Use when the user asks to open, file or create a PR, or says /...
Formats and posts GitHub comments written by an agent on the user's behalf, with clear attribution and no leaked secrets...
Compact engineering principles for design, debugging, verification, and delegation, each with a trigger. Use when choosi...
DS Prototype — creates clickable prototype flows in Figma by connecting screens with interactions and transitions. Build...
DS QA Coverage — final quality assurance pass for the complete Figma ecosystem. Verifies: all current screen-inventory e...
Runs the full ds-ship workflow but stops with the pull request ready for a human to merge, and never merges. Use when th...
This skill should be used when running Phase 4 of the /ds workflow to review methodology, data quality, and statistical...
Runs an author and a fresh-context reviewer in a loop on the current change until both agree it is correct, for at most...
Brings an old PR up to date by checking if its idea still fits the current code, then rebasing, reworking or recommendin...
Deep technical review of data science, MLOps, and machine learning projects. No feelings attached — pure roast mode. Sur...
The DS constraints C1-C6, V1-V9, A1-A6, E1-E7 as binding rule statements. Preloaded by the ds and ds-reviewer agents; lo...
DS Screen Builder — builds app screens in Figma Screens file using ONLY DS components, tokens, and styles. Reads Swift v...
Restate the user's goal, make the task deeper rather than bigger, rewrite the prompt, and optionally attack the plan to...
Takes a change all the way from code to a merged pull request without supervision: build it, prove it, review it, file t...
Internal skill used by ds-brainstorm at Phase 1 exit gate. Dispatches a reviewer subagent to verify SPEC.md completeness...
Multi-agent data science framework using DS-STAR (Data Science - Structured Thought and Action) architecture. Automates...
Fan out N parallel workers on slices of a job or on a race, collect every result, and return one evidence-backed report....
Fix a bug by first writing a focused test that fails for the right reason, then making the smallest change that makes it...
This skill should be used when the user asks "what plugins are available", "list data science tools", "what MCP servers...
Remove AI writing tells from prose and code comments, then rewrite in plain, specific English. Use when writing or editi...
Break out of a repeating failure: name the assumption behind all the failed fixes, test it directly, list three other ap...
Validate analysis outputs against SPEC.md requirements using DQ checks.
This skill should be used when the user asks to 'verify analysis results', 'check reproducibility', 'validate data scien...
Run edit, real check, read the actual error, fix the root cause, rerun, until the check passes or the cap is hit. Use wh...
Watches a pull request through CI and review, fixes real findings and stops when it is ready, merged or blocked. Use whe...
Use when converting PubMed `DocumentSummary` XML into `Pubmed-entry` ASN.1 text, or into the intermediate XML form befor...
| Topic | Score (out of 10) |
Prüfung und Gestaltung des Melde- und Abhilfeverfahrens (Notice-and-Action) nach Art. 16 DSA samt Begründungspflicht Art...
Erstellung eines DSA-konformen 'Statement of Reasons' nach Art. 17 DSA bei Inhaltsmoderations-Entscheidungen (Sperrung,...
Drafts a GDPR- and CCPA-compliant Data Subject Access Request (DSAR) intake form for collecting requester information an...
Daily GDPR data-subject-access-request runbook. Verifies each incoming request from Gmail, locates the subject's data re...
Builds a multi-channel DSAR intake system supporting web form, email, phone, and in-person requests with identity verifi...
Guides AI agents through the complete GDPR Data Subject Access Request (DSAR) workflow under Article 15, including ident...
Bestellungspflicht für Datenschutzbeauftragten prüfen. Art. 37 DSGVO § 38 BDSG Bestellungspflicht. Prüfraster: Schwellen...
When the user wants to optimize Direct Store Delivery (DSD) routes, plan delivery schedules for retail stores, or improv...
Convert DSDS UI specs, mock HTML screens, and system docs into concrete frontend component implementation tasks. Use whe...
Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes para...
Datenschutz-Folgenabschätzung (DSFA) nach Art. 35 DSGVO erstellen: Schwellwertanalyse, BfDI-Blacklist-/Whitelist-Abgleic...
Erstellt Datenschutz-Folgenabschätzung für Roboter mit Sensorik, Telemetrie, KI-Auswertung oder vulnerablen Nutzergruppe...
Création d'interfaces web conformes au Design System de l'État Français (DSFR). Utiliser ce skill pour générer des pages...
Apply GDPR workflows and EU AI Act Article 50 disclosure decisions for Ottili flows: processing register entries, human-...
Unterstützt bei der Bearbeitung von Auskunftsersuchen nach Art. 15 DSGVO – von der Identifizierung der betroffenen Perso...
Wenn es um DSGVO-Auskunftsrecht (Art. 15 DSGVO) in Datenschutzrecht geht: prüft Frist, Form, Zuständigkeit, Rechtsweg un...
DSGVO-Auskunftsantwort an Betroffenen vollständig und rechtskonform gestalten. Art. 15 12 Abs. 3 DSGVO Antwortpflicht. P...
DSGVO-Textbausteine für KI-Nutzungsrichtlinien in Kanzleien: Anwendungsfall Kanzlei erstellt oder aktualisiert KI-Richtl...
Produkt aus dem Ausland auf DSGVO-Rechtswidrigkeit prüfen: Richter oder Anwalt muss beurteilen ob Smartglasses oder IoT-...
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new...
设计或审查测试覆盖、选择单元/集成/真实入口/端到端测试及 mock 边界时使用；也用于诊断偶发失败、异步、并行及持有资源的测试。适用于测试计划、回归覆盖缺口和不可靠的 CI 证据。
设计、实现或审查客户端 UI、响应式布局、交互状态、焦点或失败反馈时使用，结合真实运行界面验证用户体验。
Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGEN...
审查代码改动或 PR 时使用，依据目标项目的实际需求检查正确性、生命周期、接口行为、验证证据和文档，报告有依据且可采取行动的问题。
把 DSH（DeepSeek Harness）的用户配置（~/.dsh 下的 AGENTS.md、settings.yaml 及可选 profiles/预设）打包成脱敏骨架并在设备间安全同步恢复，提供只读审计、显式应用与 SHA-256 校...
Конвертация промтов, инструкций и скилов ChatGPT/Claude в формат DeepSeek Harness (DSH)
Operate dsh on WSL systemd — boot, autostart, market proxy.
创建或维护工程文档、设计决策、事故复盘、归档提案或产品迁移指南时使用，保留事实依据、实际备选方案和准确状态。
Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts...
Use when writing, moving, reviewing, or auditing documentation in the deepseek-harness repo — choosing hierarchy and det...
用于功能开发、问题修复和实现设计，按项目现有约定处理默认值、输入校验、依赖和测试选择；也用于诊断、接入、更新或撤销项目 AI 工程规范，保留原有政策和本地修改。用户提出“按 DSH 规范开发”或“接入 AI 工程规范”时使用。
实现或审查错误传播、部分成功、结果未知、恢复、重试、取消或失败反馈时使用，明确状态保证和错误处理责任。
Use when working in the deepseek-harness repo to find non-obvious simplification candidates, write proposed Agent Notes...
用户明确要求审查或实施简化时使用，识别不必要的抽象、重复状态和兼容机制，并验证受支持行为得到保留。
Rebuild the DSH node's persistent knowledge state. Runs register-claude.py to (re)create the dome.db schema and upsert a...
Decode the marker fixture used by the DeepSeek Harness integration example.
Use when landing a stack of dependent GitHub PRs (A ← B ← C, where each bases on the one below) onto master, merging a P...
Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and i...
在交付或推送前验证改动时使用，核实项目必需检查、当前构建产物和真实用户行为，区分通过、失败、未运行与环境阻塞。
Use when writing, reviewing, restoring, trimming, or auditing prose in the deepseek-harness repo, including deciding whe...
用户要求从真实浏览器应用录制 GIF 演示时使用，完成实际操作、采集、本地编码和结果核验。
DSH 角色与能力边界。规定哪些工作可以交给 DSH（非视觉代码实现/修复、只读探索、代码审查、文本整理）、哪些绝对不可以（绘图、图像生成/编辑、识图、OCR、截图分析、GUI 视觉判断与验收、长等待），以及分派时必须附带的上下文、审查、权...
Install DSH on a fresh Mac. Runs sovereign-setup-mac.sh, renders .env from secrets backend, applies full sovereign lockd...
调查性能问题或优化实际测量的用户路径时使用，建立优化前后对照，保留正确性、失败行为和真实运行证据。
Delegate tasks to persistent DeepSeek Harness agents through the dsh_subagent MCP server. Use when the user asks to use...
Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose t...
仅在用户明确调用时翻译或同步指定文档，保留技术含义、结构、命令和两边的独立修改。
Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as...
DSIM simulator debugging and troubleshooting. Use when investigating compilation errors, runtime failures, waveform anal...
Use when designing or tuning exit logic for a Freqtrade strategy — ratcheting trailing stop, two-phase exit, ALO-aware e...
Reverse JavaScript-based custom DSL/VM interpreters, non-standard WASM-like runtimes, and risk-control engines. Use when...
Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and...
Turn a finished design into a developer-ready handoff spec - tokens, every interactive state, responsive breakpoints, an...
Write and review interface microcopy - errors, empty states, buttons, labels, and CTAs - that is clear, concise, human,...
Implementation guide for common DSP algorithms. Use when the user asks "implement a lowpass filter", "how do I write a c...
Production-ready DSP algorithms including filters, compressors, delays, modulation effects, saturation, and distortion w...
Design and test DSP filters (highpass, lowpass, bandpass, notch) for WaveCap-SDR. Use when adding filters to demodulatio...
Use when working on the DSP engine, biquad cascade, kernel math, interpolation, minifloat codec, coefficient ramping, AG...
Pick the right buying platform for a goal among Google Ads, DV360, Amazon DSP, The Trade Desk, and StackAdapt. Use when...
You are an expert in DSPy, the Stanford framework that replaces prompt engineering with programming. You help developers...
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and ag...
Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct),...
DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and com...
DSPy is a Python framework from Stanford NLP that replaces hand-written prompts with code: you declare LLM tasks as type...
DSPy: declarative LM programs, auto-optimize prompts, RAG.
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
Program LM pipelines with DSPy — define Signatures (input/output fields), build Modules (ChainOfThought, ReAct, Predict)...
Use when you need to customize how DSPy formats prompts for a specific provider — switching from chat to completion form...
Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and m...
This skill should be used when the user asks to "compose DSPy modules", "use Ensemble optimizer", "combine multiple prog...
Legacy reference for dspy.Assert and dspy.Suggest, both removed in DSPy 3.x - use dspy.Refine or dspy.BestOfN instead. U...
Use when you need to run DSPy modules asynchronously — FastAPI endpoints, concurrent LM calls, non-blocking execution, o...