Навыки: Разработка

Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the sp...

深度代码库初始化，生成分层 AGENTS.md 文档

Deep codebase initialization with hierarchical AGENTS.md documentation

Translate text with DeepL: translate between 30+ languages, list languages, check usage. Trigger phrases: deepl, transla...

Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pi...

GTM prospecting, enrichment, outreach, plays. Providers: adyntel,affinity,ai_ark,akta,allegrow,amplemarket,apify,attenti...

Send Deepline SDK/V2 CLI feedback or bug reports, including environment info and the current Claude/Cowork session trans...

Use this skill when a Deepline Play needs human review, evaluation against golden labels, or bounded iterative improveme...

Run a quick Deepline demo recipe on the V2 CLI using prebuilt plays.

Use this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the ag...

Use when discovering niche signals, auditing ICP or won/lost evidence, rescoring accounts, or building account and lead...

Use this skill for any GTM Engineering work in Deepline — prospecting, list-building, account research, contact enrichme...

Deep research assistant that transforms user questions into high-quality queries, calls Google Deep Research, and delive...

Thorough codebase search

Deep internet research agent for training domain-specialist agents. Use when: researching a technical domain to create a...

DeepSeek Harness (dsh) CLI 安装、启动、launcher flag 坑、WSL 后台保活。

DeepSeek special model reasoning bridge - Advanced multi-step reasoning via MCP, bridging devuser to deepseek-user for c...

Leveraging thinking tokens with DeepSeek R1.

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Mi...

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and autom...

ByteDance's open-source super agent harness — spawns parallel sub-agents, Docker sandbox execution, persistent long-term...

Defeats control-flow-flattening obfuscation by identifying the dispatcher/state- variable structure and reconstructing t...

Recovers obfuscated strings and resolves dynamically loaded APIs in malware: reversing XOR/stack-string/encoding schemes...

缺陷修复的闭环流程：分级与范围锁定、先有失败测试再改代码、最小改动、按影响面推导回归范围、验证证据、修复记录与关闭条件。当用户要修某个缺陷、按缺陷单修复、修复后要验证与回归、判断缺陷严重度与优先级、控制修复范围、要写修复记录、判断这个缺陷能...

Use when the user asks to create point defects such as vacancies, substitutional defects, or interstitial atoms in a cry...

Build detections as a repeatable pipeline, not one-off alerts. Load for "improve our detections", "detection as code", "...

Detect attacker activity in network telemetry — C2 beaconing, DNS tunnelling, data exfil, and lateral movement. Load for...

A prop whose markup is built outside a render — pushed onto a queue, held in a signal, sent from a promise — is typed `(...

Defi reference tool. Use when working with defi in blockchain contexts.

Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and flash loans. Use when buildi...

Master DeFi protocol development including AMMs, lending, yield, and oracles

Pin a measurable, outcome-based Definition of Done for a diamond — a behaviour-change that creates value, not a build-li...

Use when extracting dialogue/UI text into structured localization keys (module.context.identifier pattern) to prevent ha...

Use when selecting target platform and game engine for a game project through a guided interview. Triggers: 'select plat...

Guides users through Jobs-to-be-Done discovery to define feature requirements before implementation. Use when user wants...

Use when defining application-level screen navigation hierarchy and transitions through a guided interview. Triggers: 's...

Shape the value proposition narrative tying customer needs, solution benefits, and proof points together.

Build and debug the core of a Defold game in Lua: game.project settings, collections, game objects and components, scrip...

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages a...

Work on bifunctional degraders and molecular glues, where potency comes from a ternary complex rather than occupancy. Us...

Deinstalliert einen Community-Skill, der über den Kanzlei-Builder-Hub installiert wurde. Bestätigt vor dem Löschen von D...

This skill should be used when the user asks to "run npm test after 30 minutes", "git commit after 1 hour", "wait 2h the...

Hand ordinary implementation work to the Gemini CLI headless, then review what it actually wrote against the code graph....

Hand bulky, already-decided implementation work from the agent you are working in (Claude Code or Codex CLI) to another...

Load before dispatching the bulk-reader subagent: how to write the prompt and verify its answer.

Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or v...

Delegate bounded, implementation-heavy, repetitive, read-heavy, or independently verifiable coding work from Codex to De...

Use when handing work to another agent or model (an explorer, implementer, reviewer or critic) on any vendor, to choose...