DeepSeek

写或修改 CHANGELOG.md（待发布条目、版本亮点段、GitHub Release 说明）时使用。含按改动性质分组落位、中英双语体例、发版前的两道门禁（三处版本号同步 + 亮点段抽取会 fail-fast）与写后自检命令。

xiajiajun516/dsh-config-manager

A skill your agent uses when building any web page, HTML artifact, landing page, dashboard, slide deck, report, email, or UI component the user will look at.

drewnekota/cetus

The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models.

oxbshw/watch-skill

Helps show a model provider's usage, balance or quota in PiDeck: checks built-in support, points to the dialog templates, or writes a custom probe entry.

ayuayue/PiDeck

Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends.

Tabbit-Browser/dsh-tabbit

Check resolved dependencies and relevant code paths for security vulnerabilities.

ccch1mneyyy/dsh-TUI

当用户提问需要联网检索（最新新闻、技术资料、人物事件等）或明确说"搜一下/查一下/帮我找…"时触发。本技能会自动改写 query 并通过 DuckDuckGo 检索，再用 DeepSeek 综合回答，引用来源序号。

benchen4395/alpha_agentic_search

Add new LLM model pricing entries to Litefuse's default-model-prices.json.

litefuse/litefuse

Build evidence-backed GEO brand knowledge bases from official sites, product pages, help centers, white papers, sales materials, media releases, certifications, and trusted third-party sources.

yaojingang/yao-geo-skills

Idiomatic Go concurrency - sync primitives, channel semantics, the select statement, and the standard channel patterns (cancellation/done-channel, fan-out/fan-in, pipeline, or-done, context…

inference-gateway/inference-gateway

Guidance for using the MMSP Python SDK (mmsp). An agent skill from Prism-Shadow/model-message-stream-protocol.

Prism-Shadow/model-message-stream-protocol

Interact with a Meshtastic LoRa mesh network through MESH-API — list nodes, read messages, send texts, and check connection status.

mr-tbot/mesh-api

Orchestrates the full WeChat official account workflow from topic to draft, chaining sub-skills for writing, review, layout, images and publishing.

aiworkskills/wechat-article-skills

A skill your agent uses for web searches and current information lookups, finding sources, fact-checking, researching questions, comparing sources, or summarising web pages.

zhongkaifu/TensorSharp

Release browser extensions or similar small packaged apps by upgrading a semantic version, packaging build artifacts, creating a git commit and tag, pushing to the remote, and publishing a GitHub…

Yorick-Ryu/deep-share

Plan-first, one-time human plan approval; batched execution in either Gated (human confirms between batches) or Auto-loop (continuous run after plan approval); strict task-state updates; automatic…

AlephantAI/AIephant-AI-Agent-Gateway

How to operate a pi-dispatch deployment through its tools, and how to use the operator-confirm gates on the write tools (changing limits, adding/editing/deleting triggers).

edgehero/pi-dispatch

cc-router 发版准备一条龙：升版本号 → 根据上一个 tag 以来的提交写 release-notes/<版本/ 的中英日三份更新内容 → 校验 → 给用户审 → 本地提交「Bump version to X.Y.Z」，停在打 tag 之前。当用户说「准备发版」「发个版」「发 6.1.0」「写发版说明 / 更新内容 / release notes」「bump 版本」时必须走本…

finch-xu/cc-router

Runs a staged workflow for math modeling contests such as CUMCM and MCM/ICM, with checkpoints, verified solver code and a LaTeX paper, on DeepSeek Harness.

RealSeaberry/AutoMCM-Pro

Run a one-shot or flat parallel batch of provider LLM subagents (headless cc-fleet subagent) that return a result.

ethanhq/cc-fleet

Audit Grix diffs and pull requests for correctness, regressions, security, lifecycle safety, and cross-component contract consistency.

askie/grix

Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.

BlockRunAI/blockrun-mcp

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).

Orchestra-Research/AI-Research-SKILLs

Walks through aligning language models with SimPO, a reference-free preference optimization method, using accelerate configs for Mistral 7B, Llama 3 8B and math-focused models.

Orchestra-Research/AI-Research-SKILLs

Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.

Orchestra-Research/AI-Research-SKILLs

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.

mydisha/keirouter

A skill your agent uses to validate a dsh-web client or skin change in the real DeepSeek Harness Web GUI, including build readiness, responsive rendering, interaction checks, and evidence capture.

zhu1090093659/dsh-web

Premium judgment; cheap repository specialists; deterministic helpers for objective integrity.

frozenpepper/deepseek-and-destroy

Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action…

Bald0Wang/DeepSeek-Oracle

The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does…

oxbshw/watch-skill

Work on this repository's .NET/C SDK code, including API models, HTTP behavior, Microsoft.Extensions.AI adapters, ASP.NET Core DI, builds, and tests.

niltor/DeepSeekSDK-NET

Search, install and manage skills from ClawdHub. An agent skill from oujingzhou/openmozi.

oujingzhou/openmozi

Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.

amd/skills

[MASTER ENTRY POINT] 需要多阶段产物的中文长文、公众号文章与观点文工作流总导演. An agent skill from dongbeixiaohuo/writing-agent.

dongbeixiaohuo/writing-agent

Operate the cdesktop coding-session environment — agent teams, session management, file conventions.

cdesktop-ai/cdesktop

Review a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces…

inference-gateway/inference-gateway

穗织世界观、神话与诅咒、身边人物、API速查表——常陆茉子的背景知识库，自动加载. An agent skill from liebaojun/MakoCode.

liebaojun/MakoCode

Operate web pages in Emperor's built-in browser with the browser tools, and macOS app windows with the desktop tools — open or bind a target, read it, fill, click or type, and verify the result.

TheSyart/emperor-agent

Disciplined diagnosis for hard bugs and performance regressions.

zmy15/DeepSeek-for-VisualStudio

深色/浅色主题下 DeepSeek Harness for VS Code 原生工作台 webview 前端的跨平台（Windows / macOS）样式与功能一致性规范。当修改 media/chat.css、media/chat-responsive.css、src/webview/chat/.ts、src/webview/composer-configuration/.ts 或…

skymecode/deepseek-harness-for-vscode

Internal contract for calling the dsh bridge from commands and the dsh-delegate agent — subcommands, flags, environment, and failure handling.

cpj-dev/dsh-plugin-cc

Guidance for using the MMSP TypeScript SDK (@prismshadow/mmsp).

Prism-Shadow/model-message-stream-protocol

openInvest multi-asset AI investment committee — daily use. An agent skill from longsizhuo/openInvest.

longsizhuo/openInvest

Draw Sebastian-Raschka-gallery-style TikZ architecture diagrams for any HuggingFace decoder-only LLM, with per-block parameter formulas and concrete numbers.

yzlnew/infra-skills

Checks audit reports (financial statements and notes) for cross-reference, summation and text errors, with arithmetic done by script and results exported to Excel and Markdown.

nigo81/nigo-skills

Start the Claude Paper web viewer to browse and study papers

alaliqing/claude-paper

Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.

mydisha/keirouter

Audit the repository or a broad subsystem for security, correctness, and maintainability risks.

ccch1mneyyy/dsh-TUI