AI & ML

yugasun Bundle

火山引擎豆包搜索 API（原联网搜索/融合信息搜索），返回网页/图片结果。联网搜索场景优先使用本 skill。触发词包括：豆包搜索、查/搜/找、真的吗/靠谱吗/确认/核实、最近/今天/最新/近期、出处/来源/链接、Agent Plan、融合信息搜索、Harness、有什么/有哪些/推荐、价格/政策/汇率/行情、对比/区别/哪个好、听说/据说/不太确定、热搜/热门/火、帮我看/了解一下、求证/辟谣、值不值得/该不该。任务依赖在线事实或时效性时优先使用。若回答可能依赖外部事实，优先调用本 skill 再作答。

weaverse-claude Skill

Set up a new Weaverse Hydrogen storefront locally from a Weaverse theme. Boot a live demo-store preview before asking for any credentials, then make it the merchant's own: install the Hydrogen app, link the store, pull the Storefront credentials, push the repo to GitHub, configure the Weaverse MCP for live page edits, and install the full shopify-hydrogen-skills pack.

alib8b8 Skill

终端工作流自动化引擎，通过自然语言生成并执行 YAML 工作流。内置节点与 LLM 提供商目录可通过 aflare list 查看。

digitalocean-labs Bundle

Create and manage isolated container sandboxes for AI agent code execution. Use when you need ephemeral environments to run untrusted code, execute agent workflows, or test in isolation. NOT for debugging existing apps (use troubleshooting skill).

douglasmonsky Skill

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"

jitx-inc Bundle

Same-model self-critique pass for JITX Python code just written in this workspace. Use when the user asks to "review my JITX code", "self-critique", "check JITX conventions", "find string-hacking", "check framework-boundary issues", "audit before merge", or any equivalent. Mandatory for complete-board tier at task acceptance (folds into Think Twice); user-invoked for single-task work. Catches the architectural failure modes that grep gates and static linters miss — parallel string-keyed models, reflection-as-iteration (regardless of whether on self), owner-shaped data misplaced in design code, build-spec-then-iterate, module-import-time parallel models, and framework-boundary-bypass (the "framework does it, therefore so can I" trap). Applies an ownership test to every banned-pattern hit or proposed exception. Produces severity-tagged findings (CRITICAL / WARNING / NOTE) that fold into the task acceptance block.

dimitri-vs Skill

Strip Claude writing tells (em-dashes, "Not X, but Y" contrastives, colon-declarations, delve/realm/seamless/robust lexical cluster, wrap-up closers, synthetic empathy, collective modality) from text via the globally-installed `humanize` CLI. Invoke when the user asks to humanize, de-AI-ify, de-Claude, clean up LLM-sounding text, or make output sound less like a bot. Also use proactively after generating prose that will be shown verbatim to a human (LinkedIn posts, emails, proposals, essays) when the content should read as authored by a real person rather than an assistant.

dimitri-vs Skill

Browser automation via Playwright CLI and MCP. Use when interacting with web pages — navigating, clicking, filling forms, taking screenshots, scraping content. Defaults to CLI (`@playwright/cli`) for token efficiency. Falls back to MCP for short exploratory sessions or sandboxed environments.

kiraneswaran Bundle

Structured development workflow with Plan/Implement/Review phases, QA validation, context management, and audit requirements. Enforces no remote writes, mandatory checkpoints, and verifiable audit reports. Use when working on complex tasks, multi-file changes, or when the user mentions planning, workflow, implementing features, or needs structured development guidance.

ducconit Skill

Agent can update and synchronize skills from this repository to various IDEs (Cursor, Trae, Windsurf) and AI Agents using the `@ducconit/agentskills` CLI via `npx`.

ducconit Bundle

Agent capable of analyzing software design problems to select and apply the most appropriate design patterns (Creational, Structural, Behavioral) for optimal solutions. Supports code refactoring and design decision reporting.

ducconit Bundle

Agent capable of analyzing source code changes and crafting professional commit messages that adhere to the Conventional Commits 1.0.0 specification.

bazelbuild Skill

Create and format agent rules with proper front matter in the workspace

bazelbuild Bundle

Clean up files and resources that aren't part of the agent conversation (e.g. Bazel output base, Git worktree, local/remote branches)

dimitri-vs Bundle

Convert PDFs, scans, and document images to clean Markdown via the Mistral OCR API, with figures described inline by a vision model. Use whenever a PDF or scanned document needs text extraction — accuracy matters, so prefer this over pdftotext/pdfplumber/tesseract or ad-hoc approaches. Fast (~seconds for 100 pages, vs ~30s/page for local marker) and cheap (~$0.005/page). Requires MISTRAL_API_KEY env var.

dimitri-vs Bundle

Build AI agents with Pydantic AI framework. Use when implementing agents with Gemini/Google, structured outputs, tools, streaming, multi-agent delegation, or FastAPI integration.

rmusser01 Skill

Manage tldw_server Kanban boards via MCP with explicit workflow-status control, safe transitions, lease/approval gates, and recovery primitives for orchestrators.

nvidia-nemo-automodel Skill

Testing reference for NeMo AutoModel — unit and functional test layout, tier semantics (L0/L1/L2), running tests locally, adding or disabling tests, and pytest conventions.

nvidia-nemo-automodel Bundle

Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

nvidia-nemo-automodel Bundle

Verify numerical parity between NeMo AutoModel implementations and reference HuggingFace models, including state dict and forward-pass checks.

nvidia-nemo-automodel Skill

Dev environment setup for NeMo AutoModel — container-based development, uv package management, installation options, environment variables, and common build pitfalls.

farmanlab Bundle

Checks for broken file references in skills, agents, rules, and commands. Use when validating internal links after file reorganization or migration.

farmanlab Bundle

Validates prompt files against best practices. Use after creating or editing rules, skills, agents, commands in .agents/ for quality review.

schovi Bundle

Delegate a self-contained task to a Codex (GPT-5.6) subagent through the bundled codex-delegate.sh wrapper, which hides the event stream and returns only the final message plus a resumable session id. Use when the user says "/codex:delegate", "ask codex", "delegate this to codex", or when offloading token-heavy but well-specified work (bulk implementation, mechanical migrations, standalone investigation or review, throwaway research) would preserve Claude context for judgment work. Skip for anything finishable in a handful of tool calls, or tasks whose context can't be written into one self-contained prompt.

schovi Skill

Refine tasks in the repo's workflow/ status folders into implementable specs, and capture concrete work items found during exploration onto that board. Use when the user explicitly invokes "/workflow:groom", "/groom", "groom 052", or "use $groom". In an initialized repo (workflow/AGENTS.md exists), also use without being asked when an exploration, investigation, audit, or review — by you or by an agent reporting back — has produced concrete work items the user wants tracked, and for an unmistakable request to put an ask onto that board. Do not use for generic planning or task-refinement requests, and do not use in a repo that has no workflow/AGENTS.md. If explicitly invoked in an uninitialized repo, stop and suggest /workflow:framework-init; never invoke it automatically.

schovi Skill

Append a decision record with a stable D<N> handle to the repo's decision log. Use when the user says "/workflow:decision", "log this decision", "record why we chose X", or when /workflow:work surfaces an A/B/X choice a future agent might plausibly flip. Skip for choices that die with the task.

nvidia-nemo-automodel Skill

Code style and quality rules for NeMo AutoModel — ruff configuration, naming conventions, type hints, docstrings, copyright headers, and the code review checklist.

costiash Skill

Provides structured error handling protocol for all agent operations. Ensures users receive clear error reports, troubleshooting guidance, and actionable next steps. Use when any tool operation fails, encounters an error, or produces unexpected results.

jaivishchauhan Skill

Manage portfolio content with MDX, Contentlayer, or local JSON for projects, blog posts, and dynamic content.

jaivishchauhan Skill

Create stunning, physics-based animations and micro-interactions for portfolio websites using Framer Motion.

jaivishchauhan Skill

Production-ready portfolio components including Hero, About, Projects, Experience, Contact sections with modern design patterns.

dsifry Skill

Analyze the current session and write a self-contained handoff document so a fresh agent can resume the work with full context — outputs a single "Read XXX.md and do YYY." sentence

dsifry Skill

Create comprehensive GitHub issues with TDD plans, acceptance criteria, and agent instructions for autonomous PR lifecycle management

tnez Bundle

Evaluate agent skill quality using rubric-based assessment. Use when assessing skill effectiveness, identifying improvement opportunities, or ensuring quality standards.

tnez Skill

Install agent skills from GitHub repositories into local environment. Pure agentic installation - no scripts required. Use when adding new skills or updating existing ones.

poshan0126 Skill

Explain code. Default is a one-sentence summary plus a mental model. Add `verbose` to also get an ASCII diagram, key details, and a modification guide.