ツール
掲載中のすべての Skill、MCP サーバー、CLI、プラグインです。種類・職業・タグで絞り込むか、キーワードで検索できます。
職業:Full-stack / Indie +3
複数選択できます。いずれかの職業に合うリソースが表示されます。
- Full-stack / Indie524
- QA101
- ML / AI162
- HR88
- Frontend447
- Backend408
- Mobile & desktop96
- Game development29
- DevOps / SRE209
- Data engineering81
- Data analysis152
- GIS / Surveying12
- Security71
- Product / Projects246
- Design239
- Architecture / Civil19
- Hardware engineering17
- Operations233
- Marketing & sales306
- Admin / Office240
- Writing / Content229
- Video / Media187
- Customer support66
- Legal94
- Finance / Accounting142
- Investing / Analysis104
- Teachers / Students212
- Research / Academia255
- Healthcare19
- Translation / L10n84
- Founders282
749 件

Hugging Face LLM Trainer
SkillLets agents fine-tune language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, supporting SFT, DPO, GRPO and reward models, and convert results to GGUF for local use. Requires an HF Pro or higher paid plan. Maintained by Hugging Face.
huggingface/skills11.2k
Hugging Face Skills
PluginLets agents work with the Hugging Face Hub through the hf CLI: search and download models and datasets, manage repos and Spaces, and run training and evaluation jobs on cloud GPUs, with more workflow skills installable as needed. Maintained by Hugging Face.
huggingface/skills11.2k
MCP Inspector
CLIThe official MCP debugging tool: connect to any MCP server through a web UI, CLI or terminal UI to list and call its tools, resources and prompts. CLI mode outputs JSON, suited to scripts and CI smoke tests.
modelcontextprotocol/inspector11.2k
GSD Core
PluginSpec-driven development and context engineering framework (formerly Get Shit Done): a five-step loop of discuss, plan, execute, verify and ship, handing heavy work to subagents with fresh context to avoid degradation in long sessions. Supports Claude Code, Codex and more.
open-gsd/gsd-core11.1k
company-values
SkillFollowing Sahil Lavingia, author of The Minimalist Entrepreneur, helps founders define 3 to 5 concrete company values with real trade-offs before hiring, with example stories and counterexamples, and explains how to use them in hiring and daily work. Prompt-only; no account needed.
slavingia/skills11k
Windows-MCP
MCPLets agents operate the Windows desktop directly: launch apps, switch windows, simulate keyboard and mouse, read UI elements and run PowerShell, without needing a vision model. Windows only.
CursorTouch/Windows-MCP10.8k
visual-explainer
PluginTurns terminal output like architecture explanations, diff reviews and plan comparisons into styled HTML pages or slides with zoomable interactive Mermaid diagrams, replacing hard-to-read ASCII diagrams and tables. No build step; open directly in a browser.
nicobailon/visual-explainer10.7k
visual-explainer
SkillTurns architecture explanations, diff reviews, plan reviews and data comparisons into self-contained HTML pages or slides with Mermaid diagrams and light and dark themes, replacing ASCII diagrams in the terminal.
nicobailon/visual-explainer10.7k
drawio-skill
SkillGenerates editable draw.io architecture diagrams, ER diagrams, UML and BPMN flows from natural language or from Terraform, SQL DDL, OpenAPI specs and code repos, with incremental sync and multi-format export. Native export needs the draw.io desktop app.
Agents365-ai/drawio-skill10.5k
Desktop Commander MCP
MCPLets agents run terminal commands on your machine, manage long-running processes, and read, write, search and diff-edit files. Extends the official Filesystem server; collects pseudonymized telemetry by default (no file contents or command arguments), which you can turn off in config.
wonderwhy-er/DesktopCommanderMCP10.2k
Mobile MCP
MCPLets agents control iOS and Android simulators and real devices: reads the accessibility tree first and falls back to screenshot coordinates, and can swipe, install and uninstall apps, record the screen and read device logs. Requires Xcode or Android platform tools.
mobile-next/mobile-mcp10.2k
Feynman
CLIOpen-source research agent: one command runs literature reviews, deep research, paper reviews, paper-code consistency checks and replication plans, searching arXiv, PubMed and more with sources recorded. Good for grad students writing reviews. Run feynman setup to sign in to a model provider.
Companion-Inc/feynman10k
policy-drafting
SkillDrafts employee policies such as remote work, parental leave and PTO, generates state or country supplements where rules differ, and flags laws in flux. Mostly US states; needs web access for regulations and is best installed with the employment-legal plugin. Lawyer review required. By Anthropic.
anthropics/claude-for-legal9.9k
termination-review
SkillPre-termination check for high-risk factors (recent complaints, protected leave, discrimination or retaliation, thin documentation), reviews severance and separation agreements, and looks up state final-pay deadlines. US-focused; needs web or a legal database. Lawyer review required. By Anthropic.
anthropics/claude-for-legal9.9k
wage-hour-qa
SkillAnswers wage and hour questions for a specific state or country, such as worker classification, overtime, meal and rest breaks, leave and final pay, citing the law for each point and flagging when judgment is needed. US-focused; needs web or a legal database. Lawyer review required. By Anthropic.
anthropics/claude-for-legal9.9k
handbook-updates
SkillWhen revising an employee handbook, compares proposed changes clause by clause with the current version, finds knock-on effects (such as PTO changes affecting final pay) and state supplement changes, and flags risks of cutting existing benefits. US-focused; needs legal review. By Anthropic.
anthropics/claude-for-legal9.9k
AWS Documentation MCP Server
MCPOfficial AWS MCP that searches and reads AWS documentation, converts it to Markdown for agents to cite, and suggests related pages. No AWS credentials needed; requires uv.
awslabs/mcp9.9k
Claude for Legal
PluginAnthropic's official legal plugin marketplace: 13 plugins covering commercial contracts, privacy, product counsel, M&A, employment, regulatory, AI governance, litigation and IP, plus plugins for law school clinics and law students. All output is a draft for attorney review.
anthropics/claude-for-legal9.8k
Employment Legal
PluginAnthropic's official employment law plugin: reviews hiring and termination risk by jurisdiction, classifies workers, tracks leave deadlines, manages internal investigations, and drafts policies with state supplements. Focused on US state law; output needs attorney review.
anthropics/claude-for-legal9.8k
BrowserSkill
CLITencent's open-source browser bridge: through the bsk CLI and a Chrome/Edge extension, agents use your logged-in accounts in a separate visible window to browse, fill forms and take full-page screenshots, and correlate network requests with console output to debug sites.
Tencent/BrowserSkill9.8k
Defuddle
CLIExtracts the main content of a web page, stripping comments, sidebars, headers and footers, and outputs clean HTML or Markdown with metadata like title, author and publish date, saving tokens when agents read the web. Built for Obsidian Web Clipper by kepano; still in development.
kepano/defuddle9.8k
garak
CLINVIDIA's open-source LLM vulnerability scanner that probes for prompt injection, jailbreaks, data leakage, hallucination and harmful content, supporting OpenAI, Hugging Face, Bedrock and most REST-accessible models. Scanning cloud models needs their API keys.
NVIDIA/garak9.8k
Plannotator
PluginAnnotate and review agent-generated plans, docs and code diffs in the browser, then send feedback back to the agent in one click. Hooks into plan mode and supports Claude Code, Codex and other agents. Run the official install script to set up the CLI first.
backnotprop/plannotator9.8k
WeasyPrint
CLIRendering engine that lays out HTML and CSS and exports PDF, supporting paged media and other print style standards, ideal for generating reports, invoices and receipts in bulk. Written in Python; depends on the system Pango library.
Kozea/WeasyPrint9.7k