ツール

Anthropic's official knowledge work plugin: one question searches your connected chat, email, cloud docs, wiki and project tools at once and returns a sourced answer; can also produce daily or weekly digests. Preset MCP connectors for Slack, Notion, Atlassian, Asana and more, each needing auth.

Collects reviews and complaints from Google, Yelp, Facebook and more, groups them by theme with quotes, and drafts replies in the owner's voice that post only after approval; also finds lapsed customers and drafts win-back messages. Official Anthropic small-business plugin.

Packages customer issues that need engineering, product or leadership into an escalation brief with scope, repro steps, business impact, asks and deadline, and decides who to escalate to. Support and CRM connectors add context automatically. Part of Anthropic's official customer-support plugin.

Before replying to a customer, verifies answers across the knowledge base, past tickets, CRM and chat history, grades confidence and cites sources; can also find whether an issue was reported before or what a customer was told. From Anthropic's official customer-support plugin.

Pulls verbatim customer quotes on a topic from call transcripts, meeting notes and emails, tagging each with speaker, account and date, and summarizes recurring themes into voice-of-customer findings for product and marketing. Connect Gong, email or drive, or upload transcripts. By Anthropic.

Turns resolved tickets, common questions or workarounds into publish-ready knowledge base articles, structured as how-to guides, troubleshooting, FAQs or known issues, and optimized for search. From Anthropic's official customer-support plugin.

Customer support plugin: triages and prioritizes tickets with routing suggestions, drafts customer replies, packages escalations, researches customer issues across sources and turns resolved issues into knowledge base articles. Official from Anthropic.

Official Slack (Salesforce) plugin in Anthropic's knowledge work marketplace: connects Slack's hosted MCP to search and send messages, read channels and threads, and manage canvases, with commands for channel digests, standup updates and announcements. Needs workspace admin approval.

Vercel's React Native and Expo best practices ranked by impact, covering list scrolling performance, Reanimated animations, navigation, UI patterns, state management and monorepo setup. Maintained by Vercel.

Runs the cognee memory engine as an MCP server whose remember, recall and forget tools write documents and conversations into a knowledge graph and vector store for cross-session retrieval. Start it with Docker or uv first; needs an LLM API key by default, or connect to Cognee Cloud.

Writes conversations and business data into Graphiti's temporal knowledge graph so agents can retrieve long-term memory by entity, fact and time. Open source from Zep; start FalkorDB or Neo4j and the server with Docker first, and configure an LLM API key.

Support persona skill for the gws CLI: triages support-labeled Gmail, turns emails into tasks, logs tickets in Google Sheets, escalates urgent issues to Chat and books follow-ups. Needs gws authorized via your own Google Cloud project plus its companion skills; not officially supported by Google.

Gives coding agents IDE-like symbol-level code search, editing and refactoring via language servers (LSP) across 40+ languages, with cross-session memory. An optional paid JetBrains plugin backend adds breakpoint debugging. Install with uv first.

For SaaS customer success teams: three standard-library Python scripts turn customer data into health scores, churn-risk tiers and ranked expansion opportunities, with reproducible results. Needs Python and customer data in the sample JSON format. Part of the claude-skills collection.

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

Google's official skill library, focused on Google Cloud: 100+ skills for gcloud, Cloud Run, GKE, BigQuery, IAM, monitoring and logging, and the Well-Architected Framework, plus Ads and Analytics.

Google's official skill library and plugin marketplace: nearly 150 skills focused on Google Cloud (GKE, BigQuery, Cloud Run, IAM and more), plus 17 product plugins pairing skills with MCP for Cloud SQL, Spanner, AlloyDB, BigQuery, GCS and others.

Manages BigQuery datasets, tables and jobs with the bq and gcloud CLIs, runs SQL queries and loads data, with references for client libraries, MCP and Terraform. Google's official skill; requires a Google Cloud project.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

AI2's tool for converting PDFs and scans to Markdown with a vision LLM, handling equations, tables, handwriting and multi-column layouts, suited to bulk digitizing papers and archives. Local runs need an NVIDIA GPU with 12GB+ VRAM; otherwise use a paid OpenAI-compatible remote endpoint.

Style and convention linter for Swift, with most rules built on SwiftSyntax. Configure it with .swiftlint.yml, auto-correct with --fix, and run it in an Xcode build phase or as a SwiftPM plugin.

Browser control from the browser-use team: an editable CDP connection lets agents drive the Chrome you are already using, writing missing helper functions as they go and keeping them for reuse. Also offers an MCP server. Allow remote debugging in Chrome on first use.

Lets Claude Code push ML research forward unattended: literature review, topic selection, experiment deployment, cross-model review loops and paper writing through rebuttal, in 80+ skills. Codex acts as the independent reviewer by default; other model pairings work too.

Context and harness engineering skills covering context compression and optimization, multi-agent architectures, memory systems, tool design and LLM-as-judge evaluation, activated automatically by task. Aimed at building production-grade agent systems.