도구

Compliance skill from Anthropic's official operations plugin: maps controls, owners and evidence for SOC 2, ISO 27001, GDPR, HIPAA and PCI DSS, schedules audits, runs gap analyses, and outputs audit-readiness checklists and evidence collection plans. Have legal or compliance experts review.

Performance review season helper: generates self-review and manager review templates and calibration materials, summarizes rating distributions and promotion cases, and rewrites vague feedback into specific behavioral examples. Works in plain chat. Official from Anthropic.

Tracks the hiring funnel through sourcing, screening, interviews, debrief and offer, watching stage time and conversion, source effectiveness, offer acceptance and time to hire. With an ATS connected it pulls candidate data and updates status. A brief skill from Anthropic's human-resources plugin.

Generates people analytics reports from employee data: headcount snapshots, voluntary and involuntary attrition, diversity metrics, spans of control and flight risk, with findings and recommendations for leadership. Needs an uploaded employee CSV or a connected HRIS. Official from Anthropic.

Answers employee policy questions in plain language, such as PTO, benefits, expenses, travel and remote work, with sources cited. Paste the handbook into the chat, or connect Notion, Confluence or another knowledge base to search automatically, cutting repeat HR questions. Official from Anthropic.

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.

Fast vulnerability scanner driven by YAML templates: uses a community template library to detect known vulnerabilities over HTTP, DNS, TCP, SSL and more, supports custom templates and plugs into CI/CD. Use only on targets you're authorized to test.

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.

Built-in gws CLI skill: lets agents create Google Forms, add or edit questions in bulk, publish and read responses, handy for sign-ups, surveys and class feedback. Needs gws with a Google account authorized via your own Google Cloud project; not an officially supported Google product.

HR coordinator persona skill for the gws CLI: schedules onboarding sessions in Calendar, uploads onboarding docs to shared Drive, announces new hires in Chat, and turns email requests into tasks and bulk notices. Needs gws with OAuth via a Google Cloud project; not officially supported by Google.

Detects hardcoded passwords, API keys and tokens in Git repos, files and stdin, and can run as a pre-commit hook or GitHub Action to block leaks. Now feature-frozen with security fixes only, as the author has moved on to Betterleaks.

Chief people officer perspective for HR and founders: hiring plans and headcount costs, salary bands and equity design, org structure, performance calibration and retention. Includes two local Python scripts; pay examples use USD and US city tiers. Have comp and equity plans reviewed.

Helps HR and hiring managers design structured interviews: plans rounds by role and level, builds question banks, competency matrices and scoring rubrics, and suggests ways to reduce interviewer bias and recalibrate. Examples focus on tech roles; optional local Python scripts.

Finds leaked credentials in Git, GitHub, S3, filesystems and more, recognizing 800+ secret types and checking with each service whether a key is still live to cut false positives.

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.

Distills a colleague, friend or public figure's chats, documents and public material into a persona profile packaged as a callable skill, for handoffs and preserving know-how. Collects material from Lark, DingTalk, Slack and more. Mind privacy and consent when using others' data.

Open-source reverse engineering framework and CLI: disassemble, debug, emulate and patch binaries across many architectures and file formats, scriptable through r2pipe or built-in JavaScript.

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.

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.

Encrypts secret values in YAML, JSON, ENV and INI config files using AWS, GCP or Azure KMS, age or PGP, so secrets can be safely committed to Git alongside code. A CNCF sandbox 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.

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.