# Tools

> Every listed resource, editors’ picks first. The filters below can be combined.

- Search: append `?q=<keywords>` to the URL. Separate several keywords with spaces; all of them must match. Matches name, repository, tags, professions, description and README.
- Filter by type: append `?type=<cli|skill|plugin|mcp>` to the URL.
- Filter by profession: append `?profession=<profession id>` to the URL. Separate several ids with commas; a resource matches when it suits any of them. Ids are listed at https://hebbmind.com/api/v1/professions
- Filter by tag: append `?tag=<tag>` to the URL. Separate several tags with commas; a resource must carry all of them. Tags are listed at https://hebbmind.com/api/v1/tags

Type Skill, Resources for QA or ML / AI or Research / Academia: 124 items.

> - QA: Functional testing, test automation and quality assurance.
> - ML / AI: Model training, evaluation and LLM application development.
> - Research / Academia: Literature search and reviews, experimental data analysis, paper writing and submission.

- [Skill Creator](https://hebbmind.com/ru/skill/skill-creator.md): [Skill] Guides the agent through writing or improving a skill: clarify intent, draft SKILL.md, run scored evals with and without the skill, then tune the description so it triggers accurately. Official Anthropic skill.
- [PDF](https://hebbmind.com/ru/skill/pdf.md): [Skill] Extracts text and tables from PDFs; merges, splits and rotates pages, adds watermarks, fills forms and OCRs scanned documents. The official Anthropic skill behind Claude's document features; source-available, not open source.
- [Browser Use](https://hebbmind.com/ru/skill/browser-use.md): [Skill] Controls your local Chrome over CDP to navigate, click, type, take screenshots and scrape data, reusing logged-in sessions. Official browser-use skill; install the browser-use CLI with uv first.
- [Scientific Agent Skills](https://hebbmind.com/ru/skill/scientific-agent-skills.md): [Skill] 166 research skills maintained by K-Dense (formerly Claude Scientific Skills), spanning bioinformatics, cheminformatics, clinical research, materials and physics, including unified access to 78 public databases such as PubChem and UniProt. Works with Claude Code, Codex and Cursor.
- [Trail of Bits Skills](https://hebbmind.com/ru/skill/trailofbits-skills.md): [Skill] Skills from security firm Trail of Bits: 40+ plugins for code auditing, CodeQL and Semgrep static analysis, differential review, smart-contract and cryptography audits, fuzzing and more. Also installable as a Claude Code or Codex plugin marketplace.
- [Test-Driven Development](https://hebbmind.com/ru/skill/test-driven-development.md): [Skill] Forces red-green-refactor: write a test and watch it fail, then write the minimum code to pass. Any code written without a verified failing test gets deleted and redone. From the Superpowers workflow.
- [Teach](https://hebbmind.com/ru/skill/teach.md): [Skill] Turns the current folder into a teaching workspace you can resume across conversations: asks your learning goal, gathers reliable sources, builds short HTML lessons and cheat sheets, and tracks progress. Good for self-study and lesson prep; invoke manually (/teach), no API key.
- [Diagnosing Bugs](https://hebbmind.com/ru/skill/diagnosing-bugs.md): [Skill] A disciplined process for hard bugs and performance regressions: build a reliable reproduction loop, reproduce and minimize, form hypotheses, instrument to verify, then fix and add a regression test, redacting secrets in output. By Matt Pocock.
- [Claude API](https://hebbmind.com/ru/skill/claude-api.md): [Skill] Reference for the Claude API and Anthropic SDK: model selection and pricing, streaming, tool use, prompt caching, Managed Agents and more, plus workflows for model migration and prompt audits. Official Anthropic skill.
- [Discernment Nudge](https://hebbmind.com/ru/skill/discernment-nudge.md): [Skill] After giving advice, a draft or a data analysis, adds 2-3 targeted follow-up questions that prompt the user to check key facts, test the reasoning and fill in missing context. Fires at most once per conversation. Official Anthropic skill.
- [webapp-testing](https://hebbmind.com/ru/skill/webapp-testing.md): [Skill] Drives local web apps with Python Playwright scripts to verify features, debug the UI, take screenshots and read browser logs. Includes helper scripts to start and stop dev servers. Official Anthropic skill.
- [MCP Builder](https://hebbmind.com/ru/skill/mcp-builder.md): [Skill] Guides agents in building quality MCP servers: research the protocol and target API, design tools, implement with Python (FastMCP) or the TypeScript SDK, and write evaluation questions to test the result. Official Anthropic skill.
- [gstack](https://hebbmind.com/ru/skill/gstack.md): [Skill] Skill pack from YC president Garry Tan: slash commands such as /office-hours, /plan-ceo-review, /review, /qa and /ship play CEO, engineering manager, designer, QA and release engineer. Needs Git and Bun; clone the repo and run ./setup as the README describes.
- [Agent Skills (Addy Osmani)](https://hebbmind.com/ru/skill/addyosmani-agent-skills.md): [Skill] Engineering skill collection spanning define, plan, build, verify, review and ship, with /spec, /plan, /build, /test, /review and /ship commands, including TDD, code review and web performance audits. By Addy Osmani.
- [Literature Review (K-Dense)](https://hebbmind.com/ru/skill/literature-review.md): [Skill] Systematic literature reviews following PRISMA and similar standards: searches PubMed, arXiv, bioRxiv and other databases, verifies each citation's DOI, and outputs Markdown and PDF in APA, Nature or other styles. Main web search uses parallel-cli and needs a Parallel account.
- [Scientific Writing (K-Dense)](https://hebbmind.com/ru/skill/scientific-writing.md): [Skill] Drafts, revises and reviews research manuscripts, tying every fact and number to verified evidence and covering reporting guidelines, authorship, AI disclosure and confidentiality; explicitly forbids fabricated citations or data. Includes offline check scripts; no API key needed.
- [Database Lookup](https://hebbmind.com/ru/skill/database-lookup.md): [Skill] Unified database lookup skill from K-Dense's scientific collection: reproducibly queries about 80 public database APIs such as PubChem, UniProt, ChEMBL, ClinicalTrials.gov and FRED, returning traceable results with endpoints, parameters and count checks. Some need API keys.
- [Statistical Analysis](https://hebbmind.com/ru/skill/statistical-analysis.md): [Skill] Guides agents to the right statistical method for research data: t-tests, ANOVA, chi-square, regression and Bayesian analysis, checking assumptions, computing effect sizes and power, and reporting results in APA format. Python-based (pingouin, statsmodels); by K-Dense.
- [Scanpy Single-Cell Analysis](https://hebbmind.com/ru/skill/scanpy.md): [Skill] Teaches agents standard single-cell RNA-seq analysis with Scanpy: QC, normalization, PCA/UMAP, clustering, differential expression and plots, with ready-to-run pipeline scripts and guidance on converting Seurat and other R objects to h5ad. Needs Python 3.12+; by K-Dense.
- [Academic Research Skills](https://hebbmind.com/ru/skill/academic-research-skills.md): [Skill] Skill suite for the whole academic research workflow: deep research (including PRISMA systematic reviews), paper writing, multi-perspective peer review and revision, pausing for human approval at each stage, with citation and integrity checks. CC BY-NC, non-commercial only.
- [Chrome DevTools](https://hebbmind.com/ru/skill/chrome-devtools.md): [Skill] Teaches agents to use the Chrome DevTools MCP efficiently: snapshot first to get element uids, screenshot only when needed, paginate and filter large output, inspect CSS and test browser extensions. Needs chrome-devtools-mcp configured; maintained by the Chrome DevTools team.
- [Obsidian Skills](https://hebbmind.com/ru/skill/obsidian-skills.md): [Skill] Teaches agents to read and write Obsidian vaults: Obsidian-flavored Markdown, Bases data views, JSON Canvas and the Obsidian CLI, plus Defuddle web content extraction and Knap template rendering. Maintained by Obsidian CEO kepano.
- [Open Code Review](https://hebbmind.com/ru/skill/open-code-review.md): [Skill] Drives Alibaba's open-source ocr CLI to review Git changes (working tree, a commit or a branch diff), grouping line-level comments by severity and fixing them on request. Needs an LLM endpoint (Anthropic, OpenAI and other protocols); installs the CLI if missing. By Alibaba.
- [agent-browser](https://hebbmind.com/ru/skill/agent-browser.md): [Skill] Companion skill for the agent-browser CLI: has the agent load usage matching the installed version to navigate, fill forms, take screenshots and run exploratory tests, and can also drive Electron desktop apps. Install the agent-browser CLI first; from Vercel Labs.
- [Find Skills](https://hebbmind.com/ru/skill/find-skills.md): [Skill] When a user asks whether a skill exists for some task, searches the skills.sh ecosystem with the skills CLI, then recommends and installs a fit. Maintained by Vercel Labs and shipped in the skills CLI repo.
- [book-to-skill](https://hebbmind.com/ru/skill/book-to-skill.md): [Skill] Distills technical books, doc folders or paper collections (PDF, EPUB, DOCX, Markdown and more) into an agent skill with a core framework, on-demand chapter files, glossary and cheat sheet for lookup while working. Extraction needs local Python; poppler or docling optional for PDFs.
- [Web Design Guidelines](https://hebbmind.com/ru/skill/web-design-guidelines.md): [Skill] Reviews UI code against Vercel's Web Interface Guidelines, covering accessibility, focus, forms, animation, typography, dark mode and more, listing issues as file:line. Fetches the latest rules before each review. Maintained by Vercel.
- [baoyu-translate](https://hebbmind.com/ru/skill/baoyu-translate.md): [Skill] Translation skill by Baoyu with quick, normal and refined modes, custom glossaries, and target audience and style settings. Translates local files or URLs; suited to long-form Chinese-English translation and localization. Needs bun or npx.
- [Google Agent Skills](https://hebbmind.com/ru/skill/google-google-skills.md): [Skill] 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.
- [ARIS (Auto-claude-code-research-in-sleep)](https://hebbmind.com/ru/skill/auto-claude-code-research-in-sleep.md): [Skill] 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.
- [Agent Skills for Context Engineering](https://hebbmind.com/ru/skill/agent-skills-for-context-engineering.md): [Skill] Context and harness engineering skills: context fundamentals, degradation diagnosis and compression, multi-agent architectures, memory systems, tool design, LLM-as-judge evaluation and self-improvement loops. Focused on principles and design patterns, not tied to any agent platform.
- [Prompt Master](https://hebbmind.com/ru/skill/prompt-master.md): [Skill] Writes precise prompts for a specific AI tool: identifies the target tool, extracts your intent, asks at most three questions if details are missing, then outputs a lean, paste-ready prompt. Covers dozens of tools including ChatGPT, Claude Code, Cursor, Midjourney and Sora.
- [Playwright CLI](https://hebbmind.com/ru/skill/playwright-cli.md): [Skill] Companion skill for the official Playwright CLI: short commands to open pages, click and fill forms, take snapshots and screenshots, and write and debug Playwright tests, using less context than the MCP approach. Maintained by Microsoft; needs Node.js.
- [Localization Review](https://hebbmind.com/ru/skill/localization-review.md): [Skill] FormatJS's official localization review skill for software translators: read-only checks of UI strings and translations for ICU syntax, placeholders, terminology consistency and locale formats for dates, numbers and currency, listing issues with evidence and minimal fixes. Never edits files.
- [AI Research Skills](https://hebbmind.com/ru/skill/ai-research-skills.md): [Skill] Nearly 100 skills spanning the AI research workflow: ideation and literature review, fine-tuning and post-training, distributed training, inference serving, evaluation, interpretability and paper writing, tied together by an autoresearch orchestration skill.
- [Hugging Face CLI (hf-cli)](https://hebbmind.com/ru/skill/hf-cli.md): [Skill] Teaches agents the Hugging Face Hub CLI hf: search and download models, manage datasets, Spaces, Buckets and repos, and run Jobs and inference endpoints. The skill content is generated from your local CLI, so install hf first. Maintained by Hugging Face.
- [Hugging Face Skills](https://hebbmind.com/ru/skill/huggingface-skills.md): [Skill] Hugging Face's official skills: manage Hub models and datasets with the hf CLI, fine-tune language and vision models, run model evaluations, and build Gradio apps deployed to Spaces. Needs an HF account; cloud training on HF Jobs requires a paid plan.
- [Hugging Face LLM Trainer](https://hebbmind.com/ru/skill/huggingface-llm-trainer.md): [Skill] Lets 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.
- [Supervisor-Skills](https://hebbmind.com/ru/skill/supervisor-skills.md): [Skill] Twelve research skills from Prof. Yuyu Luo's team at HKUST (Guangzhou), built on a decade of top-venue publishing and reviewing: idea evaluation, intro and body writing, polishing, surveys, pre-submission review, figures, Draw.io rebuilds and rebuttals. Non-commercial license.
- [Scientific Figure Making](https://hebbmind.com/ru/skill/scientific-figure-making.md): [Skill] Publication-quality matplotlib plotting skill from a Yale PhD student: bar charts, trends, heatmaps and multi-panel figures with consistent fonts, colors and export settings, plus real plotting scripts from papers published in venues like Nature Machine Intelligence. Needs Python.
- [Research Paper Writing Skills](https://hebbmind.com/ru/skill/research-paper-writing-skills.md): [Skill] Turns Peng Sida's public research-writing notes into a skill: revises abstracts, introductions, methods and experiments of ML/CV/NLP papers from a reviewer's view, checks that each claim has experimental evidence, and runs a pre-submission self-check. Pure methodology, no API key.
- [Static Analysis](https://hebbmind.com/ru/skill/static-analysis.md): [Skill] Trail of Bits static analysis skills: CodeQL for interprocedural taint tracking and data-flow analysis, Semgrep for rule-based scanning, plus parsing and deduplicating SARIF results. Requires CodeQL or Semgrep installed locally.
- [Jupyter Notebooks](https://hebbmind.com/ru/skill/jupyter-notebook.md): [Skill] Creates, edits and validates reproducible Python and SQL Jupyter notebooks: organizes cells as reports or tutorials, checks conclusions against actual output and reruns top to bottom before handoff. Maintained by OpenAI in the Data Analytics plugin of openai/plugins.
- [Life Science Research](https://hebbmind.com/ru/skill/openai-skills-5.md): [Skill] OpenAI's official life-science skills: 49 skills query public databases such as UniProt, ClinVar, gnomAD and AlphaFold through Python scripts, with a router skill that breaks down questions, normalizes entities and compiles sourced evidence. Written mainly for Codex.
- [Frontend Testing Debugging](https://hebbmind.com/ru/skill/playwright-interactive.md): [Skill] Tests and debugs a locally running frontend with Codex's Browser plugin or Playwright: checks blank pages, framework and console errors, captures screenshots, re-verifies after fixes and writes a QA report. Maintained by OpenAI; formerly playwright-interactive in openai/skills.
- [Codex PPT Skill](https://hebbmind.com/ru/skill/codex-ppt-skill.md): [Skill] Turns articles, reports, papers or notes into a .pptx of full-slide images with speaker notes, in 12 styles such as lectures and thesis defenses; slide text is not editable. Needs Python 3; uses Codex's built-in image generation, or an OpenAI-compatible image API key in Claude Code.
- [Dev Browser](https://hebbmind.com/ru/skill/dev-browser.md): [Skill] Lets coding agents control real Chrome with short Puppeteer scripts, with named pages that keep state across calls, accessibility-tree snapshots and screenshots for self-testing web changes. Install the dev-browser CLI globally first; macOS and glibc Linux only.
- [Google Agents CLI Skills](https://hebbmind.com/ru/skill/google-skills.md): [Skill] Google's official skills for building ADK agents: dev workflow, scaffolding, the ADK Python API, evaluation with LLM judges and adaptive rubrics, deployment to Agent Runtime, Cloud Run or GKE, publishing and observability. Works with agents-cli; local dev needs only an AI Studio key.
- [Vitest](https://hebbmind.com/ru/skill/vitest.md): [Skill] Reference for Vitest 5: config, CLI, the test, describe and expect APIs, hooks, mocking with vi, snapshots, coverage, fixtures, concurrency, filtering and tags, reporters, benchmarks, test environments, type testing and multi-project setups. Generated by Anthony Fu from the official docs.
- [Claude Scholar](https://hebbmind.com/ru/skill/claude-scholar.md): [Skill] Semi-automated research workflow for computer science and AI researchers: ideation, Zotero literature management, experiment analysis and reports, paper writing and polishing, and rebuttals, with optional Obsidian knowledge base. 40+ skills; also installable as a Claude Code plugin.

Next page: https://hebbmind.com/ru/tools.md?page=2&type=skill&profession=qa%2Calgorithm%2Cresearch