Claude Skills for Teams

Claude skills for teams are SKILL.md files you commit to a shared repository so that Claude behaves the same way for every developer on the project. One person writes down how your team formats pull requests, writes documentation or plans work, and Claude applies it identically for everyone — no verbal agreements, no reminders during review. The difference shows up at onboarding and at review. A new developer clones the repository and immediately inherits the team's commit style, issue structure and code conventions instead of spending a week discovering unwritten rules. Review loses an entire class of comments — "we don't write it that way here" — because the code arrives already matching the standard. The skill itself stays an ordinary text file in the repository: it is changed through a pull request, discussed like code and versioned with the project.

Because skills live in git next to the code, they are versioned like any other file: a rule can be argued in a pull request, reverted, or branched. That is the practical difference from settings kept in each person's local interface, which never transfer between people and vanish when someone changes machines.

The collection below covers planning, task orchestration between agents, and documentation — the areas where team members drift apart from each other most often.

Skills in this collection

746 skills in this collection; the 24 highest-rated are listed below.

• Очистка и полировка пользовательских текстов — clean-user-facing-text is a Claude Code skill that audits and rewrites authorized natural-language text, removing suspicious invisible Unicode characters while preserving every fact, number, name, citation, and requirement. It is designed for use in Cursor when polishing articles, manuscripts, reports, documentation, emails, product copy, UI text, Markdown, or HTML prose. The workflow has two stages: a deterministic Unicode pass using bundled Python scripts (`inspect_text.py` and `clean_text.py`), and a prose rewrite that varies clause order, sentence rhythm, and connectors to replace formulaic phrasing with direct, natural wording. Code blocks, commands, paths, identifiers, formulas, verbatim quotations, and required disclosures are never modified. The skill does not support code-only tasks and explicitly does not claim detector evasion or proof of human authorship.
• Hookify — создание правил автоматизации — writing-rules is a Claude Code skill that guides creating and configuring Hookify rules — markdown files with YAML frontmatter that define patterns to watch for and messages to display when those patterns match. Rules are stored as `.claude/hookify.{rule-name}.local.md` files and support four event types: `bash` for shell commands, `file` for edit and write operations, `stop` for agent completion, and `prompt` for user input. The skill covers all frontmatter fields (`name`, `enabled`, `event`, `action`, `pattern`), both simple and multi-condition formats, matching operators (`regex_match`, `contains`, `equals`, `starts_with`, and others), and practical regex examples for dangerous commands, debug code, and sensitive file paths. It's aimed at developers who want to automate warnings, checklists, and enforcement steps inside their Claude Code workflow.
• Локальные конфиг-файлы плагинов с YAML-frontmatter — plugin-settings is a Claude Code skill that documents the `.claude/plugin-name.local.md` pattern for storing per-project plugin configuration and state using YAML frontmatter combined with a markdown body. Files live in the project root, stay out of version control, and are user-managed — the skill covers file structure, parsing techniques, and three common usage patterns. Frontmatter supports typed fields such as strings, booleans, numbers, and lists, while the markdown section holds prompts, task descriptions, or additional instructions for agents and commands. Included bash snippets use `sed` and `awk` to extract frontmatter fields, with ready-made templates for hooks, commands, and agents — including toggling hook activation without restarting and coordinating multi-agent swarm state. Aimed at Claude Code plugin authors who need flexible, project-scoped configuration driving adaptive behavior across hooks, commands, and agents.
• Генератор интерактивных HTML-площадок — playground is a Claude Code skill that generates self-contained interactive HTML playgrounds — a single file with a controls panel on one side, a live preview on the other, and a prompt output at the bottom with a copy button. It selects the appropriate template from six built-in options — design-playground, data-explorer, concept-map, document-critique, diff-review, and code-map — and builds the playground accordingly. All CSS and JS are inlined with no external dependencies; a single state object drives both the preview and the prompt, updating instantly on every control change. The prompt output is written as a natural-language instruction that mentions only non-default choices and includes enough context to act on without seeing the playground. Ideal for UI design exploration, data and query building, code review, and learning — any scenario where the input space is visual or structural and hard to express as plain text.
• Интерактивная страница статуса проекта — project-artifact is a Claude Code skill that generates and publishes a tabbed HTML status page for projects too large to fit in a single update — migrations, launches, research efforts, or any initiative with parallel workstreams. The output is a self-contained HTML file (all styles and the tab-switcher script inlined, no external hosts) published via the built-in Artifact tool to a private `https://claude.ai/code/artifact/<uuid>` URL that owners can share with teammates. Tab selection is opinionated: Overview and Workstreams are always present; Attention, Background, Plan, Risks & Open Questions, and Decisions/FAQ each appear only when there is substantive content to fill them. Per-project config lives in `${CLAUDE_PLUGIN_DATA}/artifacts/<slug>/`, enabling refreshes that redeploy to the same URL and report only what changed. For PR-driven software projects, the skill reads `swe.md` and pulls live state via `gh pr list`, `gh pr view`, and `git log` — no manual copy-pasting required.
• Шаблон пользовательской slash-команды для Claude Code — example-command is a Claude Code skill that serves as a reference template for building custom slash commands using the `skills/<name>/SKILL.md` layout. It documents every supported frontmatter field — `name`, `description`, `argument-hint`, `allowed-tools`, and `model` — and shows how to handle required and optional arguments via the `$ARGUMENTS` variable. The skill is pre-approved to use the Read, Glob, Grep, and Bash tools. Functionally it is identical to the legacy `commands/example-command.md` format; only the file structure differs. Developers creating their own Claude Code plugins or slash commands can use this as a ready-made starting point instead of piecing together the syntax from documentation.
• Аналитика сессий Claude Code в HTML-отчёте — session-report is a Claude Code skill that analyzes session transcripts from ~/.claude/projects and produces a self-contained interactive HTML report covering token usage, cache efficiency, subagents, skills, and expensive prompts. The bundled analyze-sessions.mjs script collects data for a configurable window — 24h, 7d, 30d, or all time — and outputs a JSON with sections for overall, by_project, by_subagent_type, by_skill, cache_breaks, and top_prompts. The skill copies a bundled template (with pre-built JS/CSS for sorting, bars, and drill-downs), injects the JSON blob, then fills an anomalies block with 3–5 findings expressed as percentages of total tokens and an optimizations block with 1–4 actionable suggestions tied to specific projects or prompts. It's built for developers and teams who need visibility into Claude Code spending, want to spot cache-hit rates below 85%, or identify subagent calls averaging over 1M tokens per invocation.
• Аудит и улучшение CLAUDE.md файлов — claude-md-improver is a Claude Code skill that audits and improves CLAUDE.md files across an entire repository so Claude Code receives accurate, up-to-date project context. It operates in five phases: discovery of all CLAUDE.md, .claude.local.md, and nested variants via Glob and Bash; quality assessment of each file against six weighted criteria — commands/workflows, architecture clarity, non-obvious patterns, conciseness, currency, and actionability — scored A through F; generation of a detailed per-file report with a breakdown table; targeted diff-format improvement proposals with explanations; and Edit-based updates applied only after explicit user approval. The skill is designed for developers who want to fix stale build commands, document monorepo package relationships, or capture environment setup that Claude keeps missing — essentially turning CLAUDE.md maintenance into a structured, reviewable process.
• Создание slash-команд для Claude Code — command-development is a Claude Code skill that guides the creation of slash commands — reusable Markdown-based prompts with YAML frontmatter, dynamic arguments ($ARGUMENTS, $1, $2), and optional bash execution for runtime context. It covers file layout across .claude/commands/ (project-scoped) and ~/.claude/commands/ (user-scoped) directories, frontmatter fields including description, allowed-tools, model, argument-hint, and disable-model-invocation, and the critical principle that commands must be written as directives to Claude rather than messages to the user. Developers and teams who want to standardize recurring workflows, share complex prompts across a project, or quickly invoke multi-step instructions will find this skill directly applicable.
• Шаблон для создания скилла Claude Code — example-skill is a Claude Code skill that serves as a reference template for building new plugin skills, covering their structure, file layout, and frontmatter format. The core SKILL.md file documents required and optional directory contents — including README.md, references/, examples/, and scripts/ subdirectories — along with frontmatter fields (name, description, version, license) and guidelines for writing effective trigger descriptions. It activates when a user asks to demonstrate skill format, create a skill template, or discusses plugin development patterns. Developers looking to build their own Claude Code skills will find clear explanations of how skills differ from commands and agents, plus concrete examples of trigger phrases that reliably invoke a skill.
• Структурированное планирование задач разработки — plan is a Claude Code skill that builds comprehensive, actionable work plans through intelligent interaction before any implementation begins. It supports four modes: interview (structured requirements gathering for vague requests), direct (immediate planning when the task is already well-defined), consensus (an automated Planner→Architect→Critic loop with RALPLAN-DR structured deliberation, switchable to deliberate mode for high-risk changes like auth, data migrations, or public API modifications), and review (Critic evaluation of an existing plan). The skill auto-detects which mode fits the request, asks exactly one question at a time during interviews, and pre-fetches codebase facts via an `explore` agent before prompting the user. Quality gates require 80%+ of claims to cite a file and line, and 90%+ of acceptance criteria to be testable. It suits engineers who need to scope an ambiguous feature, align on architecture across perspectives, or get a structured critique of a plan they've already drafted.
• Планирование и сборка презентации PowerPoint — Presentation Slide Planner is a Claude Code skill that locks in the narrative outline before building anything, then assembles a complete PowerPoint deck with speaker notes and a formatting review. Reach for it when you need to put together a pitch deck or project report fast but aren't sure where to start, when your slides keep ending up wall-to-wall text, or when you're designing a training course and need the storyline to hold together. The skill opens by asking three things: who the audience is, what you want them to do after the talk, and how many slides you have to work with. It then presents a slide-by-slide outline — one line per slide, title plus the single message it must land — following the arc of current situation, problem, solution, evidence, call to action, and waits for your approval or edits. Only after confirmation does it build the deck: at most four bullets per slide, each around eight words, charts and images described inline, and the spoken script placed in speaker notes. Before delivery it checks every slide for text overflow, excess bullets, and inconsistent styling, then flags one or two spots you're most likely to want to adjust. The skill is designed to create a deck from scratch, not to reformat an existing one.
• Создание вакансии и критериев отбора — Job Description Writer is a Claude Code skill that turns a hiring need into a publish-ready job description with responsibilities, requirements, and a resume-screening rubric, delivered as a Word document. Reach for it when you need to draft a JD from a hiring manager's verbal request, modernise an outdated role profile for a new position, or build a scored screening table before interviews start. The skill follows a structured workflow: it first confirms the essentials — role title and level, reporting line, the core problem the hire must solve, three to five must-have capabilities, location, and working mode — then proposes a one-sentence role mission plus three six-month deliverables for the user to approve before writing begins. The resulting Word file includes an About the team section, Responsibilities (five to eight verb-led items each naming a measurable output), Requirements split into Must have and Nice to have (no more than six hard requirements), compensation placeholders, hiring-process stages, and an appendix with a weighted screening rubric. After delivery it flags requirements likely to shrink the candidate pool and suggests which could be relaxed. The final document must be reviewed by HR or legal before publishing — no restrictions based on gender, age, marital status, or health are included.
• Глубокая документация кодовой базы для AI-агентов — deepinit is a Claude Code skill that performs deep codebase initialization by generating hierarchical AGENTS.md documentation across every project directory. It traverses the directory tree level by level — excluding node_modules, .git, dist, and similar folders — then analyzes each directory and writes a structured AGENTS.md covering key files, internal and external dependencies, code patterns, and special instructions for AI agents. Every file except the root includes a `<!-- Parent: ../AGENTS.md -->` tag, building a fully navigable hierarchy. On subsequent runs, auto-generated sections are updated while manual annotations below the `<!-- MANUAL -->` marker are preserved. The skill delegates work across specialized subagents (explore, architect, writer) and supports parallel processing of same-level directories. It suits teams that want their codebase to be immediately readable by AI tooling and easier to navigate for both agents and new developers.
• Составление стандартных операционных процедур — Преобразует текущую практику в стандартизированный SOP или политику с описанием ролей, пошаговых действий, контрольных точек и обработкой исключений. Результат — Word-документ, готовый к внедрению и аудиту.
• Деловые письма и follow-up на двух языках — Составление деловых писем is a Claude Code skill that turns a brief description of intent, recipient and context into send-ready business emails and follow-up sequences in multiple tones, in the user's language and English, delivered as a Markdown document. Reach for it when you need to write a professional email and aren't sure where to start; when a client has gone quiet and you need a polite reminder series; when the same message must work in both formal and casual registers; or when the email needs to sound like a native English speaker rather than a translation. The skill asks for the purpose, the recipient's role and relationship, the expected action with a deadline, and the preferred language — then builds a structured email: subject line under ten words, body under 200 words, closing with an explicit call to action. It produces three tone versions by default — formal, friendly, and short-and-direct — and adds a cautious variant for first contacts or senior recipients. A follow-up sequence runs three to four emails: initial send, gentle nudge on day 3, added value on day 7, final check-in on day 14. Bilingual output delivers independent texts rewritten for each language, not word-for-word pairs. Where contractual or compliance language is involved, the skill flags it for review by the relevant team before sending.
• Оформление протокола совещания в Word — Meeting Minutes is a Claude Code skill that turns a recording transcript, chat log or scattered notes into a structured set of meeting minutes — with decisions, an action-item table and a circulate-ready Word document. Reach for it when you need to write up a meeting from a raw audio transcript before end of day, when a Slack or Telegram thread contains agreements you need to extract into clear tasks with owners, or when a one-hour call produced nothing but a page of messy bullet points that need to become a proper record. The skill identifies topic, date, attendees and chair, then organises content by agenda item: discussion points (both sides of any disagreement), decisions (each prefixed "Decision:") and action items. Actions go into a table — number, item, owner, due date, status — one row per action, never merged. The output is a Word document built with the skill's built-in document tools, titled "<Topic> Meeting Minutes YYYY-MM-DD". After delivery, the skill lists any owner or due date still to confirm and reminds you to check the distribution list before circulating, especially for personnel or pay topics. This skill goes from raw input to finished document — not the other way around. Mixed-language transcripts are written up in the user's primary language; proper nouns stay as spoken. Missing data is marked "TBD", never guessed.
• Деловые отчёты в Word по структуре — Business Reports is a Claude Code skill that drafts Word-format business reports following a fixed section order: executive summary, background, findings/analysis, recommendations, risks, and appendix. Reach for it when you need to turn raw notes or spreadsheet data into a polished document ready for leadership, when a memo or assessment needs consistent voice and properly sourced numbers, or when you're tired of manually styling headings and numbering every recommendation. Before writing a single sentence, the skill reads every attached or referenced file in full — figures, dates, and names come exclusively from those sources; if a source is silent on a point, the report says so rather than inventing data. Sections are rendered with real Word heading styles, real numbered lists, and properly formatted tables (header row, right-aligned numbers, units in the header), never simulated with bold text or tabs. Each recommendation links back to a specific finding and includes an owner and time frame when the source material allows it. The skill generates or rewrites documents rather than reviewing finished text — that distinction matters when choosing among catalog tools. Default output is 2–4 pages; very large research compilations spanning dozens of sources may need manual structural review after generation.
• Еженедельный отчёт из заметок в Word — Weekly Work Report is a Claude Code skill that turns scattered progress notes, chat logs, and task lists into a structured weekly or monthly status report delivered as a Word document. Reach for it when you spend too long every Monday wrestling raw notes into a presentable update for your manager; when you need to roll last week's report forward into this week's version without starting from scratch; or when a quick status report has to look polished and submission-ready in minutes. The skill sorts whatever material you provide into four buckets — done, in progress, blockers and risks, next week's plan — and asks for missing figures or dates rather than inventing them. The Word document follows a fixed structure: a title («Week N YYYY Report» or a name you specify), a three-line overview, key results with supporting data, open items, risks, and the upcoming plan. Style is conclusion-first, numbers wherever available, no item longer than two lines. After delivering the file, the skill adds a sentence or two on highlights and what could still be adjusted. The direction is from raw input to finished document, not from a finished report into multi-period analytics or data visualisation. Suits individuals and teams with recurring reporting obligations; not the right fit when you need dashboards or aggregated trends across many weeks.
• Планирование OKR в Excel-таблице — OKR Planning is a Claude Code skill that turns team directions, annual goals, or an unstructured task list into a formatted Objectives and Key Results table delivered as a ready-to-use Excel workbook with three sheets. Reach for it when you need to set measurable quarterly goals across teams, when your OKRs feel more like to-do lists than outcome statements, or when you want to align department-level objectives to a company-wide strategy. The skill starts by asking about the cycle (quarter or half-year), the team level (company, department, or squad), and whether a parent OKR already exists — every Objective must map to one of its Key Results. It then surfaces 3–5 qualitative Objectives and 2–4 measurable KRs each, with a metric definition, baseline, target, and deadline. Missing baselines are flagged as "baseline pending" — no numbers are invented. The Excel workbook includes an OKR sheet with a formula-driven Progress column, an Alignment sheet linking this level's Os to parent KRs, and an empty Review log for weekly check-ins. After delivering the file, the skill adds written comments identifying KRs that read as tasks rather than outcomes, goals that conflict, and what to cut or merge. Works best for a single team per cycle within the 5-Objective and 15-KR limit; beyond that, it prompts prioritisation.
• Презентация для руководства по пирамиде Минто — Презентация для руководства is a Claude Code skill that builds executive and board presentations using the Minto Pyramid principle — answer first, every slide title states a conclusion, and the body of each slide contains only evidence. Reach for it when you need a board deck or quarterly business review, a status update for senior leadership, a slide-based argument for a budget or strategic decision, or when you want to convert a dense document into tight slides that tell a clear story. The skill enforces a fixed structure: a title slide naming the decision, an answer slide with one sentence conclusion and three supporting points, one slide per supporting point (chart or table, never mixed), a recommendations slide with owners and dates, an optional risks slide, and an appendix for backup detail. Formatting rules are strict: no more than five bullets of twelve words each, all numbers carry unit and time period, data sources go in a footer not a bullet, and speaker notes are written for every content slide. Figures are taken only from attached files; if a number is missing from the source, the skill says so on the slide rather than estimating. The direction is narrative architecture and argumentation — not visual design or slide layout tooling. Works for both English and Russian-language decks; does not replace PowerPoint, Keynote, or Canva for final visual production.
• Составление договоров и оценка рисков — Contract Drafter is a Claude Code skill that produces a complete contract or agreement as a Word document, paired with a pre-signing risk checklist. All output is for reference only and must be reviewed by a licensed lawyer before signing. Reach for it when you need to draft a services or outsourcing agreement quickly, put together a memorandum of cooperation, scan an existing agreement for one-sided or risky clauses, or get a structured starting point for negotiations with a counterparty. The skill first collects all required parameters — parties, subject matter and scope, amounts and payment schedule, deadlines as absolute dates, acceptance criteria, liability for breach, confidentiality, intellectual property ownership, termination conditions, and dispute resolution venue. It then generates a Word document with a standard structure: preamble with party details, recitals, numbered body articles, and a signature block. Every monetary amount appears in figures and in words; every obligation is paired with a consequence for breach. The document closes with a pre-signing checklist that flags clauses leaning against the user or left open for negotiation, explaining the risk for each. The direction is drafting reference documents, not legal analysis of applicable law.
• GenOffice — создание и конвертация Office-документов — Генерация офисных документов через ИИ is a Claude Code skill that creates, converts, reads, and edits Office files (PPTX, XLSX, DOCX, PDF) locally via the GenOffice CLI, keeping document contents off the cloud. Reach for it when you need a slide deck built from a short brief, a spreadsheet assembled from CSV or JSON data with formulas, a Word report generated from Markdown or HTML, or when you need to convert files between formats — say, DOCX to PDF or PPTX to HTML. The skill runs a checked outline → per-slide spec → render pipeline for presentations; supports conversion across pdf, docx, xlsx, pptx, md, html, and csv; reads the structure and text of existing files; and applies structured edits to them. It runs headless through GenOffice CLI (version ≥ 0.9.0, bundled with GenOffice); only the search, image, and media commands send data to the provider configured in GenOffice. The direction is generating and editing real Office files you open in PowerPoint, Excel, or Word — not online viewing or collaboration. Works wherever GenOffice is installed; not applicable if the app is absent from the machine.
• Saga — распределённые транзакции без двухфазного коммита — saga-orchestration is a Claude Code skill that implements saga patterns for managing distributed transactions and long-running business workflows without two-phase commit. It covers both orchestration and choreography approaches, producing a saga definition with ordered steps, action commands, and compensation commands for each participant service — all idempotent and guaranteed to publish a result event even on rollback. Per-step timeout configuration, state machine metrics, stuck saga detection, and DLQ recovery are included out of the box. The skill targets engineers coordinating multi-service transactions across inventory, payment, and shipping, building atomic rollback for travel booking systems (hotel, flight, car rental), or debugging production sagas stuck in a COMPENSATING state where compensation steps never complete. It integrates with durable message brokers such as Kafka, RabbitMQ, and SQS, and pairs naturally with the cqrs-implementation and event-store-design skills.

FAQ

How do I share a Claude Code skill with my team?

Put the skill folder containing SKILL.md into the project repository — usually under .claude/skills/ — and commit it. Claude Code picks up skills from the repository for everyone who has cloned it, so there is nothing to distribute or install separately.

How is a skill different from instructions in CLAUDE.md?

CLAUDE.md is always active and describes the project as a whole. A skill is a self-contained procedure for one kind of task: it loads when that task comes up and stays out of the context window the rest of the time. In practice teams use both — project rules in CLAUDE.md, repeatable procedures as skills.

All Claude Code skills