Skills by anthropics

This skill provides PDF processing utilities and scripts for extracting, filling, and transforming PDFs. It includes instructions to run local scripts and CLI tools (e.g., `python scripts/fill_pdf_form_with_annotations.py`, `qpdf`, `magick`) and contains password-based operations such as `writer.encrypt("userpassword", "ownerpassword")`.

This skill provides tools and documentation for reading, editing, and creating `.pptx` files (examples and scripts such as `scripts/office/unpack.py` and `scripts/office/pack.py`). It instructs running shell commands (e.g., `python -m markitdown presentation.pptx`) and loading remote images (e.g., `https://example.com/image.jpg`).

High-risk skill for creating and editing `.docx` files that provides unpack/modify/pack scripts and CLI examples. It explicitly instructs running shell commands and subprocesses (e.g., `soffice`, `npm install -g docx`, `python scripts/office/accept_changes.py`) and writes to paths such as `/tmp/libreoffice_docx_profile`.

This skill provides detailed workflows and scripts for creating, editing, and validating `.xlsx`/Office files using `pandas`, `openpyxl`, and included tooling. It explicitly instructs running local CLI scripts such as `python scripts/recalc.py <excel_file>` and `python pack.py`, which invoke local shell execution.

Dangerous skill that executes user-supplied shell commands and advises treating bundled scripts as `black-box` without inspecting their source. It launches commands via `subprocess.Popen(..., shell=True)` and writes outputs to `'/mnt/user-data/outputs/console.log'` and screenshots like `'/tmp/page_discovery.png'`.

This skill is a guide and example codebase for building and evaluating MCP servers (TypeScript/Python), including an evaluation harness and transport examples. It instructs external fetches to `https://modelcontextprotocol.io/sitemap.xml` and `https://raw.githubusercontent.com/...`, runs commands like `python scripts/evaluation.py`, and uses env vars such as `ANTHROPIC_API_KEY`.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

This skill documents how to create and package Claude skills and includes runnable helper scripts and templates. It explicitly instructs executing `scripts/init_skill.py` and `scripts/package_skill.py`, which create directories and write files on the filesystem.

This skill provides guidance for creating Claude Code plugin skills and organizing `scripts/`, `references/`, and `assets/`. It includes explicit shell commands such as `mkdir -p plugin-name/skills/skill-name/{references,examples,scripts}` and `scripts/init_skill.py <skill-name> --path <output-directory>` that instruct executing local scripts.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill documents integrating Model Context Protocol (MCP) servers into Claude Code plugins (stdio, SSE, HTTP, ws) with examples and lifecycle guidance. It includes instructions to start local processes (`${CLAUDE_PLUGIN_ROOT}/servers/db-server`), run shell commands (`claude --debug`, `curl`), and use environment variables like `DB_PASSWORD` and `API_TOKEN`.

Provides guidance and examples for implementing Claude Code plugin hooks (prompt and `command` hooks) plus example scripts. It includes explicit `command` hooks such as `bash ${CLAUDE_PLUGIN_ROOT}/scripts/validate.sh` and integrations that call external endpoints (`curl` to `$SLACK_WEBHOOK`) and databases (`psql $DATABASE_URL`).

Dangerous skill: contains explicit directives to run shell commands (e.g., `!`git status`, `!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/build.sh`) and to invoke networked CLIs (e.g., `gh`, `kubectl`). It is a `Command Development` guide for building Claude Code slash commands that uses `${CLAUDE_PLUGIN_ROOT}` and wide `allowed-tools` patterns.

This skill audits and updates repository `CLAUDE.md` files. It runs shell commands such as `find . -name "CLAUDE.md" -o -name ".claude.local.md"` and can write/update `CLAUDE.md` and `./.claude.local.md`.

Provides comprehensive guidance and examples for Claude Code plugin structure, manifests, hooks, skills, and MCP server integration. Includes hook commands that run `bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/...` scripts, MCP configs referencing env vars such as `${GITHUB_TOKEN}`, and repository URLs like `https://github.com/company/devops-plugin.git`.

Provides patterns, templates, and example scripts for per-project plugin settings stored in `.claude/*.local.md`. Includes runnable shell scripts (e.g., `#!/bin/bash`, `cat > ...`, `tmux send-keys`) that perform file writes, atomic moves, and removals.

This skill builds single-file HTML playgrounds from templates in `templates/` for visual exploration and prompt generation. It includes explicit shell instructions such as `open <filename>.html` and `git show <commit> --format="%H%n%s%n%an%n%ad" -p`, which are low-risk static shell executions.

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

This skill provides best-practice guidance for building Stripe integrations (e.g., `CheckoutSessions`, `PaymentIntents`, Billing, Connect) and references `docs.stripe.com` for details. No security-relevant behaviors detected.

This skill analyzes a codebase and recommends Claude Code automations (MCP servers, hooks, skills, subagents, plugins). It explicitly instructs running shell commands like `ls -la` and `cat package.json` and using `!`command`` injection, recommends checking `.mcp.json` into git, and directs `web search`/MCP integrations such as `context7`.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

This skill documents how to create Claude Code plugin skills, including structure, resources, and best practices. It contains explicit instructions to run CLI scripts such as `scripts/init_skill.py`, `scripts/package_skill.py`, and `cc --plugin-dir /path/to/plugin`, which directs shell command execution.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill provides guidance, examples, and scripts for implementing Claude Code plugin hooks (prompt and command hooks, configuration, and testing). It enables executing shell commands (e.g., `"command": "bash ${CLAUDE_PLUGIN_ROOT}/scripts/validate.sh"`), persisting env vars to `"$CLAUDE_ENV_FILE"`, and external calls using `"$SLACK_WEBHOOK"`/`"$DATABASE_URL"`.

This skill documents how to author Claude Code slash commands, covering frontmatter, `@` file references, argument substitution, and bash/script integration. It instructs executing shell commands (e.g., `!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/build.sh`), accessing plugin files via `@${CLAUDE_PLUGIN_ROOT}`, requesting broad `allowed-tools` (`allowed-tools: "*"`, `Bash(*)`), and calling CLI APIs like `gh api /deployments/$1`.

This skill documents how to integrate MCP servers into Claude Code plugins, including `stdio`, `sse`, `http`, and `ws` configurations. It explicitly instructs spawning local processes via `command`/`args`, executing shell commands (`claude --debug`, `source .env`), using secret env vars like `${API_TOKEN}`, and contacting endpoints such as `https://api.example.com/mcp`.

This skill documents the `.claude/*.local.md` per-project settings pattern and includes templates and examples. It provides executable shell scripts and commands (e.g., `read-settings-hook.sh`, `parse-frontmatter.sh`, `tmux send-keys`, `cat > ... <<EOF`) that instruct running shell actions.

This skill documents Claude Code plugin structure, manifest fields, component locations, and best practices for scaffolding plugins. It includes executable hooks (e.g., `bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/security/scan-secrets.sh`, `hooks/scripts/validate-commit.sh`), MCP server env bindings like `GITHUB_TOKEN` and `API_KEY`, and examples calling external services (`tools.github_actions_trigger_workflow`, `SlackClient.notify`).

Write structured product requirements documents (PRDs) with problem statements, user stories, requirements, and success metrics. Use when speccing a new feature, writing a PRD, defining acceptance criteria, prioritizing requirements, or documenting product decisions.

Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Draft marketing content across channels — blog posts, social media, email newsletters, landing pages, press releases, and case studies. Use when writing any marketing content, when you need channel-specific formatting, SEO-optimized copy, headline options, or calls to action.

Research competitors and compare positioning, messaging, content strategy, and market presence. Use when analyzing a competitor, building battlecards, identifying content gaps, comparing feature messaging, or preparing competitive positioning recommendations.

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.

Plan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE. Use when creating a roadmap, reprioritizing features, mapping dependencies, choosing between Now/Next/Later or quarterly formats, or presenting roadmap tradeoffs to stakeholders.

Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.

Synthesize qualitative and quantitative user research into structured insights and opportunity areas. Use when analyzing interview notes, survey responses, support tickets, or behavioral data to identify themes, build personas, or prioritize opportunities.

This skill audits Anthropic Cookbook notebooks and runs `validate_notebook.py` and `detect-secrets` to generate a markdown review. It instructs executing local commands (`python3 validate_notebook.py`, `uv run`, `sh -c ...`) and scans files for hardcoded keys such as `ANTHROPIC_API_KEY` and `OPENAI_API_KEY`.

Define, track, and analyze product metrics with frameworks for goal setting and dashboard design. Use when setting up OKRs, building metrics dashboards, running weekly metrics reviews, identifying trends, or choosing the right metrics for a product area.

Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations.

Apply and enforce brand voice, style guide, and messaging pillars across content. Use when reviewing content for brand consistency, documenting a brand voice, adapting tone for different audiences, or checking terminology and style guide compliance.

Generate income statements, balance sheets, and cash flow statements with GAAP presentation and period-over-period comparison. Use when preparing financial statements, running flux analysis, or creating P&L reports with variance commentary.

Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.

Draft stakeholder updates tailored to audience — executives, engineering, customers, or cross-functional partners. Use when writing weekly status updates, monthly reports, launch announcements, risk communications, or decision documentation.

Review contracts against your organization's negotiation playbook, flagging deviations and generating redline suggestions. Use when reviewing vendor contracts, customer agreements, or any commercial agreement where you need clause-by-clause analysis against standard positions.

Analyze marketing performance with key metrics, trend analysis, and optimization recommendations. Use when building performance reports, reviewing campaign results, analyzing channel metrics (email, social, paid, SEO), or identifying what's working and what needs improvement.

Research a prospect then draft personalized outreach. Uses web research by default, supercharged with enrichment and CRM. Trigger with "draft outreach to [person/company]", "write cold email to [prospect]", "reach out to [name]".

`data-validation` provides a pre-delivery QA checklist, common data-analysis pitfalls, sanity checks, and documentation templates to make analyses reproducible. No security-relevant behaviors detected.

Profile and explore datasets to understand their shape, quality, and patterns before analysis. Use when encountering a new dataset, assessing data quality, discovering column distributions, identifying nulls and outliers, or deciding which dimensions to analyze.

Plan marketing campaigns with objectives, audience segmentation, channel strategy, content calendars, and success metrics. Use when launching a campaign, planning a product launch, building a content calendar, allocating budget across channels, or defining campaign KPIs.

The `knowledge-synthesis` skill merges results from multiple sources into coherent, deduplicated answers with source attribution and confidence scoring. No security-relevant behaviors detected.

Research your competitors and build an interactive battlecard. Outputs an HTML artifact with clickable competitor cards and a comparison matrix. Trigger with "competitive intel", "research competitors", "how do we compare to [competitor]", "battlecard for [competitor]", or "what's new with [competitor]".

Write and maintain knowledge base articles from resolved support issues. Use when a ticket has been resolved and the solution should be documented, when updating existing KB articles, or when creating how-to guides, troubleshooting docs, or FAQ entries.

Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect enrichment tools or your CRM. Trigger with "research [company]", "look up [person]", "intel on [prospect]", "who is [name] at [company]", or "tell me about [company]".