Development
anthropics-skills
Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks.
Install on Claude Code
> /plugin marketplace add anthropics/skills
Stats
169,699
Stars
20,200
Forks
Active
Maintenance
Python
Language
2d ago
Last commit
10mo ago
Created
1mo ago
Added
Repo: anthropics/skills
What's inside
Skills
17/algorithmic-artCreating 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/brand-guidelinesApplies 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./canvas-designCreate 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/claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names/doc-coauthoringGuide 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/docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting
Show all 17 skillsShow fewer
/frontend-designGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults./internal-commsA 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/mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK)./pdfUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms,/pptxUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used/skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's/slack-gif-creatorKnowledge 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./theme-factoryToolkit 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./web-artifacts-builderSuite 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/webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs./xlsxUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy
Agents
3README
1Note: This repository contains Anthropic's implementation of skills for Claude. For information about the Agent Skills standard, see agentskills.io.
Skills
Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks. Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows, or automating personal tasks.
For more information, check out:
- What are skills?
- Using skills in Claude
- How to create custom skills
- Equipping agents for the real world with Agent Skills
About This Repository
This repository contains skills that demonstrate what's possible with Claude's skills system. These skills range from creative applications (art, music, design) to technical tasks (testing web apps, MCP server generation) to enterprise workflows (communications, branding, etc.).
Each skill is self-contained in its own folder with a SKILL.md file containing the instructions and metadata that Claude uses. Browse through these skills to get inspiration for your own skills or to understand different patterns and approaches.
Many skills in this repo are open source (Apache 2.0). We've also included the document creation & editing skills that power Claude's document capabilities under the hood in the skills/docx, skills/pdf, skills/pptx, and skills/xlsx subfolders. These are source-available, not open source, but we wanted to share these with developers as a reference for more complex skills that are actively used in a production AI application.
Disclaimer
These skills are provided for demonstration and educational purposes only. While some of these capabilities may be available in Claude, the implementations and behaviors you receive from Claude may differ from what is shown in these skills. These skills are meant to illustrate patterns and possibilities. Always test skills thoroughly in your own environment before relying on them for critical tasks.
Skill Sets
- ./skills: Skill examples for Creative & Design, Development & Technical, Enterprise & Communication, and Document Skills
- ./spec: The Agent Skills specification
- ./template: Skill template
Try in Claude Code, Claude.ai, and the API
Claude Code
You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code:
/plugin marketplace add anthropics/skills
Then, to install a specific set of skills:
- Select
Browse and install plugins - Select
anthropic-agent-skills - Select
document-skillsorexample-skills - Select
Install now
Alternatively, directly install either Plugin via:
/plugin install document-skills@anthropic-agent-skills
/plugin install example-skills@anthropic-agent-skills
After installing the plugin, you can use the skill by just mentioning it. For instance, if you install the document-skills plugin from the marketplace, you can ask Claude Code to do something like: "Use the PDF skill to extract the form fields from path/to/some-file.pdf"
Claude.ai
These example skills are all already available to paid plans in Claude.ai.
To use any skill from this repository or upload custom skills, follow the instructions in Using skills in Claude.
Claude API
You can use Anthropic's pre-built skills, and upload custom skills, via the Claude API. See the Skills API Quickstart for more.
Creating a Basic Skill
Skills are simple to create - just a folder with a SKILL.md file containing YAML frontmatter and instructions. You can use the template-skill in this repository as a starting point:
---
name: my-skill-name
description: A clear description of what this skill does and when to use it
---
# My Skill Name
[Add your instructions here that Claude will follow when this skill is active]
## Examples
- Example usage 1
- Example usage 2
## Guidelines
- Guideline 1
- Guideline 2
The frontmatter requires only two fields:
name- A unique identifier for your skill (lowercase, hyphens for spaces)description- A complete description of what the skill does and when to use it
The markdown content below contains the instructions, examples, and guidelines that Claude will follow. For more details, see How to create custom skills.
Partner Skills
Skills are a great way to teach Claude how to get better at using specific pieces of software. As we see awesome example skills from partners, we may highlight some of them here:
- Notion - Notion Skills for Claude
File tree
412anthropics/skillsView on GitHub
.claude-plugin/
marketplace.json
.gitignore
README.md
skills/
algorithmic-art/
LICENSE.txt
SKILL.md
templates/
generator_template.js
viewer.html
brand-guidelines/
LICENSE.txt
SKILL.md
canvas-design/
canvas-fonts/
ArsenalSC-OFL.txt
ArsenalSC-Regular.ttf
BigShoulders-Bold.ttf
BigShoulders-OFL.txt
BigShoulders-Regular.ttf
Boldonse-OFL.txt
Boldonse-Regular.ttf
BricolageGrotesque-Bold.ttf
BricolageGrotesque-OFL.txt
BricolageGrotesque-Regular.ttf
CrimsonPro-Bold.ttf
CrimsonPro-Italic.ttf
CrimsonPro-OFL.txt
CrimsonPro-Regular.ttf
DMMono-OFL.txt
DMMono-Regular.ttf
EricaOne-OFL.txt
EricaOne-Regular.ttf
GeistMono-Bold.ttf
GeistMono-OFL.txt
GeistMono-Regular.ttf
Gloock-OFL.txt
Gloock-Regular.ttf
IBMPlexMono-Bold.ttf
IBMPlexMono-OFL.txt
IBMPlexMono-Regular.ttf
IBMPlexSerif-Bold.ttf
IBMPlexSerif-BoldItalic.ttf
IBMPlexSerif-Italic.ttf
IBMPlexSerif-Regular.ttf
InstrumentSans-Bold.ttf
InstrumentSans-BoldItalic.ttf
InstrumentSans-Italic.ttf
InstrumentSans-OFL.txt
InstrumentSans-Regular.ttf
InstrumentSerif-Italic.ttf
InstrumentSerif-Regular.ttf
Italiana-OFL.txt
Italiana-Regular.ttf
JetBrainsMono-Bold.ttf
JetBrainsMono-OFL.txt
JetBrainsMono-Regular.ttf
Jura-Light.ttf
Jura-Medium.ttf
Jura-OFL.txt
LibreBaskerville-OFL.txt
LibreBaskerville-Regular.ttf
Lora-Bold.ttf
Lora-BoldItalic.ttf
Lora-Italic.ttf
Lora-OFL.txt
Lora-Regular.ttf
NationalPark-Bold.ttf
NationalPark-OFL.txt
NationalPark-Regular.ttf
NothingYouCouldDo-OFL.txt
NothingYouCouldDo-Regular.ttf
Outfit-Bold.ttf
Outfit-OFL.txt
Outfit-Regular.ttf
PixelifySans-Medium.ttf
PixelifySans-OFL.txt
PoiretOne-OFL.txt
PoiretOne-Regular.ttf
RedHatMono-Bold.ttf
RedHatMono-OFL.txt
RedHatMono-Regular.ttf
Silkscreen-OFL.txt
Silkscreen-Regular.ttf
SmoochSans-Medium.ttf
SmoochSans-OFL.txt
Tektur-Medium.ttf
Tektur-OFL.txt
Tektur-Regular.ttf
WorkSans-Bold.ttf
WorkSans-BoldItalic.ttf
WorkSans-Italic.ttf
WorkSans-OFL.txt
WorkSans-Regular.ttf
YoungSerif-OFL.txt
YoungSerif-Regular.ttf
LICENSE.txt
SKILL.md
claude-api/
csharp/
claude-api/
batches.md
files-api.md
README.md
streaming.md
tool-use.md
curl/
examples.md
managed-agents.md
go/
claude-api/
files-api.md
README.md
streaming.md
tool-use.md
managed-agents/
README.md
java/
claude-api/
files-api.md
README.md
streaming.md
tool-use.md
managed-agents/
README.md
LICENSE.txt
php/
claude-api/
batches.md
files-api.md
README.md
streaming.md
tool-use.md
managed-agents/
README.md
python/
claude-api/
batches.md
files-api.md
README.md
streaming.md
tool-use.md
managed-agents/
README.md
ruby/
claude-api/
README.md
streaming.md
tool-use.md
managed-agents/
README.md
shared/
agent-design.md
anthropic-cli.md
claude-platform-on-aws.md
error-codes.md
live-sources.md
managed-agents-api-reference.md
managed-agents-client-patterns.md
managed-agents-core.md
managed-agents-environments.md
managed-agents-events.md
managed-agents-memory.md
managed-agents-multiagent.md
managed-agents-onboarding.md
managed-agents-outcomes.md
managed-agents-overview.md
managed-agents-scheduled-deployments.md
managed-agents-self-hosted-sandboxes.md
managed-agents-tools.md
managed-agents-webhooks.md
model-migration.md
models.md
platform-availability.md
prompt-audit.md
prompt-caching.md
token-counting.md
tool-use-concepts.md
SKILL.md
typescript/
claude-api/
batches.md
files-api.md
README.md
streaming.md
tool-use.md
managed-agents/
README.md
doc-coauthoring/
SKILL.md
docx/
LICENSE.txt
scripts/
__init__.py
accept_changes.py
comment.py
merge_runs.py
office/
helpers/
__init__.py
pptx_chart.py
pptx_slide.py
pptx_theme.py
schemas/
ecma/
fouth-edition/
opc-contentTypes.xsd
opc-coreProperties.xsd
opc-digSig.xsd
opc-relationships.xsd
ISO-IEC29500-4_2016/
dml-chart.xsd
dml-chartDrawing.xsd
dml-diagram.xsd
dml-lockedCanvas.xsd
dml-main.xsd
dml-picture.xsd
dml-spreadsheetDrawing.xsd
dml-wordprocessingDrawing.xsd
pml.xsd
shared-additionalCharacteristics.xsd
shared-bibliography.xsd
shared-commonSimpleTypes.xsd
shared-customXmlDataProperties.xsd
shared-customXmlSchemaProperties.xsd
shared-documentPropertiesCustom.xsd
shared-documentPropertiesExtended.xsd
shared-documentPropertiesVariantTypes.xsd
shared-math.xsd
shared-relationshipReference.xsd
sml.xsd
vml-main.xsd
vml-officeDrawing.xsd
vml-presentationDrawing.xsd
vml-spreadsheetDrawing.xsd
vml-wordprocessingDrawing.xsd
wml.xsd
xml.xsd
mce/
mc.xsd
microsoft/
wml-2010.xsd
wml-2012.xsd
wml-2018.xsd
wml-cex-2018.xsd
wml-cid-2016.xsd
wml-sdtdatahash-2020.xsd
wml-symex-2015.xsd
soffice.py
validate.py
validators/
__init__.py
base.py
docx.py
pptx.py
redlining.py
templates/
comments.xml
commentsExtended.xml
commentsExtensible.xml
commentsIds.xml
people.xml
SKILL.md
frontend-design/
LICENSE.txt
SKILL.md
internal-comms/
examples/
3p-updates.md
company-newsletter.md
faq-answers.md
general-comms.md
LICENSE.txt
SKILL.md
mcp-builder/
LICENSE.txt
reference/
evaluation.md
mcp_best_practices.md
node_mcp_server.md
python_mcp_server.md
scripts/
connections.py
evaluation.py
example_evaluation.xml
requirements.txt
SKILL.md
pdf/
forms.md
LICENSE.txt
reference.md
scripts/
check_bounding_boxes.py
check_fillable_fields.py
convert_pdf_to_images.py
create_validation_image.py
extract_form_field_info.py
extract_form_structure.py
fill_fillable_fields.py
fill_pdf_form_with_annotations.py
SKILL.md
pptx/
LICENSE.txt
scripts/
__init__.py
add_slide.py
clean.py
office/
helpers/
__init__.py
pptx_chart.py
pptx_slide.py
pptx_theme.py
schemas/
ecma/
fouth-edition/
opc-contentTypes.xsd
opc-coreProperties.xsd
opc-digSig.xsd
opc-relationships.xsd
ISO-IEC29500-4_2016/
dml-chart.xsd
dml-chartDrawing.xsd
dml-diagram.xsd
dml-lockedCanvas.xsd
dml-main.xsd
dml-picture.xsd
dml-spreadsheetDrawing.xsd
dml-wordprocessingDrawing.xsd
pml.xsd
shared-additionalCharacteristics.xsd
shared-bibliography.xsd
shared-commonSimpleTypes.xsd
shared-customXmlDataProperties.xsd
shared-customXmlSchemaProperties.xsd
shared-documentPropertiesCustom.xsd
shared-documentPropertiesExtended.xsd
shared-documentPropertiesVariantTypes.xsd
shared-math.xsd
shared-relationshipReference.xsd
sml.xsd
vml-main.xsd
vml-officeDrawing.xsd
vml-presentationDrawing.xsd
vml-spreadsheetDrawing.xsd
vml-wordprocessingDrawing.xsd
wml.xsd
xml.xsd
mce/
mc.xsd
microsoft/
wml-2010.xsd
wml-2012.xsd
wml-2018.xsd
wml-cex-2018.xsd
wml-cid-2016.xsd
wml-sdtdatahash-2020.xsd
wml-symex-2015.xsd
soffice.py
validate.py
validators/
__init__.py
base.py
docx.py
pptx.py
redlining.py
thumbnail.py
SKILL.md
skill-creator/
agents/
analyzer.md
comparator.md
grader.md
assets/
eval_review.html
eval-viewer/
generate_review.py
viewer.html
LICENSE.txt
references/
schemas.md
scripts/
__init__.py
aggregate_benchmark.py
generate_report.py
improve_description.py
package_skill.py
quick_validate.py
run_eval.py
run_loop.py
utils.py
SKILL.md
slack-gif-creator/
core/
easing.py
frame_composer.py
gif_builder.py
validators.py
LICENSE.txt
... 102 moreThe FLOW.md
Read what you run.
This file reads your intent and auto-invokes the right skill at the right moment. You just prompt.
flow.anthropic-design-test-flow.FLOW.md
# FLOW.md: Design & Test > Build front-end work that looks deliberate and is proven to run, by routing the design, test, and skill-authoring steps to the right skill and refusing to call UI "done" until it has been driven against a running app. > Skills vendored from Anthropic (Apache-2.0). See ATTRIBUTION.md. Routing by Flowy. <!-- The Flowy engine supplies the universal contract (announce ritual, invoke/READ, host-wins, post-compaction re-read). This file carries only the routing. --> ## Phases 1. **Design**. Entry: a UI is being built or reshaped and no intentional design exists yet. Gate: a design plan (palette, type, layout, signature) committed before any production code. 2. **Build**. Entry: the design plan is approved and code is being written. Gate: the interface implemented from that plan, reachable in a running app. 3. **Verify**. Entry: any claim that the UI renders, works, or is done. Gate: a Playwright run against the running app plus a screenshot that proves the claim. 4. **Capture**. Entry: this design-then-verify loop is one you keep repeating and want to reuse. Gate: a packaged skill whose evals were run. ## Routing ``` USER MESSAGE / NEW REQUEST (intake: classify the intent first) │ ├─ Just asking a question, no UI to change (advisory / answer-only)? │ └─ answer directly, propose the matching phase → no skill │ Gate: no artifact; routing recorded │ ├─ Phase 1: needs an interface designed or reshaped? │ ├─ greenfield page / component, no visual direction yet? │ │ → invoke frontend-design │ │ Gate: design plan (palette, type, layout, signature) committed │ └─ restyling an existing screen that reads templated? │ → invoke frontend-design │ Gate: revised plan naming what changed and why │ ├─ Phase 2: design approved, writing the UI code? │ └─ implement strictly from the committed plan │ → invoke frontend-design │ Gate: interface reachable in a running app │ ├─ Phase 3, DONE-CHECK: about to claim it renders / works / is done? │ ├─ server already running? │ │ → invoke webapp-testing │ │ Gate: Playwright run + screenshot proving the claim │ └─ server not started yet? │ → invoke webapp-testing │ Gate: with_server.py launches it, then a passing Playwright run │ ├─ Phase 4: repeating this loop and want it reusable? │ └─ capture the workflow as a skill │ → invoke skill-creator │ Gate: packaged skill with evals run │ ├─ SCOPE CHANGE: brief or requirements changed mid-flow? │ └─ re-enter the earliest affected phase → invoke frontend-design │ Gate: design plan updated to the new brief before building resumes │ ├─ BLOCKED: waiting on a design decision, asset, or credential? │ └─ park the task, name the resume trigger → no skill │ Gate: blocker + resume condition written down │ ├─ REVIEW-LOOP: design or test feedback came back? │ └─ address each item, then re-verify → invoke webapp-testing │ Gate: every finding resolved and a fresh Playwright run is green │ └─ DEFAULT: no branch fits? └─ state Routing: none and ask one narrowing question → no skill Gate: intent restated so a phase can be picked ``` ## Priority on collision 1. **Blocked**: a parked dependency wins; do not route work that cannot proceed. 2. **Scope changed**: a new brief re-enters the earliest affected phase before anything else. 3. **Done-check**: any pending "it works" claim routes to webapp-testing before moving on. 4. **Lifecycle order**: otherwise design before build before verify before capture. 5. **Advisory**: a pure question is answered without forcing a phase. 6. **Default**: nothing fits, so restate intent and ask one question. ## You are rationalizing if you think… - "It looks right in the code, ship it." → invoke webapp-testing. Looking right in source is not running right in a browser; drive the actual app. - "A big number, a gradient accent, and three feature cards is a clean hero." → invoke frontend-design. That is the templated default; the plan must justify a choice made for THIS brief. - "The server is a hassle to start, I will eyeball the markup." → invoke webapp-testing. with_server.py starts it for you; an unrun page is an unverified page. - "This is a tiny tweak, no design plan needed." → invoke frontend-design. Even a restyle commits a short plan naming what changed, so the change is deliberate not random. - "I already verified earlier this session." → each done-claim is a fresh invocation; re-run webapp-testing against the current build before you say done. ## Additional skills (also available) The full upstream set is vendored in this Flow. The routing above sequences the core lifecycle; these additional skills are available and fire when their trigger matches. See ATTRIBUTION.md for the complete list and license. ### general - `algorithmic-art`: 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. - `brand-guidelines`: 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. - `canvas-design`: 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. - `claude-api`: |- - `doc-coauthoring`: 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. - `internal-comms`: 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.). - `mcp-builder`: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). - `slack-gif-creator`: 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. - `theme-factory`: 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. - `web-artifacts-builder`: 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. ## Attribution - `frontend-design` by **Anthropic** (https://github.com/anthropics/skills), Apache-2.0. - `webapp-testing` by **Anthropic** (https://github.com/anthropics/skills), Apache-2.0. - `skill-creator` by **Anthropic** (https://github.com/anthropics/skills), Apache-2.0. FLOW.md routing by Flowy. Listed for attribution; Anthropic does not endorse Flowy.
FAQ
anthropics-skills is a Claude Code plugin of 17 hand-picked skills with a FLOW.md router. Install it once and the right skill fires as you prompt, with no slash command to remember. It is built for development work. It includes algorithmic-art, brand-guidelines, canvas-design. Free and open source.
- What is anthropics-skills?
- Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks.
- How do I install anthropics-skills?
- Run these in Claude Code: /plugin install flowy@flowy-flows then /flowy:anthropic-design-test-flow. Then prompt normally.
- Does anthropics-skills auto-invoke its skills?
- Yes. It ships a FLOW.md router that Flowy's hook fires, so the matching skill runs as you prompt. You never name a skill.
- Is anthropics-skills free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.