Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add daymade/claude-code-skills --skill excalidraw-usegit clone --depth 1 https://github.com/daymade/claude-code-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/daymade/claude-code-skills/excalidraw-use)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/excalidraw-use"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/excalidraw-use/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/daymade/claude-code-skills/excalidraw-use"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/excalidraw-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 97 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 124 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00175 | $0.02193 |
| Opus 5 | $0.00088 | $0.01097 |
| Sonnet 5 | $0.00035 | $0.00439 |
| Haiku 4.5 | $0.00017 | $0.00219 |
Grade A, and why
excalidraw-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excalidraw: images onto a board
Excalidraw is a whiteboard people draw on live. This skill covers the part that is fiddly to do by hand: getting a lot of existing images onto a board, laid out so nobody has to drag them apart afterwards.
It does not generate diagrams from prose. If the request is "draw the
architecture" or "make a flowchart", that is a diagram-generation job — several
tools and skills do it, including a diagram skill in the gstack suite if the
user has it installed.
Which job is this?
| The user says | Go to |
|---|---|
| "put these images on my board", "add the old screenshots to the canvas" | Job 1 — build a pick tray |
| "turn the deck into images", "screenshot every slide" | Job 2 — deck to images, then Job 1 |
| "what's in this file", "how big is this board", "is anything broken" | Job 3 — inspect |
| "draw me a flowchart from this description" | not this skill |
Job 1 — build a pick tray of images
python3 scripts/build_scene.py \
--out tray.excalidraw \
--cols 6 \
--template-from ~/path/to/their-board.excalidraw \
--exclude already-placed.png \
images/*.png
Expected output — if you do not see the verified: line, the file is not usable:
verified: 30 image element(s), hashes match, no overlap
placed 30 image(s), 6 x 5 grid, min gap 600
wrote tray.excalidraw (3.5 MB)
Hand the user the file plus how to get it onto their board. That second half is where this goes wrong: at excalidraw.com, both Open and drag-and-drop replace the entire current scene. Telling someone to "open this file" when they have a live board is telling them to lose it. The additive route is the clipboard — full instructions and the reasoning in references/paste_workflow.md. Read it before you write the hand-off message.
Three decisions worth making deliberately:
--template-fromwhenever they have an existing board. Excalidraw's published JSON schema documents the top-level shape and thefilesmap, but not the image element's own fields (fileId,status,scale,crop), so copying a live element from their board is the only way to be sure the field set matches the build they actually run. Without it a reasonable default is used, which has worked but is one observed field set, not a spec. references/scene_file_format.md has the field-by-field breakdown, keeping what the official docs state separate from what was read off a real file — open it when you need to hand-build or repair a scene rather than let the script write one.--excludeanything already on their board. The check is by image content, not filename, so a renamed copy is still caught. Skipping this is how someone ends up with the same picture twice and has to delete one by hand.- Spacing.
--cellis the longest side each image is scaled to;--pitchis the distance between cell centres. The gap ispitch - cell, and the defaults (800 / 1400 → 600) are deliberately generous. If a user has ever said "don't make me fix the spacing again", raise--pitch, don't lower it.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 184 lines · 175 tokens per session scan A 50345e19af49
excalidraw-use is a skill published in the GitHub repository daymade/claude-code-skills (1,384 stars, last pushed today), licensed MIT. It adds 175 tokens to every session and 2,193 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.