← Search

Archify Diagram Skill for Muse
Design 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit ba701d2
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: Node.js 18+ (to run the bundled archify CLI that…

Archify Diagram Skill for Muse

Interactive architecture diagrams that validate themselves

At a glance
What
Interactive architecture diagrams that validate themselves
Cost
Free
Needs
Node.js 18+ (to run the bundled archify CLI that ships with the skill package); a working directory where artifacts will be generated; your system description in plain language, pasted Mermaid input, a repository to trace, or a question to turn into an explainer page. No API keys.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Archify Diagram Skill for Muse is a free Muse skill that creates interactive architecture diagrams that validate themselves, turning plain-language system descriptions or pasted Mermaid flowcharts, sequence diagrams and state diagrams into diagrams you can explore, with checks that catch inconsistencies instead of letting a pretty picture lie.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit ba701d2

Before you start: tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead. Prerequisites: Node.js 18+ (to run the bundled archify CLI that ships with the skill package); a working directory where artifacts will be generated; your system description in plain language, pasted Mermaid input, a repository to trace, or a question to turn into an explainer page. No API keys. Install "Archify" for me. It turns plain-language system descriptions or pasted Mermaid diagrams into validated, explorable diagrams as standalone HTML with inline SVG — ten types: architecture, workflow, sequence, data-flow, lifecycle/state, entity-relationship, class/interface, tree, timeline, and execution waterfall — and it can also turn an answer into a one-page explainer: a standalone page with the conclusion first, structured panels, and native diagrams and charts inside. Dark/light themes, live motion in the viewer, PNG/JPEG/WebP/SVG/WebM export, and a gated finalize pipeline with real-browser checks for native diagrams. Source: https://raw.githubusercontent.com/tt-a1i/archify/ba701d20a55ed6f139484d9ead7ff45671fe40eb/archify/SKILL.md (the skill is the whole archify/ folder at that commit — SKILL.md and every subfolder) Pinned version: install the code at commit ba701d20a55ed6f139484d9ead7ff45671fe40eb exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 19, 2026: Skill Harbor regenerated this install prompt from the current upstream file. What changed since the version the previous prompt described: upstream is now version 3.2 — a new artifact mode, explainer, alongside the ten native diagram types. Routing comes first (a new “Choose the artifact” step): draw or visualize a system, flow, schema or history and it is a native diagram; use explainer only when the answer is asked for as a page, an explainer or something to share, unless a rules line in context opts in — [archify explainer: proactive] also makes pages unasked for explanations, comparisons, trade-offs, decisions, diagnoses, reviews or plans that need a table, steps or several sections, [archify explainer: always-on] adds a compact page of at most four panels to every reply that reaches a conclusion, and [archify explainer: on-demand] is request-only. An explainer is written as candidate.archify.md following references/explainer-authoring.md — conclusion first, up to four opening reasons, then panels with native diagrams, tables, steps and charts — and delivered with “finalize explainer” (validation, atomic delivery and artifact checks; it does not launch a browser), with panel patch for a local revision of one panel. The skill folder now also holds an explainer/ folder and references/explainer-authoring.md, so the whole folder must be installed, not SKILL.md alone. Two things that happen in use are disclosed below before they happen: the bounded update check inside finalize/deliver, and the one-line mode offer after an explainer made on request, which writes to your global rules file only if you accept it. 1. Download the whole archify/ folder at the pinned commit — SKILL.md and all its subfolders (schemas/, examples/, references/, bin/, renderers/, assets/, scripts/, recipes/, explainer/, brand-marks/, delta/, locales/, migrations/, and the rest) — into a temporary folder. 2. Compare SKILL.md with the fingerprint from Skill Harbor's review of 2026-10-19: [FINGERPRINTS] - SKILL.md: SHA-256 93434ad579983f4cff639c2b7230c311e0785cc48a25b66b1498e1802be7de91 (18870 bytes) If it does not match, it changed since the review: do not install it yet — tell me what you found and let me decide. 3. Read SKILL.md and tell me in plain words: what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Nothing is sent anywhere during installation itself. Confirm these points from the files before I decide: - In use, the agent runs the bundled CLI locally with Node: “finalize <type>” for a native diagram (its passing receipt proves validate, deliver, strict check and real-browser browser-check passed, with bounded repair reruns if a gate fails) and “finalize explainer” for a page. Each artifact request gets its own .archify/<type>-<slug>-<YYYYMMDD-HHMMSS>/ folder in the working directory — candidate.json for native diagrams, candidate.archify.md for explainers. - The one network call in ordinary use, disclosed here before it happens: finalize and standalone deliver include a bounded update check that fetches the update manifest at https://tt-a1i.github.io/archify/skill-updates/archify/stable.json. It never downloads, installs or executes an update; at most it adds one compact update notice to the final reply, and it can be snoozed or ignored only when I explicitly ask. Brand marks are queried only for a mark I explicitly request. - After an explainer made on request, when no [archify explainer: ...] line is in context, the reply may end with a one-line offer of the proactive mode, once per conversation. Only if I accept does the agent add an [archify explainer: ...] line to my agent's global rules file (such as ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md or ~/.config/devin/AGENTS.md) and name the file; the skill never writes that line, and never installs or updates itself, on its own initiative. - No API keys and no account are needed. For a code-backed artifact the skill reads repository evidence locally; when shell access is unavailable, native diagrams fall back to hand-placed SVG in assets/template.html, while explainers cannot be delivered as HTML — the skill must report that limitation and answer in text instead, without claiming HTML delivery. 4. When I say yes, copy the whole archify/ folder's contents into my skills folder, in a folder named "archify", keeping every subfolder as it is. 5. Check the copy with no network calls (valid frontmatter, files in place) and tell me what was installed, where, and what is left for me to do (for example: have Node.js 18+ available and point the skill at the bundled bin/archify.mjs CLI). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: only touch the temporary folder and the install target. If something seems off, stop and ask me. Never print or paste a secret value.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit ba701d2 · 2026-10-19
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : registry.npmjs.org
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
ba701d2 · 2026-10-19
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.