← Search

Allium: formal domain-level specification language for software behavior
AI agents 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit 7f7f008
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: nothing to install…

Allium: formal domain-level specification language for software behavior

Specify observable behavior (entities, rules, surfaces, contracts) in Allium, then drive the loop — spec, tests, code — to convergence

At a glance
What
Specify observable behavior (entities, rules, surfaces, contracts) in Allium, then drive the loop — spec, tests, code — to convergence
Cost
Free
Needs
nothing to install — the skill teaches the Allium specification language; the allium CLI is optional (enables automatic validation of .allium files via hook)
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Allium is a free listing for Juxt's Allium, a formal language for domain-level software behavior. It describes what software does without prescribing how it is built, with entities, fields, enums and state-dependent presence, rules with triggers, surfaces with boundary contracts, and invariants. The skill teaches the full convergence loop of spec, tests and code, to convergence.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 7f7f008

Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: nothing to install — the skill teaches the Allium specification language; the allium CLI is optional (enables automatic validation of .allium files via hook) Install "Allium: formal domain-level specification language for software behavior" for me. It teaches my agent @juxt's Allium language: entities, rules with triggers, surfaces with boundary contracts, contracts and invariants, modular specs with immutable coordinates — plus the convergence loop (gather context → act → verify → repeat) that drives spec, tests and code to agreement, with a routing table for companion skills (elicit, distill, tend, weed, propagate, witness) and strict rules (never weaken a generated test, escalate real ambiguity to the human). MIT-licensed. Repository: https://raw.githubusercontent.com/juxt/allium/7f7f008e0c6b0a17cc81f5cb1c05a4b923cd63c2/skills/allium/SKILL.md Pinned version: install the code at commit 7f7f008e0c6b0a17cc81f5cb1c05a4b923cd63c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "allium". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. give the agent a goal to specify in Allium; install the allium CLI separately for file validation). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 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 7f7f008 · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 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
7f7f008 · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
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.