allium
Allium behavioral specs integrated with /core:agent-loop. Use when attaching a formal spec to an epic, propagating tests from a spec before TDD, or weed-checking spec/code divergence after CI passes.
What this skill does
# Allium
Opinionated integration between [juxt/allium](https://github.com/juxt/allium) and the `/core:agent-loop` workflow. Allium captures observable behavior in `.allium` files using `entity`, `rule`, and `config` blocks — implementation-agnostic, co-located with code.
## When to Use
- Epic author is attaching a formal behavioral spec to a new epic
- Worker needs to seed failing TDD tests from a spec before implementing
- Validator has passed CI and needs to confirm the code matches the spec semantically
- Refactor epic requires a behavioral baseline before decomposition
## Prerequisites
Upstream Allium Claude plugin must be installed separately:
```
/plugin install allium@juxt
```
The CLI (`allium-tools` binary) installs via mise — see `references/installation.md`.
## Spec Location Convention
Recommended convention for projects adopting this skill: specs live at `docs/specs/<epic-slug>.allium` with shared specs in `docs/specs/shared/`. A project-root `allium.config.json` declares `specPaths: ["docs/specs"]` so the CLI and LSP resolve them. Copy `templates/allium.config.json` into the project root to bootstrap this layout.
## Integration Points by Tier
See `references/agent-loop-integration.md` for the complete 6-tier breakdown. Summary:
| Tier | Allium action |
|---|---|
| Epic Author | Run `/allium:elicit` or copy a template from `templates/`; set `spec:` field in epic markdown |
| Team Leader | If refactor label and no spec: run `/allium:distill` for baseline |
| Worker | If spec attached: run `/allium:propagate` to seed failing tests BEFORE implementing |
| Validator | After CI passes: run `/allium:weed`; divergences route to fix-agent same as CI failures |
## Spec Syntax (v3)
```allium
entity Order {
status: pending | confirmed | shipped | delivered | cancelled
tracking_number: String when status = shipped | delivered
transitions status {
pending -> confirmed
confirmed -> shipped
terminal: delivered, cancelled
}
invariant NonNegativeTotal { this.total >= 0 }
}
rule ShipOrder {
when: ShipOrder(order, tracking)
requires: order.status = confirmed
ensures:
order.status = shipped
order.tracking_number = tracking
}
```
Key constructs:
- `entity` — domain object with typed fields, conditional attributes (`when`), state transitions, and invariants
- `rule` — behavioral rule with `when` (trigger), `requires` (preconditions), `ensures` (postconditions)
- `config` — project-level settings (thresholds, retry counts, timeout values)
- `use` — import another spec: `use "./shared/oauth.allium" as oauth`
## Templates
Copy-pasteable specs in `templates/`:
- `oauth-pkce-flow.allium` — OAuth2 PKCE flow matching the agent-loop epic-authoring example
- `circuit-breaker.allium` — infrastructure contract with `entity` + `config` + `rule`
- `runex-workflow.allium` — spec for a Runex workflow step
- `epic-with-spec.md` — VantageEx epic showing the `spec:` field in use
See `references/epic-spec-template.md` for a guided walkthrough.
## Anti-Fabrication
All claims about spec content must derive from reading actual `.allium` files with Read tool. Never assert that a spec covers a behavior without verifying the `ensures` or `invariant` blocks. See `/core:anti-fabrication`.
## References
- `references/installation.md` — mise backend details and upstream plugin install
- `references/agent-loop-integration.md` — 6-tier integration procedure
- `references/epic-spec-template.md` — template walkthrough
- `references/distilling-legacy-code.md` — `/allium:distill` procedure for existing modules
Related in Cloud & DevOps
appbuilder-action-scaffolder
IncludedCreate, implement, deploy, and debug Adobe Runtime actions with consistent layout, validation, and error handling. Use this skill whenever the user needs to add actions to an App Builder project, understand action structure (params, response format, web/raw actions), configure actions in the manifest, use App Builder SDKs (State, Files, Events, database), deploy and invoke actions via CLI, debug action issues, or implement patterns such as webhook receivers, custom event providers, journaling consumers, large payload redirects, action sequence pipelines, and Asset Compute workers. Also trigger when users mention serverless functions in Adobe context, action logging, IMS authentication for actions, or cron-style scheduled actions.
orchestrating-datacloud
IncludedSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. Use this skill when the user needs a multi-step Data Cloud pipeline, cross-phase troubleshooting, or data space and data kit management. TRIGGER when: user needs a multi-step Data Cloud pipeline, asks to set up or troubleshoot Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase sf data360 workflow. DO NOT TRIGGER when: work is isolated to a single phase (use the matching phase-specific skill), the task is STDM/session tracing/parquet telemetry (use observing-agentforce), standard CRM SOQL (use querying-soql), or Apex implementation (use generating-apex).
github-project-automation
IncludedAutomate GitHub repository setup with CI/CD workflows, issue templates, Dependabot, and CodeQL security scanning. Includes 12 production-tested workflows and prevents 18 errors: YAML syntax, action pinning, and configuration. Use when: setting up GitHub Actions CI/CD, creating issue/PR templates, enabling Dependabot or CodeQL scanning, deploying to Cloudflare Workers, implementing matrix testing, or troubleshooting YAML indentation, action version pinning, secrets syntax, runner versions, or CodeQL configuration. Keywords: github actions, github workflow, ci/cd, issue templates, pull request templates, dependabot, codeql, security scanning, yaml syntax, github automation, repository setup, workflow templates, github actions matrix, secrets management, branch protection, codeowners, github projects, continuous integration, continuous deployment, workflow syntax error, action version pinning, runner version, github context, yaml indentation error
sf-datacloud
IncludedSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. TRIGGER when: user needs a multi-step Data Cloud pipeline, asks to set up or troubleshoot Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase `sf data360` workflow. DO NOT TRIGGER when: work is isolated to a single phase (use the matching sf-datacloud-* skill), the task is STDM/session tracing/parquet telemetry (use sf-ai-agentforce-observability), standard CRM SOQL (use sf-soql), or Apex implementation (use sf-apex).
fabric-cli
IncludedUse this skill for Fabric.so CLI workflows with the `fabric` terminal command: diagnose/install/login, search or browse a Fabric library, save notes/links/files, create folders, ask the Fabric AI assistant, manage tasks/workspaces, generate shell completion, check subscription usage, produce JSON output, and use Fabric as persistent agent memory. Do not use for Microsoft Fabric/Azure/Power BI `fab`, Daniel Miessler's Fabric framework, Python Fabric SSH, Fabric.js, or textile/fashion fabric.
lark
IncludedLark/Feishu CLI skills: lark-cli operations for docs, markdown, sheets, base, calendar, im, mail, task, okr, drive, wiki, slides, whiteboard, apps, approval, attendance, contact, vc, minutes, event. Use when the user needs to operate Lark/Feishu resources via lark-cli, send messages, manage documents, spreadsheets, calendars, tasks, OKRs, deploy web pages, or any Feishu/Lark workspace operations.