Lamina Init
Use only when explicitly invoked as lamina-init. Turn an incomplete product idea into usable business context and evidence-grounded personas, asking only high-leverage questions and labeling provisional assumptions for later product-graph design.
Install
$ agentstack add skill-aryaniyaps-lamina-lamina-init ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-aryaniyaps-lamina-lamina-init) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/lamina-init
Product
Capture the minimum context needed to shape the product and persist it in .lamina/business-context.md. Establish mode also writes evidence-grounded .lamina/personas.json using Contract v2.
Modes
- establish (default) — first-time bootstrap
- update — pivot, new market, scope change; merges into existing file and appends changelog
Required reads (do this before anything else)
You are already inside this slash skill. Do not call Skill for lamina-init.
The skill base directory is printed above this body. Resolve paths from that base.
Your first tool calls must be Read on each of these files, in order. Do not Write under .lamina/ until all of them are read.
../lamina-orchestrator/load-protocol.md../lamina-orchestrator/SKILL.md../lamina-orchestrator/workflows/init.md../lamina-orchestrator/artifacts.md../lamina-orchestrator/audit-profiles.yaml../lamina-business-context/SKILL.md../lamina-orchestrator/prompts/outputs/init.md
Then follow workflows/init.md. Load lamina-user-modeling before writing personas.json; load other supporting skills only when the product evidence requires them.
business-context.md must use every canonical ## section heading from lamina-business-context exactly once. Do not combine or rename required sections (for example, keep ## Business goals separate from ## Problem statement, and ## Success metrics separate from narrative success signals). Run the init check when available before reporting success.
Do not invent artifact paths. Only names in artifacts.md.
Do not spawn Agent/Task to “run lamina-init” with a homemade file list.
Guardrail
Writes: .lamina/ only. Repo: read-only. Do not create, edit, delete, format, or refactor application source. See [guardrails](../lamina-core/guardrails.md).
Subagent hints
- Brownfield: [field-research](../lamina-field-research/SKILL.md)
- Interactive: prefer clarifying questions when humans can answer
- Agent-primary: if the brief already has goals, users, scope, and constraints, extract + label assumptions; do not clarify-and-STOP
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aryaniyaps
- Source: aryaniyaps/lamina
- License: MIT
- Homepage: https://lamina.dev
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.