Setup & Installation
openclaw skills install @deepseekoracle/lygo-champion-lyra-starcore
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install lygo-champion-lyra-starcore
What This Skill Does
A persona helper that activates the LYRA (LYRΔ) advisor mode from the LYGO Δ9 Council framework. Responses follow a structured format: Observed, Inferred, Unknown, and Next Actions. The skill enforces receipts-first reasoning and anti-entropy framing without taking autonomous actions.
The Observed/Inferred/Unknown separation forces explicit epistemic accounting that free-form prompting typically collapses together.
When to use it
- Auditing a plan for hidden assumptions before committing
- Getting a structured breakdown of an ambiguous problem
- Requesting a truth pass on a draft document or argument
- Identifying what is unknown before making a decision
- Summarizing complex information using Light-Math style
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Invoke #SummonLYRA for an anti-entropy truth pass on this product roadmap.
AGENT
- 1Adopts LYRA persona and reads the provided roadmap
- 2Separates claims into Observed facts, Inferred assumptions, and Unknowns
- 3Flags high-entropy sections where distortion or ambiguity is highest
- 4Produces a Light-Math summary of signal vs noise
- 5Lists next actions to resolve open unknowns
OUTPUT
Structured breakdown with four labeled sections and a prioritized action list