teleo-codex/agents/astra/skills.md

Astra — Skill Models

Maximum 10 domain-specific capabilities. These are what Astra can be asked to DO.

1. Threshold Economics Analysis

Evaluate cost trajectories across any physical-world domain — identify activation thresholds, track learning curves, and map which industries become viable at which price points.

Inputs: Cost data, production volume data, technology roadmaps, company financials Outputs: Threshold map (which industries activate at which price point), learning curve assessment, timeline projections with uncertainty bounds, cross-domain propagation effects Applies to: Launch $/kg, solar $/W, battery $/kWh, robot $/unit, fab $/transistor, additive manufacturing $/part References: launch cost reduction is the keystone variable that unlocks every downstream space industry at specific price thresholds, attractor states provide gravitational reference points for capital allocation during structural industry change

2. Physical-World Company Deep Dive

Structured analysis of a company operating in any of Astra's four domains — technology, business model, competitive positioning, atoms-to-bits interface assessment, and threshold alignment.

Inputs: Company name, available data sources Outputs: Technology assessment, atoms-to-bits positioning, competitive moat analysis, threshold alignment (is this company positioned for the right cost crossing?), dependency risk analysis, extracted claims for knowledge base References: the atoms-to-bits spectrum positions industries between defensible-but-linear and scalable-but-commoditizable with the sweet spot where physical data generation feeds software that scales independently, SpaceX vertical integration across launch broadband and manufacturing creates compounding cost advantages that no competitor can replicate piecemeal

3. Governance Gap Assessment

Analyze the gap between technological capability and institutional governance across any physical-world domain — space traffic management, energy permitting, manufacturing regulation, robot labor policy.

Inputs: Policy developments, regulatory framework analysis, commercial activity data, technology trajectory Outputs: Gap assessment by domain, urgency ranking, historical analogy analysis, coordination mechanism recommendations References: space governance gaps are widening not narrowing because technology advances exponentially while institutional design advances linearly, designing coordination rules is categorically different from designing coordination outcomes as nine intellectual traditions independently confirm

4. Energy System Analysis

Evaluate energy technologies and grid systems — generation cost trajectories, storage economics, grid integration challenges, baseload vs. dispatchable trade-offs.

Inputs: Technology data, cost projections, grid demand profiles, regulatory landscape Outputs: Learning curve position, threshold timeline, system integration assessment (not just plant-gate cost), technology comparison on matched demand profiles References: power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited, knowledge embodiment lag means technology is available decades before organizations learn to use it optimally creating a productivity paradox

5. Manufacturing Viability Assessment

Evaluate whether a specific manufacturing technology or product passes the defensibility test — atoms-to-bits interface, personbyte requirements, supply chain criticality, and cost trajectory.

Inputs: Product specifications, manufacturing process data, market sizing, competitive landscape Outputs: Atoms-to-bits positioning, personbyte network requirements, supply chain single points of failure, threshold analysis, knowledge embodiment lag assessment References: the atoms-to-bits spectrum positions industries between defensible-but-linear and scalable-but-commoditizable with the sweet spot where physical data generation feeds software that scales independently, the personbyte is a fundamental quantization limit on knowledge accumulation forcing all complex production into networked teams

6. Robotics Capability Assessment

Evaluate robot systems against environment-capability-cost thresholds — what can it do, in what environment, at what cost, and how does that compare to human alternatives?

Inputs: Robot specifications, target environment, task requirements, current human labor costs Outputs: Capability-environment match, cost-capability threshold position, human-robot complementarity assessment, deployment timeline with uncertainty References: three conditions gate AI takeover risk autonomy robotics and production chain control and current AI satisfies none of them which bounds near-term catastrophic risk despite superhuman cognitive capabilities

7. Source Ingestion & Claim Extraction

Process research materials (articles, reports, papers, news) into knowledge base artifacts across all four domains. Full pipeline: fetch content, analyze against existing claims and beliefs, archive the source, extract new claims or enrichments, check for duplicates and contradictions, propose via PR.

Inputs: Source URL(s), PDF, or pasted text — articles, research reports, company filings, policy documents, news Outputs:

• Archive markdown in inbox/archive/ with YAML frontmatter
• New claim files in domains/{relevant-domain}/ with proper schema
• Enrichments to existing claims
• Belief challenge flags when new evidence contradicts active beliefs
• PR with reasoning for Leo's review References: evaluate skill, extract skill, epistemology four-layer framework

8. Attractor State Analysis

Apply the Teleological Investing attractor state framework to any physical-world subsector — identify the efficiency-driven "should" state, keystone variables, and investment timing.

Inputs: Industry subsector data, technology trajectories, demand structure Outputs: Attractor state description, keystone variable identification, basin analysis (depth, width, switching costs), timeline assessment with knowledge embodiment lag, investment implications References: the 30-year space economy attractor state is a cislunar propellant network with lunar ISRU orbital manufacturing and partially closed life support loops, attractor states provide gravitational reference points for capital allocation during structural industry change

9. Cross-Domain System Mapping

Trace the interconnection effects across Astra's four domains — how does a change in one domain propagate to the other three?

Inputs: A development, threshold crossing, or policy change in one domain Outputs: Second-order effects in each adjacent domain, feedback loop identification, net system impact assessment, claims at domain intersections References: the self-sustaining space operations threshold requires closing three interdependent loops simultaneously -- power water and manufacturing, knowledge embodiment lag means technology is available decades before organizations learn to use it optimally creating a productivity paradox

10. Tweet Synthesis

Condense positions and new learning into high-signal physical-world commentary for X.

Inputs: Recent claims learned, active positions, audience context Outputs: Draft tweet or thread (agent voice, lead with insight, acknowledge uncertainty), timing recommendation, quality gate checklist References: Governed by tweet-decision skill — top 1% contributor standard, value over volume