yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Full-page web reading for non-academic perspectives — blogs, tech reports, product pages, industry analysis. Spawns a subagent to read pages in isolated context. Hard constraint: at least 30 web pages read in full.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Focus within the user's chosen field(s). Identify specific sub-directions through deep paper and web research, then present ranked candidates. Use after landscape-reconnaissance has identified fields of interest.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Understand the user's background comprehensively — technical stack, project experience, research experience, publications, research directions. Allows user to express interest beyond their resume. Execute once only, never re-run.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Cross-reference the GoalTree against ActorProfile (capabilities), ObstacleReport (known barriers), and timeline (deadline feasibility). Identify infeasible paths and suggest OR alternatives.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Self-review the North Star + ResearchBrief for completeness, consistency, and clarity before presenting to user. If issues found, return to specific tactic/SOP for targeted fix. If passes, present final output to user for confirmation.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Express the user's chosen research direction as a formal goal statement in the format: 'Achieve [what], such that [effect], under [constraints]'. Confirm with user before proceeding to decomposition.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Propose 3-8 candidate research fields based on the full ActorProfile. When user wants to explore beyond their current stack, use other ActorProfile signals (intentionality, boundary) to determine exploration space. Free exploration within the boundary.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Aggregate all accumulated context from the crystallization process into a structured ResearchBrief document. This is the final output artifact alongside the North Star — a comprehensive requirement context document for downstream research strategies.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Structure the user's chosen direction into a formal goal tree using KAOS-style AND/OR decomposition. Validate feasibility against ActorProfile and ObstacleReport. Use after obstacle-analysis confirms the direction is viable.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Minimal crystallization strategy for users who already have a specific research topic or problem (e.g., "I want to improve CoT faithfulness in LLMs") and need structuring into a formal North Star. Heavily simplifies or skips exploration tactics, focusing on obstacle analysis, goal decomposition, and synthesis. Use…
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Enumerate barriers to pursuing the chosen research direction — knowledge barriers, resource barriers, capability barriers, competition barriers. May optionally use search tools to discover obstacles the user hasn't mentioned.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Broad, shallow exploration of candidate research fields. Understand what's out there before narrowing. Use when the user needs to discover which fields are available to them — especially in cold-start and warm-start scenarios.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Evaluate each candidate research field on maturity, competition, entry barrier, and publication opportunity. Synthesizes broad-web-search results into a structured FieldPanorama. Must consider both niche approaches AND direct frontal competition in hot fields.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Goal-Driven Requirement Refinement Engine for Research. Crystallize a user's fuzzy research intent into a North Star statement and structured ResearchBrief through adaptive dialogue and on-demand investigation.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Converge all accumulated context into a crystallized North Star statement and structured ResearchBrief. Performs self-review before presenting to user. Use as the final tactic in any start mode — this is where everything comes together.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Identify what blocks the user from pursuing their chosen direction, assess severity, propose mitigations with search-validated evidence, and get user acceptance. Use after direction-narrowing has identified a specific direction.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Present the field panorama to the user and gather their preferences — which fields interest them, which they reject, and why. A dialogue SOP that bridges landscape-synthesis output to user decision.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Analyze sub-directions within the user's chosen field and present ranked candidates. Combines sub-direction identification, skill-gap matching, and presentation into a single SOP. Depth scales by start mode: cold-start shows broad sub-directions, warm-start shows specific sub-problems, hot-start shows granular…
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Propose concrete mitigation strategies for severe obstacles. MUST use search tools to validate that proposed mitigations are realistic — no armchair theorizing. Each mitigation must have evidence of feasibility.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Quality check on leaf nodes of the GoalTree. Verify each leaf is specific enough, actionable, and that the set of leaves fully covers the top goal. Flag issues for further decomposition.
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Simplified crystallization strategy for users who have a general research direction (e.g., "I'm interested in LLM reasoning") but lack specificity. Simplifies actor profiling and landscape reconnaissance, then proceeds through direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use…
Skill Claude CodeCodex
Compute Risk Priority Number (RPN = S x O x D), classify failure modes into H/M/L action priority per AIAG-VDA tables.
Skill Claude CodeCodex
Strategy: Dialectic engine retuned for truth-seeking, not survival. A defender steelmans a claim into its MOST falsifiable form, a critic attacks to refute it, a judge classifies the exchange into BROKEN/CORROBORATED/UNFALSIFIABLE — the judge does NOT pick a winner or score persuasiveness. Methods: Irving debate…
Skill Claude CodeCodex
Strategy: Progressive pressure escalation — starts with surface-level challenges and escalates to fundamental assumption attacks based on defender confidence decay.