Structure project docs as modular memory + reasoning files so AI agents load only what they need — cutting token usage by 70–96% per query. Grounded in Anthropic, LangChain, and Crawl4AI's production llm.txt research. Implements write/select/compress/isolate context engineering strategies.
Audit installed MCP tool-schema token cost; get consolidation plans and task-profile allow-lists so cold starts stop burning context.
Turns any named decision framework into a 4-part reference card — definition, how-to, real example, limits — with every claim traced to a cited source.
This Skill encodes the current 2026 CSRD/ESRS framework - post-Omnibus scope and thresholds, the ESRS simplification, the 12 standards (ESRS 2 + E1-E5, S1-S4, G1) and the full double materiality method - as a structured workflow. It runs scoping, a double materiality assessment, disclosure mapping, gap analysis, and drafts the sustainability statement. It never invents data and flags where auditor limited assurance is required.
Turn pasted incident notes into a factual postmortem draft with a timeline, evidence ledger, bounded causal analysis, and follow-up plan that leaves unknowns visible.
Compare football players using multi-source public evidence, recent match context and internally derived metrics. Analyze usage, starting consistency, role stability, attacking involvement, availability, schedule load, fixture context and rotation exposure. Generate aligned visual comparison boards and squad dashboards with transparent data confidence — without performance predictions, lineup picks, transfer advice or betting recommendations.
Turn video scripts into structured retention audits — map hook failures, desertion windows, and re-engagement fixes using attention psychology.