Agent skills for Devin Desktop

Materials selection skill for corrosion resistance based on process conditions and industry standards

ONLY load this skill when the user explicitly types $cortex-run or /cortex-run.

Install Snowflake CLI and Cortex Code CLI.

CosmoSIS cosmological parameter estimation skill for MCMC sampling and likelihood analysis

Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call).

Read accumulated cost-tracking spend + budget config, compute utilization, emit 50/75/90/100% alert ladder

Analyze and optimize AWS costs. Use when reviewing infrastructure for cost savings, estimating costs for new architectures, investigating…

Infrastructure and development cost estimation for technical projects.

Consumer-side wiring for ADR-097 Phase 3 federation_spend events — per-peer rolling windows + suspension-threshold check

Show cost trends across multiple workflow sessions, surfacing expensive operations, spending patterns, and outliers

Cost modeling expertise including infrastructure cost estimation, TCO calculation, build vs buy analysis, pricing model comparison, ROI…

Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns

Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace

Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.

Read every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over time

Update template catalogs and UI prompts after adding new infographic templates (src/templates/*.ts), including SKILL.md template list…

Run a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff.

Multi-perspective analysis methodology for complex decisions.

Shape a task before implementation, then pressure-test the proposed shape with a council made of a Codex subagent on gpt-5.6 with high…

Generate structured alternate timelines for a past decision log entry and write them as a `reflection` entry under your decision wiki's…