Agent skills for DeepSeek Harness

Retell AI cost tuning \u2014 AI voice agent and phone call automation.\n\

Retell AI local dev loop \u2014 AI voice agent and phone call automation.\n\

Retell AI observability \u2014 AI voice agent and phone call automation.\n\

Retell AI performance tuning \u2014 AI voice agent and phone call automation.\n\

Structure a retention analysis, churn investigation, or engagement deep-dive for any product team.

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid…

A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close.

Orchestrate systematic retrospective cycle with structured feedback collection, improvement tracking, and action item management

Retrospective data collection. Gathers observation, impact, and evidence for retrospective analysis. Invoked by game-retrospective agent…

Build quick IRR/MOIC sensitivity tables for PE deal evaluation.

Codified expertise for returns authorization, receipt and inspection, disposition decisions, refund processing, fraud detection, and warranty claims management. Informed by returns operations…

Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask.

Use this skill whenever a reveal.js deck needs live or highlighted code, staged code walkthroughs, math/equation rendering, interactive or…

Export a Reveal.js HTML presentation to a pixel-perfect PDF using Chrome CDP (no Puppeteer/Playwright dependency).

Analyzes pipeline coverage, tracks forecast accuracy with MAPE, and calculates GTM efficiency metrics for SaaS revenue optimization

Reverse engineer web APIs by capturing browser traffic (HAR files) and generating production-ready Python API clients.

Transforms existing source code into structured technical specifications, Gherkin BDD scenarios, and test coverage reports.

Reverse engineers Rust-compiled malware using IDA Pro and Ghidra, covering

Git-aware logical undo at track, phase, or task level with confirmation gates

All quality reviews — routes to appropriate critics based on target file type and flags.

Review a design specification in Specs/ against the actual codebase to find inaccuracies, potential issues, or things that need correction…