Agent skills for Windsurf (legacy)

Use when assembling the data and code deposit for an accepted empirical The Review of Economic Studies (REStud) manuscript, writing the…

Use when building, sharpening, or stress-testing the theoretical model in a The Review of Economic Studies (REStud) manuscript — whether a…

Use when deciding which restud-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a…

Prepare a grant resubmission or revision after review — decode the summary statement/reviews, plan a point-by-point response, write the…

Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib…

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing.

Transform weak resume bullets into achievement-focused statements with metrics and impact

Resume disconnected, stale, or out-of-context Codex work from available local evidence.

Use when preparing resume content and source-level interview follow-ups from an unfamiliar or open-source project under a limited study…

Ensure ATS-friendly formatting and create clean scannable layouts

Analyzes candidate resumes and generates structured, role-matched technical interview question lists with specific evaluation criteria.

Find opportunities to add metrics and estimate numbers when exact data unavailable

Customize resume for specific job postings while maintaining truthfulness

Turn a job description into a tailored, accurate, one-page LaTeX resume drawn from the user's own knowledge base.

Track different resume versions, maintain master resume, manage tailored versions

Automate Retellai tasks via Rube MCP (Composio).

Reduces churn through cancel flows, dunning, and win-back.

When the user has to produce the recurring CS / retention report that leadership actually reads — monthly, quarterly, or for an operating…

Document ingestion, parsing, chunking, embeddings, vector stores,

Agent retrieval policy for intelligent memory search.

Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating.