Agent skills for Devin Desktop

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.

Generate a reusable GitHub Actions workflow for automated CI failure detection and fixing with Claude Code.

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 engineers malicious Android APK files using the JADX decompiler

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

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…

Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments.

Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

Use when reviewing SQL migrations, queries, RLS/policy changes, schema modifications, or ORM access patterns for safety, performance, or…

Open a document or plan in crit's interactive TUI for review.

Schema for tracking code review outcomes to enable feedback-driven skill improvement.

Get comprehensive review of a GitLab merge request

Run the Julia code review protocol on Julia scripts.

Review LaTeX documents for common issues, style consistency, typography, cross-references, draft artifacts, and debugging code.

Use when working with crit CLI commands, .crit.json files, addressing review comments, leaving inline code review comments, sharing…

Use when targeting Review of Accounting Studies (RAST) or deciding whether an accounting manuscript fits this venue.