Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests, security/data-safety issues, and other behavior-changing defects.
Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-local` skill + script, and the installed driver skill. Use when someone says "set up verification", "make this repo verifiable", "scaffold a verify skill", "set up the verifier".
Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want system-level tests — "set up e2e", "add end-to-end tests", "scaffold a test gate".
E2E testing workflow for the RDoc live-reload server (rdoc --server)
Turn minified, bundled, or transpiled JavaScript back into readable modules. Use when you encounter unreadable production JS — a webpack/esbuild/Rollup bundle, a minified vendor script, Babel/TypeScript/SWC-transpiled output, or a single mangled .js file — and need to read, audit, debug it, or recover a best-effort Vue 3 SFC artifact from generated render code. Not a deobfuscator (see webcrack for obfuscator.io-style protection).
INTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes this skill BEFORE any non-trivial edit AND AFTER multi-file changes, to enforce CLAUDE.md rules (functions <=25 lines, classes <=300, 1-file-1-responsibility, module boundaries, forbidden patterns). Auto-trigger on: edits >50 lines, new files, refactors, module-crossing changes, plugin/SDK touches, performance-sensitive paths (HexEditor buffer, CodeEditor render, viewport, drag/scroll), Roslyn diagnostics work. Skip on: doc-only, resx-only, comment fixes, single-line bug fixes, single-file <20-line edits.
INTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes on two scopes: (1) PARITY — after editing any *.resx (base or satellite), verifies the 28-language satellite parity (missing/orphan keys, placeholder drift, untranslated). (2) SOURCE — after editing *.xaml or *.cs under App/, Editors/, Plugins/, Core/, Controls/, advisory checks for: DynamicResource on loc keys (must be StaticResource), hardcoded user-visible string literals, IdeMessageBox.Show literals, legacy MessageBox.Show usage (ADR-009), and missing LocalizedResourceDictionary wiring (ADR-005). All SOURCE findings are warn-only. Distinct from xaml-guard (which only checks Designer.cs parity for the base resx). Skip on: Themes/, ColorPicker, Designer.cs/g.cs, Tests/, Samples/, pure structural XAML edits.
INTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing any *.cs or *.csproj that belongs to one of the 13 packages published on nuget.org by abbaye (WpfHexEditor.Core.ByteProvider, .BinaryAnalysis, WPFHexaEditor, WpfCodeEditor, WpfDocking, WpfColorPicker, WpfTerminal, whfmt.Analysis/.Backfill/.CodeGen/.Fuzz/.Validate/.FileFormatCatalog). Protects the standalone-mode contract when IDE features are added: detects IDE-only references leaking into a NuGet package, TFM drift, UseWPF leak on core-xplat packages, WPF/WinForms usings in core-xplat, and public-API regressions vs git HEAD (api-removed, api-renamed). Extending the API is always allowed; removing/renaming is not. Skip on files outside protected packages, Tests/, Samples/, *.Designer.cs, *.g.cs.
INTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing C# in render/layout/scroll hot paths (HexEditor/, CodeEditor/Rendering*, *Viewport*, *GlyphRun*, *Renderer*, *ScrollHandler*, OnRender, MeasureOverride, ArrangeOverride) to detect allocations and patterns that cause jank or GC pressure. Skip on: tests, mocks, designer files, non-render code in non-hot directories.
INTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after creating new C# files OR adding >50 lines to existing classes (especially under Services/, Managers/, *Manager.cs, *Service.cs). Heuristics that CORRELATE with SOLID violations: SRP (mixed UI+IO concerns, classes >300 lines + >15 public methods), OCP (massive switch statements >10 cases), DIP (newing services instead of injecting, static singleton mutation), ISP (fat interfaces, NotImplementedException stubs). LSP is out of scope (impossible to detect mechanically). All findings are ADVISORY (warn-only). Skip on: Tests/, Samples/, *.Designer.cs, *.g.cs.