AI Agent Skills

Guides the agent to avoid common Go error management mistakes when writing or reviewing Go code. Covers panic usage, error wrapping vs transforming, checking error types…

Guides the agent to avoid common Go standard library mistakes when writing or reviewing Go code. Covers time.Duration misuse, time.After memory leaks, JSON handling pitf…

Guides the agent to write correct and efficient Go string code. Use when writing or reviewing Go code that iterates over strings, concatenates strings, trims strings, co…

Guides the agent to avoid common Go testing mistakes when writing or reviewing test code. Covers test categorization (build tags, env vars, short mode), race detection,…

Detect discrepancies between project specifications and actual code. Use when you suspect specs have drifted from implementation, after a major refactoring, during onboa…

Spec-aware Explore → Plan → Implement for projects that use the vibespec specification system. A thinking partner for exploring ideas and clarifying requirements that gr…

Update existing specification documents after code changes that alter documented behavior, interfaces, or invariants. Use after implementation when you have changed beha…

Enforces a fixed main() cold-launch order — crash-log sink + FlutterError.onError + PlatformDispatcher.onError installed BEFORE any code that can throw, settings/theme r…

Use for writing or updating QEMU reStructuredText documentation, including board and machine docs, system docs, device docs, developer docs, boot command examples, featu…

Use for adapting a QEMU TCG host backend, including optional op support, constraints, register allocation, host code emission, qemu_ld/st, atomics, vectors, and native-v…

Use for building U-Boot artifacts for QEMU firmware boot testing, including defconfig selection, cross compile variables, SPL/TPL, U-Boot proper, FIT or ITB files, BL31…

Stress-tests an already-written game bug fix with adversarial cases selected from the state, timing, identity, lifecycle, persistence, and input surfaces the patch can a…

Assess agent code, changes, traces and evaluations; report findings and prepare missing evals only with confirmed authorization.

Use when a task needs Playwright-backed browser automation from the shell: open or attach to browser sessions, inspect snapshots and element refs, click/type/fill forms,…

Use when named or when the user requests additional context for code review. Review Bitbucket/GitHub PRs or local changes using TWG context, create JSON and Markdown, an…

Use with root `twg` for code search, repositories using an API/package, implementation and reverse-dependency discovery, PR status and reviews, repo contributors, hot ar…