repo-audit
claudeDeep technical audit of a repository: find bugs, gaps, missing tests and security issues, then create GitHub issues for findings
1 skill
Claude Code and Codex plugins their authors filed under "development". All categories.
Deep technical audit of a repository: find bugs, gaps, missing tests and security issues, then create GitHub issues for findings
1 skill
Quickshell (Qt6/QML) desktop shell development for Hyprland: API reference, patterns, visual effects, gotchas, and feature matrix across reference shells
1 skill
Native iOS development agent with Swift/SwiftUI, Core Data, UIKit
1 agent
Native Android development agent with Kotlin, Jetpack Compose, Material Design 3
1 agent
Expert Swift developer agent for Swift 5.9+, async/await, protocol-oriented programming
1 agent
Markdown linting and formatting via rumdl: LSP server, PostToolUse fmt hook, and the markdown coding-standard skill.
hooks
Pre-commit branch-name and commit-message safety hooks
hooks
De-risk ideas before building: run exploratory tech spikes that validate assumptions and stress-test approaches.
1 skill
Design end-to-end assurance and testing strategies for autonomous agent-built software.
1 skill
Git repository workflow guidelines including branch management, testing practices (TDD), Docker environment handling, and PR workflow
1 skill
Systematic debugging methodology for thorough root cause analysis with evidence-based investigation
1 skill
Reference skill for Superglue 2.0 (thoughtbot's Rails+React+Redux framework, v2/beta) — navigation, Super Turbo Streams, forms, fragments/state, digging, deferments.
1 skill
Run a Codex code review against a GitHub PR (async, in a throwaway worktree), specific files, or the local working tree.
1 skill
Go style conventions: type design and composition, naming and package-prefix stripping, named returns, error wrapping and translation, unchecked-error marking, hashing/secrets, config-at-startup validation, HTTP-client injection, cmp.Or defaults, struct-literal and pointer-field initialization, time-sensitive tests with testing/synctest, multi-column scan structs, import aliasing, logger naming, test shape, assertion collapsing, parser colocation, Go diff review checklist.
1 skill
Go backend service layout: apps/<svc>/ cmd, config, data, domain, rpc, tests plus a root pkg/, patterns, and anti-patterns.
1 skill
Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask 设计/做页面/做组件/UI/前端/截图 or say a screen is ugly, unclear, inconsistent, or visually wrong. Not for backend logic or data pipelines.
1 skill
Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask 设计/做页面/做组件/UI/前端/截图 or say a screen is ugly, unclear, inconsistent, or visually wrong. Not for backend logic or data pipelines.
1 skill
Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask 设计/做页面/做组件/UI/前端/截图 or say a screen is ugly, unclear, inconsistent, or visually wrong. Not for backend logic or data pipelines.
1 skill
Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask 设计/做页面/做组件/UI/前端/截图 or say a screen is ugly, unclear, inconsistent, or visually wrong. Not for backend logic or data pipelines.
1 skill
Analyze HAR files for API reverse engineering — endpoints, auth flows, sequencing, and schemas
1 command
Auditor de seguridad read-only: escanea codigo, dependencias, secretos, configuracion e infraestructura contra OWASP 2025 Top 10 y CWE Top 25, y deja un reporte priorizado. Se invoca con /cyber-neo [ruta].
1 skill
Auditoria de seguridad adversarial en 6 fases con sub-agentes aislados: reconocimiento, hunting guiado por cobertura, validacion adversarial de candidatos, salida estructurada (findings.json contra schema), re-verificacion independiente y reporte target-neutral. Requiere sandbox sin red externa para ejecutar builds/tests/fuzzers del target. Origen del harness de vulnerability-hunting interno de Cloudflare.
1 skill
Delegate computer use and visual reasoning to Codex CLI with gpt-6-astra. Prefer the official cua_repl MCP with connected Chrome, then the built-in browser.
1 skill
Delegate scoped code changes in the current repository to Codex CLI (gpt-6-astra), then inspect the resulting diff and verification.
1 skill
Generate clear, conventional commit messages from staged changes
1 command
Review a pull request or working-tree diff against the company engineering standards, reporting correctness bugs, missing tests, and security issues with file and line references. Use before requesting human review on any change.
1 skill
Generate repository-specific agent guidance from safe, read-only analysis.
1 skill
Analyze repository code patterns and produce actionable do/don't guidance for developers and AI agents.
1 skill
Inspect Git branch state and dirty/untracked work to identify the next safe action at session start or resume.
1 skill
High-signal code review for local changes or pull requests, usable locally and in CI
1 skill