db-guard
claudeTwo-layer guard against unauthorized DROP TABLE, TRUNCATE, DROP DATABASE, DROP SCHEMA, and DROP COLUMN.
1 skill
Claude Code and Codex plugins their authors filed under "development". All categories.
Two-layer guard against unauthorized DROP TABLE, TRUNCATE, DROP DATABASE, DROP SCHEMA, and DROP COLUMN.
1 skill
iOS 개발 워크플로 - Xcode 27 MCP 브리지로 빌드·테스트·디버그, Device Hub(SimSlim)·iPhone Mirroring으로 검증, asc CLI로 App Store 배포
1 skill
Capture browser network requests through Chrome DevTools Protocol when a web UI is the only reliable API reference.
1 skill
Perform post-merge git cleanup by returning to main/master, pulling latest, deleting merged branches, pruning remotes, and verifying a clean state.
1 skill
Control Microsoft Edge over Chrome DevTools Protocol, either on a dedicated debug profile or on the real signed-in profile via Edge's in-browser remote-debugging opt-in.
1 skill
Tidy the files a PR or branch changed against its base, or all tracked source on the default branch or with whole-repo: autonomous coach-first Stage-B refactor by default (may change behavior), then SOLID tidy with no further behavior change. Opt out with solid-only / no-behavior-change / prune-comments-only. Tests document behavior, comments earn their place
1 skill
Re-pin Cursor user GitHub marketplaces llm-wiki and karlorz-agent-skills, then reinstall KEEP plugins.
1 skill
Structured bug audit covering functional correctness, UX quality, test coverage gaps, and customer-surfaced classification
1 skill
Write complete feature specs with acceptance criteria, task breakdown, and Cypress test plan — nothing ships without all three
1 skill
Brand-compliant Recharts chart components — chart type guide, color tokens, tooltip patterns, mobile responsiveness
1 skill
Build, run, view, and interact with Android apps on an emulator or connected device. Use when the user asks to build, run, install, screenshot, tap, scroll, swipe, type, inspect, or debug an Android emulator/device.
1 skill
Collect a batch of bugs / issues / changes from the user, then categorize them and dispatch parallel subagents — one per category — each working in its own git worktree to fix that category's items. Use when the user invokes `/msilvis:bug-bash` or says "bug bash", "let's bug bash", "queue up some fixes", or otherwise signals they want to dump a list of issues and have them worked in parallel.
1 skill
Diagnose and fix failing CircleCI builds. Use when the user asks to investigate CI failures, fix a broken build, or debug CircleCI pipeline issues.
1 skill
Makes Claude fluent in Every Layout's composable CSS primitives — picks the right primitive for the job and writes it in your project's own stack (Tailwind, CSS-in-JS, or vanilla CSS).
1 skill
Build or migrate a website into Ploy's Astro runtime and sync it with the Ploy CLI.
1 skill
Audits a running Flutter app at the user-journey level, merging static, runtime and visual evidence into a heuristic UX report scored against the journey's goal.
1 skill
A registry-driven hook dispatcher for Claude Code — composable deterministic harness via JSON-declared subprocess rules.
hooks
Leases each Android device and emulator to one agent at a time, so concurrent agents cannot install over each other's build or drive the same UI.
hooks
Busca en el TOTVS Developer Network, lee sus paginas como markdown con la fecha de ultima edicion, recorre arboles, descarga adjuntos y mide la fidelidad del markdown.
1 skill
Create, inspect, compile, and validate complex legacy iReport and JasperReports 2.x JRXML reports without introducing incompatible modern syntax.
1 skill
Skill authoring guidance for writing and validating agent skills.
1 skill
Coding practices that apply on any host: design and clarity over expediency, security first, comment discipline, logging, and verifying what you don't know. No hooks, no forge.
1 skill
Multi-model committee: your agent chairs up to 4 heterogeneous LLM members that blind-review, decide, and brainstorm in parallel — independent generation → structured interaction → evidence-driven convergence.
1 skill
Human-on-the-Loop (HOTL) delivery workflow design and application, plus CTO-level decision support for AI-native engineering operations: repository takeover, staged quality gates, CI/CD and eval gates, autonomy promotion, and J-SOX/audit readiness.
1 skill
Skills for developing CAN & CANopen Studio: the Rust canopen-core engine, the Python Tkinter studio, the Slint front end and the CLI.
1 skill
Turns Claude into a Signaturit integration expert: describe a business workflow in plain language and it designs and implements the correct Signaturit API integration, with production-safe defaults for auth, retries, idempotency, and webhooks.
1 skill
CSV preflight validation and batch CSV quality checks that fail fast before pipeline runs.
1 skill
Optimize decision-model requests from reviewed labeled examples and integrate decide() code.
1 MCP server
Operation-state authoring skill for package:flutter_operations/flutter_operations.dart. Use for AsyncOperation execution, host and widget mixins, state-manager integrations, cached refreshes, commands, transitions, and exhaustive rendering.
1 skill
AI-powered code review and suggestions
1 command