Agent skills for VS Code

Create detailed implementation plans with task breakdown

Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync.

John Carmack-level implementation review via rp-cli for current branch changes.

Use this skill whenever you are implementing or fixing an update_* tool in unifi-mcp.

Implements Syncfusion .NET MAUI Segmented Control (SfSegmentedControl).

Imports failing CI checks and jobs as open items in a code-review session record, keeping the run id, job name, conclusion, and log…

Imports existing Grafana dashboards as Go builder code via gcx.

Import posts from external sources into your local feed

Starts from visual examples supplied by the user (a logo, screenshots of their site, existing visuals, an image they like, a moodboard) to…

Audit and modernize Python scripts inside portable skills with PEP 723 dependency metadata, stable uv launchers, standard-library…

Explicitly invoked UI magic-wand orchestrator that discovers available skills, selects a complementary stack, improves an existing…

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained…

Library of in-product message patterns, triggers, and targeting rules.

Use when the user mentions in-app purchase review, IAP audit, StoreKit issues, purchase bugs, transaction problems, or subscription…

Create and maintain GitHub Agentic Workflows (gh-aw) for Prowler.

End-to-end protocol for when outbound open-source contributions generate inbound relationship opportunities.

Generate a single-page incentive-design tear sheet for one public company from Verity (InsiderScore) compensation data.

Orchestrate Inception→Elaboration phase transition with architecture baselining and risk retirement

Guide incident response from detection to post-mortem using SRE principles, severity classification, on-call management, blameless…

Write a structured incident postmortem or post-incident review.

This skill should be used when the user asks to "write a postmortem", "run an incident retro", "do a blameless postmortem", "document this…