Skill UI

Vibers provides a human-in-the-loop code review workflow for AI-generated GitHub projects. Users push code, and the service reviews it against a specification, checks for security issues, and submits a pull request with suggested fixes. It supports various languages and requires adding a collaborator and configuring a GitHub Action to trigger the review process.

WGM is a robust, agentic methodology designed to transform vague or rough requirements into working, validated software. It enforces a disciplined workflow across six stages: deep alignment (Grill), structured planning, deterministic iterative building (Loop), mandatory holdout-scenario judging, and final documentation audits. It ensures that the resulting code converges against rigorously tested acceptance criteria rather than relying on single-pass generation.

Standardizes how coding agents snapshot active state before /clear, /compact, or task switches. Produces a verified handoff document covering goals, decisions, files touched, open loops with owners, and a single next action.

Guides investigation of broad process mining questions, observed patterns, or competing explanations across analytical perspectives, using an evidence loop to test claims and route to specialists.

Manage a file-based epic→story→sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira/Linear/Taiga but needs structured delivery tracking.

Query Microsoft Fabric and Power BI semantic models with DAX to build trustworthy dashboards: reuse governed measures, design KPIs with target and trend, wire crossfiltering, and test queries with an execute-inspect-fix loop.

Capture a full DevTools-protocol trace of any browser automation run — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets for debugging, auditing, and agent feedback loops.

A disciplined approach for diagnosing hard bugs and performance regressions. This skill guides users to build tight feedback loops, reproduce issues, and minimize scenarios before hypothesizing. It emphasizes redacting secrets, creating deterministic tests, and avoiding premature assumptions. Use when debugging complex failures or performance issues in software development.

Build, debug, test, and package playable 2D games in Go using Ebitengine, covering game loops, input, rendering, audio, scenes, gameplay tests, and desktop, browser, or mobile builds.

Starts a recurring autonomous experiment loop for a given experiment using CronCreate at intervals from 10 minutes to monthly. Manages interval selection, loop metadata, and stopping active loops.

Processes deficiency reports from Goldfish reviewers, categorizes findings into contest/escalate/propose fix/decline categories, generates audit reports, and manages interactive resolution gates for code review workflows with automated fixes and human-in-the-loop approval

Executes automated multi-agent review loops to audit documents against qualitative standards and structural templates, automatically applying approved fixes. Ideal for reviewing design docs, READMEs, feature specifications, and implementation plans. Uses adversarial auditors in fresh contexts and persistent resolvers with institutional knowledge.