Coding standards, frameworks, refactoring, and code review (16.6K skills)
Delegate a clearly scoped coding task to Google Antigravity CLI when explicitly requested. Provides a workflow for preparing instructions, reading the implementer’s report, reviewing changes, rerunning project checks, and committing verified work.
Inspect local AI coding session logs with agenttrace to identify cost spikes, delays, failed tools, and retry loops. Produce readable reports, compare attempts, and configure automated checks for unusual or unhealthy runs.
Analyze a codebase to create project-specific AGENTS.md instructions and supporting rule files. Detect the package manager and relevant conventions, preview proposed changes, or update existing guidance when the project’s tools change.
Create, update, or audit AGENTS.md instructions using evidence from repository files and CI workflows. Preserve maintainer policies while clarifying commands, validation steps, and directory-specific rules that guide coding agents.
Hand a scoped coding task to Aider while the coordinating agent reviews changes, runs project checks, and commits the result. Covers task briefs, execution tracking, and follow-up edits, but the executable helper is not bundled.
Compare AAS skills against a project's capabilities, then record the chosen combination as a validated stack manifest. Inspect the result, identify catalog gaps, and optionally export evidence documenting the selection process.
Build and debug interactive web 3D scenes with Three.js, React Three Fiber, or Spline. Plan product configurators and portfolios, prepare models, connect scroll interactions, and review loading feedback, fallback content, accessibility, and performance on target devices.
Turn a repeatable task into an Andru.ia skill with clear inputs, outputs, examples, and limits. Draft SKILL.md, check the folder structure and required validations, and prepare a pull request describing the changes for review.
Organize feedback on an open GitHub pull request, make scoped code fixes, and verify the results. Prepare evidence-backed replies and, when authorized, post responses or resolve individual review threads.
Review an AAS skill stack, its proposed changes, and selection evidence in Workbench. Check identifiers, versions, setup gaps, and mismatches between related files without installing skills or applying the proposed changes.
Add a lightweight iOS App Clip to an Expo app so people can launch it from a website URL. Covers domain association, website launch cards, permissions, TestFlight submission, and App Clip metadata.
Assess a new or existing AI project by examining its code, goals, and constraints. Recommend skills confirmed to exist in the available registry, then outline tasks and implementation phases with dependencies, completion criteria, and checks.
Manage coding work from issue intake through implementation, review, deployment, and acceptance checks. Track each completion requirement against fresh evidence, with defined retry limits and explicit escalation when progress needs human input.
Let the host AI agent review Git changes while ocr selects files and resolves review rules. Receive findings grouped by severity, plus coverage details showing which files were reviewed or skipped and why.
Review Git changes with the ocr command-line tool and a configured AI model. Get line-level findings grouped by severity for working changes, commits, or branch comparisons, with code fixes applied when explicitly requested.
Explore unfamiliar code with GitNexus to understand project structure and execution flows. Find related functions, inspect their callers and callees, and read implementation files to explain how a feature works, with repository and index freshness information.
Coordinate a development task from planning through implementation and review. Choose whether to proceed after seeing the plan, then receive a report covering commits, verification results, review findings, and any work left unfinished.
Build and maintain a GitNexus code index, a searchable map of code relationships. Use CLI commands to refresh or remove indexes, check their status, list indexed projects, and generate repository documentation with an LLM.
Carry out an engineering plan through stepwise code changes, dependency impact checks, tests, and focused commits. It also handles small, bounded tasks directly, checking the code relationship index before relying on its results.
Find the right GitNexus tools and workflows for exploring code relationships. This reference explains available commands, graph queries, and resources, including how to check which branch an answer describes and whether its index is current.
Investigate errors and unexpected behavior by finding related code, following function calls, and checking source files. GitNexus helps trace execution paths, while the diagnosis identifies the repository and reports how current its code index is.
Create an implementation plan grounded in code relationships and verified source files, with proposed changes, test scenarios, risks, and a structured handoff for an implementation agent. It can also revisit and strengthen an existing plan.
Rename functions, extract modules, and split or move code with dependency checks before editing and validation afterward. GitNexus previews semantic renames, meaning changes follow code bindings, and reports the scope and limits of its coverage.
Assess the impact of code changes with GitNexus by tracing callers, dependencies, and affected execution flows. Check existing changes and report their scope, risk, and uncertainty before editing or committing.