Agent Ready
Connectors
Categories
Blog
Usage
Methodology
Work with us
S
Connectors
/
Code & repositories
skillquiver
Twenty-four Agent Skills shared by your AI, your AI Code, and Codex.
Skills
24 in the Claude listing
Automate ui
Automates web and desktop UIs while capturing evidence that separates navigation from verified behavior.
brainstorming
Explores user intent, requirements, and design before implementation.
Communicate clearly
Controls report length while preserving evidence and explains external sources without overstating them.
Design ui
Builds accessible interfaces and verifies renders.
Diagnose systematically
Finds root causes through reproduction and falsifiable experiments.
Dispatching parallel agents
Dispatches one subagent per independent problem.
Engineer prompts
Builds or audits testable prompt contracts with explicit outcomes, permissions, tools, evidence, and stop conditions.
Execute durably
Runs long or interruption-prone work from a durable state file with falsifiable criteria and evidence.
Executing plans
Executes a written implementation plan inline, task by task, stopping only on blockers.
Finishing a development branch
Guides integration of a finished branch: verify tests, present merge/PR/keep/discard options to the user, and clean up worktrees.
Handle host boundaries
Handles unavailable named capabilities and destructive filesystem roots.
Improve agent instructions
Audits and safely updates scoped AGENTS.md and CLAUDE.md guidance for Claude Code and Codex.
Receiving code review
Verifies code review feedback before implementation and pushes back with evidence when a claim is wrong.
Refactor safely
Refactors working or legacy code without changing observable behavior, using characterization tests when needed.
Requesting code review
Dispatches a bounded reviewer and preserves verified findings.
Research systematically
Runs source-bound research and version-matched documentation lookup.
Skillquiver doctor
Audits the current ChatGPT, Claude Code, or Codex host for conflicting skills, plugins, and persistent hooks, then offers reversible per-item repairs.
Solve efficiently
Routes multi-module work with progressive discovery, matched effort, and context economy.
Subagent driven development
Executes an implementation plan by dispatching one subagent per task with per-task review gates, keeping the orchestrator's context small.
Test driven development
Runs a recorded red-green-refactor cycle.
Using git worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
Verification before completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs; requires running verification commands and confirming output before making any success claims.
Verify work
Independently audits finished work — verifies a delivery or completion claim against real evidence.
Writing plans
Creates implementation plans with interfaces, tests, and open decisions.
Three.js 3D Viewer
#184