Search skill packs and skills together

AI agents can waste time when requirements or preferences are unclear. This skill gives Claude, Codex, and Claude Code a practical pattern for asking focused questions.

Long AI workflows can lose context after crashes, timeouts, or session resumes. This skill defines checkpoint files, validation steps, and resume logic for safe recovery.

Large repositories are hard to understand before making changes. This skill gives Claude, Codex, and Claude Code a repeatable exploration workflow.

Parallel implementation can cause agents to overwrite files from other workstreams. This skill defines ownership, read-only access, and blocked workflows for Claude, Codex, and Claude Code.

Teams lose lessons from completed AI coding tasks. This skill guides Claude, Codex, and Claude Code to return concise reflection fields after work.

Implementation work can finish with missed failures. This skill guides Claude, Codex, and Claude Code through tests, lint, and type checks before completion.

Large AI tasks slow down when independent work is handled one step at a time. This skill helps teams split safe parallel work into bounded subagent tasks with clear outputs.

Many AI-built interfaces look generic and predictable. This skill guides Claude, Codex, and Claude Code toward richer visual design choices.

Large changes often produce messy commit history that slows review. This skill guides Claude, Codex, and Claude Code to make small commits with quality checks.

Important decisions can retain hidden assumptions when reviewed by one perspective. This skill assigns independent review lenses and combines concrete findings before you finalize a plan.

Early project decisions often rely on incomplete technical and market evidence. This skill coordinates specialist agents and combines sourced findings into a structured research report.

Implementation teams need reliable review before merge. This skill guides Claude, Codex, and Claude Code through structured readiness checks.