Software documentation often mixes learning, task, reference, and conceptual content. This skill separates those needs and produces focused Markdown for a defined audience.

Controller windows can close early or waste context while workers run. This skill schedules low-frequency, ETA-aware checks and waits for clear terminal states.

AI-assisted branches often include extra comments, unnecessary defensive code, and weak type workarounds. This skill reviews the branch diff and removes changes that do not match the surrounding code style.

Unsafe or missing Claude Code permissions can slow repository setup and create avoidable risk. This skill inspects project tooling and proposes settings that match detected files and services.

Important project context is easily lost between sessions. This skill stores it in structured files and helps retrieve it later with PARA and qmd.

Creating a new agent requires consistent configuration, a clear role charter, and the correct approval process. This skill guides Paperclip users through discovery, drafting, review, submission, and approval follow-up.

Plans often fail when tasks lack owners, dependencies, or clear starting conditions. This skill turns accepted Paperclip plans into a verified task graph that supports focused and parallel execution.

Managing an AI-agent company can require many API calls and scattered operational checks. This skill turns board requests into structured Paperclip workflows for onboarding, approvals, monitoring, and review.

Teams need a consistent way to coordinate agent work, approvals, and task progress. This skill guides Paperclip API workflows for assignments, updates, routines, and deliverables.

Paperclip UI work can drift when components, tokens, and layouts are created ad hoc. This skill gives Claude, Codex, and Claude Code a shared design guide for consistent frontend implementation.

Convex auth setup can fail when provider wiring, environment variables, and backend checks do not match. This skill guides the correct provider flow and adds verified Convex authentication patterns.

Starting a Convex app can require several framework-specific setup steps. This skill guides scaffolding, provider wiring, environment variables, and first validation checks.

Slow Convex features waste reads, trigger broad invalidations, and hide contention. This skill guides Claude, Codex, and Claude Code through targeted performance audits.

Breaking Convex schema changes can fail deploys or damage production data. This skill guides safe rollouts, batched backfills, dry runs, and verification.

Convex components need clear data ownership, wrapper functions, and generated types. This skill guides component design, implementation, wiring, and validation for Convex projects.

Convex requests can be broad, and teams may choose the wrong workflow. This skill directs Claude, Codex, and Claude Code toward setup guidance and specialized Convex skills.

Genkit projects can fail when APIs, model names, and provider setup drift. This skill guides Node.js and TypeScript developers with current setup, examples, and troubleshooting steps.

Turning requirements into consistent, interactive prototypes can take significant design and engineering time. This skill converts page requirements into validated GemDesign prototypes with local preview and platform synchronization.

Online work offers often hide weak funding, closed access, or costly payout conditions. This skill reviews primary evidence and estimates conservative expected value before you commit.

Creating a useful AI skill requires more than generic instructions. This skill guides Claude, Codex, and Claude Code to research proven expert methods before drafting the skill.