Product teams often lose time turning ideas into clear, testable backlog items. This skill helps create user stories, acceptance criteria, estimates, and capacity-based sprint plans.

Produit des synthèses robustes et traçables en faisant analyser une même source par plusieurs modèles aux rôles complémentaires, puis en consolidant leurs accords, divergences et points de vigilance.

Teams using AI agents need a reliable way to select ready work and avoid dependency conflicts. This skill guides Claude, Codex, and Claude Code through Beads and bv workflows for planning, claiming, and closing tasks.

Finding the right agent skill is hard when each registry has different coverage and ranking signals. This skill searches major registries together, compares native metrics, and highlights safety signals before a recommendation.

Local agent artifacts are difficult to review from another device or with teammates. Agentspace uploads a selected path and returns a browser link for viewing, comments, or editing.

Agents often need specialized instructions that are not loaded at the start of a session. This skill lets Claude, Codex, and Claude Code search, preview, scan, install, update, remove, and rate skills from agentskill.sh.

Coordinating several AI workers can make roles, tasks, and progress difficult to track. This skill manages Agentix teams through a structured API workflow.

Parallel AI work fails when roles, checkpoints, and reports are unclear. This skill gives Claude, Codex, and Claude Code teams a repeatable child-agent operating process.

Large or vague projects are difficult to start and coordinate. This skill turns clear requirements into ordered tasks with dependencies, acceptance criteria, and checkpoints.

Recipe data becomes difficult to maintain when fields, units, and ingredient formats vary. This skill provides a shared JavaScript schema, conversion guidance, and validation checks for consistent recipes.

Complex browser tasks require current selectors and reliable session control. This skill uses Actionbook snapshots and explicit sessions to automate websites.

Complex evidence workflows can lose context, citations, and handoff discipline. This skill gives Claude, Codex, and Claude Code a structured manager role for planning, delegation, tests, and audits.

Teams lose time when agents repeat the same project mistakes. This skill records concise error lessons in a shared project file.

Vague requests slow quality pipelines and cause rework. This skill checks requirements against project standards before the next step.

Final checks often miss consistency, security, or completeness gaps. This skill guides Claude, Codex, and Claude Code through a scored review before delivery.

Teams lose time turning validated requirements into consistent deliverables. This skill guides Claude, Codex, and Claude Code to create complete outputs that follow project standards.

Generated work often mixes styles, spacing, and structure. This skill applies consistent formatting so deliverables are easier to review and reuse.

Staged changes can be difficult to summarize clearly. This skill reviews the staged diff and drafts an editable commit message that explains the change and its purpose.

Complex websites hide important pages and weaken navigation. This skill creates a clear hierarchy, URL plan, link map, and prioritized implementation roadmap.

Shopping campaigns can lose visibility when product feeds contain missing attributes, incorrect prices, or policy risks. This skill reviews feed data and produces clear, truthful fixes for Merchant Center and Performance Max workflows.