Teams lose time when technical docs are incomplete, inconsistent, or hard to scan. This skill helps Claude, Codex, and Claude Code produce structured specs, runbooks, API docs, and architecture guides.

Teams need consistent estimates for sprint planning and roadmaps. This skill guides story points, planning poker, sizing, risks, and task breakdowns.

Teams often receive broad feature requests without clear tasks, priorities, or acceptance criteria. This skill turns feature ideas into user stories, sprint backlog items, dependencies, and Definition of Done checks.

Project environments drift when services, secrets, and tooling are configured by hand. This skill provides setup templates for Docker Compose, .env files, dev containers, Makefiles, and Terraform.

Teams lose focus when standups become long status meetings. This skill structures updates, blockers, action items, and async check-ins.

Users often struggle to choose between local state, global stores, and server data caching. This skill gives React patterns for Context, Zustand, Redux Toolkit, and TanStack Query.

Sprint teams need structured reflection to turn issues into practical improvements. This skill guides Claude, Codex, or Claude Code through retrospective formats, action items, and follow-up practices.

Skill files can drift from the Agent Skills specification and trigger unreliably. This skill validates structure, frontmatter, descriptions, and evaluation examples.

Web applications often ship with weak headers, unchecked inputs, and unsafe secret handling. This skill guides Claude, Codex, and Claude Code through practical hardening steps for APIs and infrastructure.

Fixed layouts fail on phones, tablets, and wide screens. This skill guides mobile-first CSS, breakpoints, images, and layout patterns.

Vague software requests often lead to rework and drift. Ralph helps Claude, Codex, and Claude Code clarify requirements, create specs, and verify progress through bounded loops.

Lightweight models can miss context when questions arrive after important information. This skill repeats suitable prompts with guardrails to improve accuracy on selected tasks.

Teams need fast concept images without paid accounts or complex setup. This skill guides prompt creation, URL generation, batch variants, and local saving through Pollinations.ai.

AI coding agents can start work before plans are clear, which makes errors costly. Plannotator adds a browser review step for plans, diffs, images, approvals, and structured feedback.

Teams miss recurring defects, risky patterns, and data anomalies when reviews rely only on manual inspection. This skill guides read-only pattern searches, regex checks, and concise reports for Claude, Codex, and Claude Code.

AI agents lose project context between sessions, causing repeated explanations and stale assumptions. This skill guides Claude, Codex, and Claude Code to store, search, and reuse OpenContext knowledge.

Complex coding tasks are hard to split, verify, and resume across multiple agents. OMC adds team, autopilot, and verify/fix workflows for Claude Code projects.

Complex projects need clear handoffs between planning, implementation, QA, and debugging agents. This skill defines a Serena Memory based workflow for coordinating specialized agents and monitoring progress.

Teams often need packages from branches, forks, or private GitHub repositories before they reach npm. This skill explains npm Git URL formats, authentication options, install checks, and common fixes.

Production systems fail silently without clear signals. This skill helps teams add metrics, logs, dashboards, alerts, and health checks with practical examples.