fieldsphere/cursor-team-marketplace-template
Agent
Spawns a GPT-5.4-high agent for planning, review, analysis, and debugging of complex or difficult tasks—higher-quality reasoning, second opinions, or architectural guidance when ambiguity, risk, or failures appear. ONLY call this subagent when the user explicitly requests it. NEVER use the fast model for this…
fieldsphere/cursor-team-marketplace-template
Agent
Adversarial review plus acceptance verification. Scrutinizes diffs for quality issues, runs tests and lint when possible, and reports review findings alongside pass/fail against completion criteria. Use after substantive edits when you need review plus verification; use test-runner for execution-only test runs.
fieldsphere/cursor-team-marketplace-template
Cursor rule
Security, structure, and quality expectations for application code in any language.
fieldsphere/cursor-team-marketplace-template
Cursor rule
Software design expectations for modules, APIs, and long-term evolution.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Names Cursor cloud and local agents consistently. When starting an agent from a ticket or issue, uses TICKET-ID plus a short Title Case description after a colon. When there is no ticket, uses Title Case with at most four words. Use whenever naming a new agent, cloud agent, background agent, or when the user mentions…
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Create commits with conventional commit messages. Analyzes staged changes, generates a short one-line message, and runs git commit. Use when the user asks to commit, write a commit message, or create a commit.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Keep git history clean and reviewable with branch naming, branch upkeep, merge conflict handling, and pull request prep. Use when starting work on a branch, syncing with main, resolving conflicts, preparing a pull request, or when the user asks about git workflow hygiene.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Learn an unfamiliar codebase—structure, entry points, how to run and test, and where to change things safely. Use when joining a project, switching teams, or ramping on a new repo.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Naming conventions for markdown files across the project, including Cursor configuration files and general documentation. Use when creating or renaming any .md or .mdc files.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Shape implementation plans into a concise, execution-ready format with problem, scope, acceptance criteria, risks, steps, and verification. Use in Plan mode or when the user asks for a plan.
fieldsphere/cursor-team-marketplace-template
Agent
Creative design specialist for visual direction, composition, interaction concepts, and design exploration. Use when shaping the look and feel before implementation.
fieldsphere/cursor-team-marketplace-template
Agent
Technical UI implementation specialist for high-fidelity interfaces. Use when translating approved designs, mockups, or Figma files into polished, design-system-compliant frontend code.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Create production-ready UI mockups tied to real API states and design system constraints. Use when the user asks for polished screen mockups, stateful UI explorations, or handoff-ready visual specs.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Guide PMs and designers in creating comprehensive wireframes and mockups that accurately represent all backend API responses and data states. Use when creating wireframes or mockups for new features.
fieldsphere/cursor-team-marketplace-template
Agent
Technical devil's advocate that challenges feature plans, strategies, and implementation approaches when the user launches a request in plan mode. This subagent should be used by the Ask Clarification Tool before creating a plan when planning features, designing systems, or proposing solutions. It should be triggered…
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Summarize board, backlog, or sprint status for stakeholders with risks, blockers, and delivery confidence. Use for weekly PM updates and planning checkpoints.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Write high-quality tickets from product requests, incidents, or discovery notes. Use when drafting or refining implementation-ready work items.
fieldsphere/cursor-team-marketplace-template
Agent
Documentation specialist for long-form developer docs, API references, guides, and substantial README updates. Use when documentation itself is the deliverable.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Check whether README documentation should be updated when code changes affect setup, usage, commands, configuration, environment variables, workflows, or user-visible behavior. Use when making changes that may invalidate existing README content or require new documentation.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Generate or update a repository README with startup instructions and a Mermaid architecture diagram. Use when creating a README, updating project documentation, onboarding new contributors, or when the user mentions README, startup guide, or architecture overview.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Generate weekly commit summaries and categorize work. Use for weekly retrospectives or progress reviews.
fieldsphere/cursor-team-marketplace-template
Agent
Writes and extends unit tests and end-to-end tests that match the project's frameworks and conventions. Use when implementing features, fixing bugs, or when coverage is required for new or changed code.
fieldsphere/cursor-team-marketplace-template
Agent
Test execution specialist that proactively runs tests and reports results. Use when you need execution-only verification; use code-skeptic when you also want adversarial review.
fieldsphere/cursor-team-marketplace-template
Skill Claude CodeCodex
Verify product behavior with Cursor browser automation by driving real UI flows, capturing failures, and turning findings into actionable repro steps or follow-up tests. Use when the user asks for browser automation, in-browser verification, UI smoke checks, or manual flow testing in Cursor.