- Skills
- 50
- 仓库
- 1
- 职业覆盖
- 0
- 场景覆盖
- 0
- Stars
- ★ 1
Jan M Montalvo 的 Skills 50
ui-ux-pro-max
UI/UX design intelligence for web and mobile. Local database with 79 searchable styles (88 catalog entries), 192 color palettes, 74 font pairings, 192 product types, 119 UX guidelines, 105 curated icon entries, 17 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js, and HTML/CSS). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.
figma-mcp
Implement or compare UI against Figma designs using an available Figma MCP integration. Use for Figma-backed implementation, design-token extraction, or visual-parity gap analysis; Figma MCP access is optional and must already be configured by the user.
improve-codebase-architecture
Find evidence-based, active-change architecture improvements using shared design and domain-modeling guidance. Use when a user wants to reduce architectural friction, deepen a module, or make a current change safer, more testable, and easier to navigate.
domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing GLOSSARY.md or CONTEXT.md, or recording or editing an ADR.
codebase-design
Provide the shared vocabulary and discipline for designing deep modules with clear interfaces and seams. Use when a user wants to design or improve a module, find deepening opportunities, choose a seam, or make code more testable and AI-navigable.
test-coverage-review
MUST invoke to review whether added or updated tests cover code changes in a diff. Checks new logic, branches, error paths, and regression risk, producing a change-to-test matrix. Use requirements-to-tests-traceability for acceptance-criteria mapping and orchestrated-review for bundled reviews.
test-correctness-review
MUST invoke to review whether tests are valid, correctly implemented, and prove the behavior they claim. Checks setup, execution, mocks, and assertions for false-confidence risks. Use test-coverage-review for changed-code coverage and requirements-to-tests-traceability for requirement mapping.
security-review
MUST invoke for a security-focused review of code changes. Identifies evidence-backed vulnerabilities involving secret exposure, authentication, authorization, data access, dependencies, configuration, injection, cryptography, and external requests. Use for 'security review', 'security check', 'check for vulnerabilities', 'OWASP review', 'security audit', 'check for secrets', or 'is this secure'. Do not use for functional correctness, design adherence, or test coverage reviews.
requirements-to-tests-traceability
MUST invoke to review whether requirements, acceptance criteria, Jira expectations, or specs are verified by tests. Maps requirements to test cases, finds missing or weak verification, and reports a requirement-to-test matrix. Use test-coverage-review for diff coverage and orchestrated-review for bundled reviews.
pr-comment-addressed-check
Determine whether a pull request review comment has been addressed in the current codebase. If the user already provided the pull request comment, inspect the relevant code immediately; otherwise ask for the comment first, then decide if the concern raised in the comment has been resolved or is still outstanding.
orchestrated-review
MUST invoke for full-suite, combined, bundled, or multi-lens code reviews. Runs security-review, design-principles-review, requirements-to-tests-traceability, test-coverage-review, and test-correctness-review as applicable, preserving each output in one wrapper. Do not use for a single review lens, review-cycle automation, or GitHub inline comments.
multi-agent-code-review
Orchestrate parallel code review only when the user explicitly asks for multiple agents, sub-agents, or parallel review of a branch, PR, commit range, diff, or local changes. Spawn one sub-agent per review point, de-duplicate exact duplicates, and preserve unique findings.
draft-code-review-comment
MUST invoke when the user asks to draft, write, word, or turn an agreed code-review concern into a concise PR/code review comment in the current chat. Trigger phrases include "draft a review comment", "write a PR comment", "turn this into a code review comment", "comment for this change", "word this review feedback", and "make this a concise code review comment". Also use after a discussion about branch or PR changes when the user says the issue should be raised as review feedback. Do NOT invoke for performing a fresh review, checking whether an existing comment was addressed, or editing the code.
design-principles-review
MUST invoke for SOLID, design-principles, abstraction, modularity, coupling/cohesion, maintainability, or design-pattern code reviews. Produces findings-first maintainability/testability risks. Use requirements-to-tests-traceability for requirements verification, security-review for security-only, and orchestrated-review for bundled reviews.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
wait-what
Stop. That last message did not land — re-pitch it.
handoff
Create a concise, redacted temporary handoff for a user or another workflow to continue in a new session.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any "grill" trigger phrases.