Vendor Profile
guanyang
SkillShield has analyzed 58 skills from guanyang. The average trust score across their skills is 79/100. 41 skills are trusted, 7 require caution, 10 are untrusted.
test-driven-development
guanyang/antigravity-skills
100Use when implementing any feature or bugfix, before writing implementation code
SKILLPASSING0 Findings5 days agodispatching-parallel-agents
guanyang/antigravity-skills
100Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
SKILLPASSING0 Findings5 days agorequesting-code-review
guanyang/antigravity-skills
100Use when completing tasks, implementing major features, or before merging to verify work meets requirements
SKILLPASSING0 Findings5 days agoremotion-best-practices
guanyang/antigravity-skills
100Best practices for Remotion - Video creation in React
SKILLPASSING0 Findings5 days agoreceiving-code-review
guanyang/antigravity-skills
100Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
SKILLPASSING0 Findings5 days agovercel-composition-patterns
guanyang/antigravity-skills
100React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
SKILLPASSING0 Findings5 days agoalgorithmic-art
guanyang/antigravity-skills
100Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
SKILLPASSING0 Findings5 days agoadvanced-evaluation
guanyang/antigravity-skills
100This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
SKILLPASSING0 Findings5 days agoevaluation
guanyang/antigravity-skills
100This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
SKILLPASSING0 Findings5 days agoverification-before-completion
guanyang/antigravity-skills
100Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
SKILLPASSING0 Findings5 days agoexecuting-plans
guanyang/antigravity-skills
100Use when you have a written implementation plan to execute in a separate session with review checkpoints
SKILLPASSING0 Findings5 days agotemplate-skill
guanyang/antigravity-skills
100Replace with description of the skill and when Claude should use it.
SKILLPASSING0 Findings5 days ago