- Skills
- 111
- 仓库
- 1
- 职业覆盖
- 8
- 场景覆盖
- 7
- Stars
- ★ 0
LuisAlbertoMK 的 Skills 111
web-quality-audit
Comprehensive web audit: performance, a11y, SEO, responsive, animation, design tokens.
ui-engine
UI system — Grid/Flexbox/@layer/:has(), container queries, compositor-only animation, OKLCH tokens, component patterns
baseline-ui
Anti-slop UI — layout, typography, responsive, animation, tokens. Use for cleanup or polish.
skill-creator
Create new AI agent skills following Agent Skills spec -- auto-bootstrap unknown tasks, define structure, register in AGENTS.md
senior-engineer
Apply senior engineering competencies — system design, trade-off analysis, delegation, mentoring, and tech debt strategy
prompt-engineering
Design effective prompts using SPEARS framework — scope, principles, examples, assertions, refinements, with ReAct and multi-agent patterns
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
workflow-optimizer
Optimize workflow patterns — faster info access, reduced token waste, smarter caching, auto-learning triggers.
work-unit-commits
Plan commits as reviewable work units.
web-quality-audit
Comprehensive web audit: performance, a11y, SEO, responsive, animation, design tokens.
visual-testing
Visual verification - screenshots, visual regression, UI bug detection via Playwright. See vision-analyze for LLM.
vision-analyze
Local vision analysis - screenshots, UI review, error detection via Ollama. 100% local. NOT visual regression.
ui-engine
UI system — Grid/Flexbox/@layer/:has(), container queries, compositor-only animation, OKLCH tokens, component patterns
triple-verify
Triple verification — 3 enfoques, thresholds por zona, modos !ship/!fast/!draft
trial-verify
When facing >=2 viable options for a non-trivial reversible decision, implement/evaluate ALL of them, verify via independent subagent scoring, and PROCEED with the verified winner without asking the user to choose. Triggered by exception (d) of the 1-question rule.
testing-strategy
Test strategy - pyramid analysis, coverage gaps, risk-based prioritization, test debt, ROI-driven investment.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
subagent-isolation
Clean context boundaries between agents - prevent hallucination cascades, cross-contamination, enforce error isolation.