Loading...
Loading...
Found 758 Skills
Review existing Perses dashboards for quality: fetch via MCP or API, analyze panel layout, query efficiency, variable usage, datasource configuration. Generate improvement report. Optional --fix mode. 4-phase pipeline: FETCH, ANALYZE, REPORT, FIX. Use for "review perses dashboard", "audit dashboard", "perses dashboard quality". Do NOT use for creating new dashboards (use perses-dashboard-create).
Style Canvas components with Tailwind CSS 4 theme tokens and approved utility patterns. Use when (1) Creating a new component, (2) Adding colors or styling to components, (3) Working with Tailwind theme tokens, (4) Adding or updating design tokens in global.css, (5) Creating color/style props, (6) Any change where component props are added/removed/renamed/retyped and can affect rendered styles. Covers @theme variables, CVA variants, and cn() utility.
Technical design interview + adversarial review → living doc Technical Design section ready to implement. Stateful: detects existing sections and resumes where needed. Triggers: 'architect this,' 'how should we build,' 'design the tech,' post-define/design. Not for: scoping (explore), requirements (define), UX (design).
Use this skill when users need to apply themes, customize appearance, switch dark mode, use CSS variables, configure icons, or modify visual styling for Syncfusion React components. Covers icon library, size modes, and Theme Studio integration.
Guides KtUI theming with CSS variables, light/dark mode, and semantic colors. Use this skill when the user asks about KtUI colors, theme, dark mode, customizing appearance, or CSS variables for KtUI.
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes.
Manage Railway deployments, view logs, check status, and manage environment variables. Use when working with Railway hosting, deployments, or infrastructure.
Manage environment variables across Vercel environments. Sync with Vercel CLI, handle local overrides, and load env vars in scripts.
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
Use when investigating why something happened and need to distinguish correlation from causation, identify root causes vs symptoms, test competing hypotheses, control for confounding variables, or design experiments to validate causal claims. Invoke when debugging systems, analyzing failures, researching health outcomes, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"
Use when deploying to Vercel - covers Fluid Compute (timeout issues, 60s bug), vercel.json configuration, maxDuration settings, cron jobs, environment variables (printf gotcha), monorepo setup, Next.js issues, and common build errors