Loading...
Loading...
Found 160 Skills
Help create paper-quality plots and figures with matplotlib or seaborn. Use when the user asks for plots, figures, or visualizations.
Analyzes project bounded contexts, extracts business rules and domain knowledge, writes ai-context/features/<context>.md files, and produces a teach-report.md with documentation coverage metrics. Trigger: /codebase-teach, teach codebase, extract domain knowledge, update feature docs.
Zustand 5 state management patterns for React: stores, persistence, selectors, slices. Trigger: When managing global state in React, using Zustand, or implementing state slices.
Implements SDD plan tasks following specs and design, marking progress in tasks.md as it goes. Trigger: /sdd-apply <change-name>, implement change, apply SDD tasks, write code for change.
Analyzes staged and unstaged files from the full working tree, groups them into functional clusters (test, docs, chore, directory prefix), generates a conventional commit message per group, detects common issues (secrets, debug statements, large files), and executes one commit per group sequentially after presenting a multi-commit plan for confirmation. Falls through to a single-commit flow when all detected files resolve to one group. Trigger: When the user says "commit", "smart commit", or /commit.
Tailwind CSS 4 patterns: semantic classes, cn() utility, dynamic styling, library exceptions. Trigger: When styling with Tailwind, using className, conditional styles, or dark mode.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
LLM prompt testing, evaluation, and CI/CD quality gates using Promptfoo. Invoke when: - Setting up prompt evaluation or regression testing - Integrating LLM testing into CI/CD pipelines - Configuring security testing (red teaming, jailbreaks) - Comparing prompt or model performance - Building evaluation suites for RAG, factuality, or safety Keywords: promptfoo, llm evaluation, prompt testing, red team, CI/CD, regression testing
Use Bun instead of Node.js, npm, pnpm, or vite. Provides command mappings, Bun-specific APIs, and development patterns.
Actionable design system complementing official frontend-design plugin. The plugin provides philosophy; this skill provides executable patterns. Invoke when: - Building web components, pages, or applications - Designing UI that needs to stand out (not generic) - Implementing visual polish and micro-interactions - Choosing typography, color palettes, or spatial layouts CRITICAL: Avoid "AI slop" aesthetics. Make creative, unexpected choices. MANDATORY: Consult Gemini before any frontend work. See also: references/dna-codes.md, references/banned-patterns.md
Run /check-posthog, then create GitHub issues for all findings. Each finding becomes a separate, actionable issue with clear acceptance criteria. Invoke for: PostHog audit to issues, analytics backlog creation.
Multi-AI orchestration primitive. Delegate to specialized AI tools, collect outputs, synthesize. Use when: analysis, review, audit, investigation tasks need multiple expert perspectives. Keywords: orchestrate, delegate, multi-ai, parallel, synthesis, consensus, dag, swarm