Loading...
Loading...
Found 719 Skills
Reduce your AI API bill. Use when AI costs are too high, API calls are too expensive, you want to use cheaper models, optimize token usage, reduce LLM spending, route easy questions to cheap models, or make your AI feature more cost-effective. Covers DSPy cost optimization — cheaper models, smart routing, per-module LMs, fine-tuning, caching, and prompt reduction.
Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.
Provides comprehensive guidance for Vue Router v4 including route configuration, navigation, nested routes, route guards, and Vue 3 integration. Use when the user asks about Vue Router v4, needs to set up routing for Vue 3 applications, implement navigation guards, or work with Vue Router v4 features.
Track and manage API costs across sessions. Budget alerts, model routing for cost optimization, spend reports. Use when: cost check, budget status, how much spent, optimize costs, cost tracking.
Next.js 16 internationalization with next-intl or DIY. Use when implementing i18n, translations, localization, multilingual, language switch, locale routing, or formatters.
Add a lesson to a skill LEARN.md file, routing feedback to skill, template, or context learning. Use when capturing workflow lessons.
Analyzes Claude Code session transcripts to evaluate skill portfolio health — routing errors, attention competition between descriptions, and coverage gaps. Generates an interactive HTML report with per-skill health cards, competition matrix, attention budget analysis, and actionable patches. Unlike skill-creator which optimizes individual skills in isolation, skill-auditor optimizes the portfolio as a system, detecting cross-skill attention theft and cascade risks. Use when user says "audit my skills", "skill audit", "run skill-auditor", "analyze skill routing", "check skill competition", "portfolio health", "スキル監査", "スキルの精度を分析", "スキルルーティング分析".
ALWAYS invoke this skill at the START of every session before doing any other work. This skill ensures the host project has agent governance rules (skill routing, pre-implementation protocol, issue tracking conventions) installed in its context file. It is idempotent — if rules are already present, it exits silently. Without this skill running first, other swain skills (swain-design, swain-do, swain-release) will not be routable.
Comprehensive guide for TanStack ecosystem in React - Query/DB for data fetching, Form for form handling, and Router for client-side routing. Use when working with collections, live queries, optimistic updates, forms, validation, routing, URL parameters, or navigation.
Quality gate via second model. Spawn a different AI model to review work before committing. Includes refusal routing: if one model refuses, silently switch to the next.
Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.
Grafana OnCall and Incident Response Management (IRM) — alert routing, escalation chains, on-call schedules, Jinja2 routing templates, Slack/mobile notifications, integrations (Alertmanager, Grafana Alerting, webhooks, PagerDuty), and incident lifecycle management. Use when setting up on-call rotations, configuring escalation policies, routing alerts to the right team, declaring and managing incidents, integrating with Alertmanager or Grafana Alerting, or configuring Slack-based alert workflows.