Use when analyzing existing projects or codebases - onboard project to store context in Serena MCP, then use context-aware analysis that mentions existing code, modules, and patterns for better recommendations
Access Context Portal (ConPort) as persistent project memory via MCPorter. Load/update project context, log decisions and progress, track patterns. Use PROACTIVELY at session start to load context and throughout work to log decisions. Combats AI amnesia across sessions.
MCP orchestration via TypeScript execution for efficient multi-tool workflows. Use Code Mode for ALL MCP tool calls (ClickUp, Notion, Figma, Webflow, Chrome DevTools, etc.). Provides 98.7% context reduction, 60% faster execution, and type-safe invocation. Mandatory for external tool integration.
Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, or manage issue workflows. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", or any GitHub issue management task.
Aggregate and summarize event datasets (logs) using OPAL statsby. Use when you need to count, sum, or calculate statistics across log events. Covers make_col for derived columns, statsby for aggregation, group_by for grouping, aggregation functions (count, sum, avg, percentile), and topk for top N results. Returns single summary row per group across entire time range. For time-series trends, see time-series-analysis skill.
Monitor production errors using Sentry MCP. Query errors, analyze patterns, create issues, and verify error tracking is working. Use after deployment, when debugging production issues, or when verifying Sentry integration.
Analyze percentile metrics (tdigest type) using OPAL for latency analysis and SLO tracking. Use when calculating p50, p95, p99 from pre-aggregated duration or latency metrics. Covers the critical double-combine pattern with align + m_tdigest() + tdigest_combine + aggregate. For simple metrics (counts, averages), see aggregating-gauge-metrics skill.
Use for implementation plans - dispatches fresh subagent per task with quality scoring (0.00-1.00), code review gates, Serena pattern learning, and MCP tracking
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with Shannon quantitative analysis, exact file paths, complete code examples, validation gates, and MCP requirements assuming engineer has minimal domain knowledge
Advanced Git operations using Git MCP. Manage branches, analyze commit history, review changes, handle merges, investigate file history, and automate Git workflows. Use when working with version control, code reviews, or Git debugging.
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
How to update roadmap, changelog, and Kanban when completing features. Use after finishing any feature, bug fix, or improvement to ensure proper documentation and tracking. Keywords: changelog, roadmap, kanban, feedback, documentation, completion, tracking, MCP.
Master instructions for using Serena MCP tools for code navigation, search, navigation, and editing. Includes rules for terminal usage and memory management.
Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, or manage issue workflows. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", or any GitHub issue management task.
AEGIS v2.5開発の包括的Planモード。数学データ収集、形式証明環境構築、GRPO訓練パイプライン、MCP/A2Aエージェント開発、進捗監視を実装。SO(8)四重推論再現のための完全開発ワークフロー。
Work with Interval datasets (time-bounded data) using OPAL. Use when analyzing data with start and end timestamps like distributed traces, batch jobs, or CI/CD pipeline runs. Covers duration calculations, temporal filtering, and aggregating by time properties. Intervals are immutable completed activities with two timestamps, distinct from Events (single timestamp) and Resources (mutable state).
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Expert in creating well-structured GitHub issues with clear problem statements, specific acceptance criteria, and actionable technical context using GitHub MCP. Specializes in feature requests, bug reports, and refactoring tasks with proper labels and issue tracking. Use when creating issues before implementation, reporting bugs, or structuring project work.
Provides expertise in converting Figma designs to HTML/CSS using Figma MCP tools, with data attributes for content tracking and comprehensive analysis. Use when converting Figma designs to web code.
Use when saving workflow state to Serena MCP memory at research, planning, execution, or completion stages - enables resuming work later with /cc:resume command
