发现 Skills

Search past messages to recall context. Use when you need to remember previous discussions, find specific topics mentioned before, pull up context from earlier in the conversation history, or find which agent discussed a topic.

Parallelize build tasks to reduce total compilation time

Implement advanced serialization patterns for data persistence

Reviews staged git changes for code quality, maintainability, readability, and potential regressions. Verifies changes make sense in context, improve maintainability, enhance readability, and don't introduce side effects. Use when reviewing staged changes, examining git diffs, or when the user asks to review modifications before committing.

Enforces internal React and TypeScript coding standards using avoid/prefer rules. Use when reviewing or refactoring React/TS code, applying company standards, or when the user asks to align code with coding standards.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Word flow: deep-dive word analysis plus an infograph card in one step. Accepts one or more English words, runs ljg-word (produces deep semantic analysis) and then ljg-card -i (creates an infograph PNG). Use when the user says “词卡”, “word card”, “word flow”, or provides English words and wants both analysis and a visual card.

Step-by-step guide for implementing new features in laneweaverTMS, orchestrating the use of specialized skills and agents for database, backend, and frontend work.

Creative Spark Explosion — a high-pressure brainstorming engine that accepts only show‑stopping, viral ideas.

Apply systems thinking to leadership decisions and produce a Systems Thinking Pack (system boundary, actors & incentives map, feedback loops, second-order effects ledger, leverage points, intervention plan). Use for complex ecosystems, second-order effects, feedback loops, org/process redesign, and preventing unintended consequences. NOT for single-decision trade-off analysis (use evaluating-trade-offs) or decision process facilitation (use running-decision-processes). Category: Leadership.

Customize personalized travel plans based on MBTI personality types. Use when a user mentions their MBTI, wants a trip that matches their personality, or asks what travel style suits them.

Travel photo and outfit suggestions. Use this when a user wants to know what photo styles suit a destination, what clothes to wear, and how to take flattering pictures.

Software architecture design patterns and best practices

Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.

Use when executing implementation plans with independent tasks in the current session

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Run multi-persona code reviews on Lodestar PRs. Use when reviewing a PR, diff, or code change in ChainSafe/lodestar. Spawns specialized reviewer agents (bug hunter, security engineer, architect, etc.) with Lodestar-specific context, collects findings, and synthesizes a consolidated report. Covers PR review, code quality assessment, and security analysis for Ethereum consensus client code.

Charlie Munger's multidisciplinary mental-models investment approach, emphasizing cross-disciplinary knowledge and the Lollapalooza effect

GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GEO audits, citability scoring, AI crawler analysis, llms.txt generation, brand mention scanning, platform-specific optimization, schema markup, technical SEO, content quality (E-E-A-T), and client-ready GEO report generation. Use when user says "geo", "seo", "audit", "AI search", "AI visibility", "optimize", "citability", "llms.txt", "schema", "brand mentions", "GEO report", or any URL for analysis.

Use when you need to automate the daily stand-up process. Daily Sync automation includes pre-meeting AI preparation (progress summaries, obstacle identification, suggestions for daily work items), in-meeting human synchronization, and post-meeting AI processing (notes, action items, risk tagging), producing a daily sync report. Keywords: daily stand-up, Daily Sync, progress sync, blocker tracking, agile daily, stand-up, what to do today.

Use when you need to determine product core metrics, the OKR North Star metric, or design a metrics system. North Star metric selection: AI assists in choosing the metric that best measures product success and user value. This is a human decision point—AI provides data support, and humans make the final choice. Keywords: North Star metric, core metric, metric selection, product success metric, NSM, key metric, what data to look at.

This skill should be used when the user wants to set up an autonomous coding loop, plan a Ralph loop, prepare for headless Claude execution, create a spec and implementation plan for autonomous coding, or run an autonomous development workflow. Trigger phrases include "ralph", "autonomous loop", "coding loop", "ralph prep", "set up ralph", "headless loop", "autonomous coding", "ralph plan".

Use LycheeMem as Claude Code's structured long-term memory for prior conversations, user preferences, project decisions, timelines, and durable facts.

Session memory writer. Dumps what file exploration cannot recover — pitfalls, true working-tree state, uncommitted decisions, specific next steps — into daily/YYYY-MM-DD.md. Forms CQRS write-side pair with project-onboarding (read-side).