发现 Skills

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Python data validation using type hints and runtime type checking with Pydantic v2's Rust-powered core for high-performance validation in FastAPI, Django, and configuration management.

Use this skill when starting a new project or adding SynthesisFlow to an existing project. Scaffolds the directory structure (docs/specs, docs/changes) and configuration files needed for the spec-driven development workflow.

Evaluate whether a software architect is fulfilling the 8 core expectations of the role and assess their technical breadth vs depth balance using the knowledge pyramid. Use this skill whenever the user asks what a software architect should be doing, questions whether they are performing the architect role correctly, wants to assess their own or someone else's architect performance, describes symptoms of role dysfunction (spending too much time coding, not attending stakeholder meetings, only recommending technologies they know, avoiding decisions), asks about transitioning from developer to architect, or encounters the Frozen Caveman anti-pattern where past experiences irrationally drive current decisions — even if they don't explicitly say "architect role" or "expectations."

Analyze a system's architecture quanta — independently deployable units with distinct quality attribute needs. Use this skill whenever the user needs to determine if their system should be monolith or distributed, is analyzing deployment boundaries, evaluating which parts of a system need different scalability/reliability/performance characteristics, decomposing a monolith, or asking "should this be one service or many?" — even if they don't use the term "quantum."

Build a complete mnemonic device or memory palace for anything the user needs to memorize, recall, or remember. Use this skill whenever someone wants to memorize a list, sequence, set of terms, vocabulary, historical dates, medical facts, or any body of material they struggle to recall. Activates on requests like "help me remember", "I can't recall", "memorize this", "make a mnemonic", "build a memory palace", "use method of loci", "create a flashcard structure", "remember in order", "recall under pressure", or "stop forgetting." Covers simple devices (acronyms, peg method, chunking, rhyme schemes) and complex devices (memory palace, method of loci, location-based recall). Does NOT teach the underlying subject matter — the learner must understand the content first; this skill organizes it for retrieval.

Diagnose why a product team or organization is slow, not innovative, or delivering poor outcomes. Use when a leader or team observes slow velocity, lack of innovation, poor product quality, feature factory behavior, or team dysfunction — and needs root causes and a prioritized fix list. Also use when a new product leader is assessing an organization, when a CEO or board says teams are too slow, or when someone says 'why are we not shipping faster?', 'engineering and design aren't collaborating', 'we ship but nothing moves the needle', or 'I need to assess team health before proposing changes.' Scores 42 diagnostic criteria across team behaviors, innovation capacity, velocity killers, and design integration. Produces a severity-ranked report with a composite health score and remediation priorities. For culture-level issues (innovation vs. execution quadrant), use product-culture-assessment. For process-level waterfall diagnosis, use product-process-dysfunction-diagnosis.

Design UTM naming conventions and campaign tracking systems for marketing attribution. Use when setting up tracking, standardizing naming, or improving attribution data quality.

See the essence of a codebase. Identifies core abstractions, surfaces dilution and scattering, finds the true shape beneath accumulated code. Outputs a distillation - a seeing, not a plan. Use before pruning or honing.

Dockview with practical React examples (~170k tokens). USE THIS SKILL FOR: finding working code patterns to copy, seeing how to implement specific features, learning idiomatic usage, understanding real-world integration patterns. Contains everything in dockview-full PLUS 45 React sandbox examples covering tabs, groups, drag-drop, serialization, theming, and more. Choose this when you need 'show me how to implement X' or 'what's the pattern for Y'.

Full OpenClaw trading skill for the Base blockchain. Execute swaps on Aerodrome and Uniswap V3, manage portfolio, run token safety checks (55-point scoring), monitor prices, manage liquidity positions, and track P&L. Kill switch, risk controls, flash loan arb via Aave V3.

Manage the Proxmox VE virtualization platform on a Dell PowerEdge R720 XD. Use this tool when connecting to the Proxmox server at 192.168.1.115:8006 to list VMs and containers, check node status, manage virtual machines, or monitor server resources.

Build on Snowflake's AI Data Cloud with snow CLI, Cortex AI (COMPLETE, SUMMARIZE, AI_FILTER), Native Apps, and Snowpark. Covers JWT auth, account identifiers, Marketplace publishing. Prevents 11 documented errors. Use when: Snowflake apps, Cortex AI SQL, Native App publishing. Troubleshoot: JWT auth failures, account locator confusion, memory leaks, AI throttling.

Audit how a brand appears in AI-powered search (ChatGPT, Perplexity, Claude, Gemini). Use when a user mentions 'AI search,' 'how do I show up in ChatGPT,' 'AI discoverability,' 'AEO,' 'LLM visibility,' or wants to understand their brand's AI presence.

This skill helps users extract structured best-selling product data from Amazon via the BrowserAct API. Agent should proactively apply this skill when users express needs like search for best selling products on Amazon, extract Amazon product data based on keywords, find top rated Amazon products, monitor Amazon competitor prices and sales, discover trending products on Amazon marketplace, extract Amazon product titles prices and ratings, gather Amazon product sales volume for market research, search Amazon best sellers in specific region, collect Amazon product reviews and promotion details, analyze Amazon product availability and badges, get Amazon product data for market analysis.

CMake cross-platform build system reference for C/C++. Covers modern target-based CMakeLists.txt, FetchContent dependencies, find_package, CMakePresets.json, CTest testing, install/export targets, compile_commands.json for clangd, and build types.

iperf

Neo4j graph database reference. Covers Cypher query language, node/relationship CRUD, path traversal, shortest path, graph algorithms (PageRank, Louvain, similarity), indexes, constraints, full-text search, and Python driver usage.

Analyze sandwich operations. Use when you need to understand sandwich mechanisms, evaluate protocol security, or reference on-chain concepts.

Symptom self-check tool: symptom analysis, guidance on when to see a doctor, prevention measures, lifestyle improvement tips, symptom tracking, and emergency recognition. ⚠️ Not a medical diagnostic tool. Use when you need symptom-checker capabilities. Triggers on: symptom checker.

This skill should be used when editing Python code in the erk codebase. Use when writing, reviewing, or refactoring Python to ensure adherence to LBYL exception handling patterns, Python 3.13+ type syntax (list[str], str | None), pathlib operations, ABC-based interfaces, absolute imports, and explicit error boundaries at CLI level. Also provides production-tested code smell patterns from Dagster Labs for API design, parameter complexity, and code organization. Essential for maintaining erk's dignified Python standards.

Batch update ARB translation files across all languages when new translation keys are added to English and Chinese files; use when adding new i18n strings to the Flutter app.

Compare a data file against a backup or prior version. Cell-level diff with float tolerance, key-based alignment, and structured verdicts. Use when verifying that dataset changes are intentional.

Next.js 16 with Turbopack, Cache Components, and proxy.ts. Use for bootstrapping, migrating, and building with App Router and React 19.