Claude Code Skills · page 155

Bradley Sutton (Helium 10 VP of Education) 视角. 数据驱动亚马逊运营方法论. 调用此 skill 时, 用 Bradley 的认知框架做 Amazon 运营 / 关键词 / PPC 决策.

Steve Chou (My Wife Quit Her Job) 视角. 美国独立站 + 跨境老兵的长期主义方法论. 调用此 skill 时, 用 Steve 的认知框架做 DTC / 多平台决策.

阳萌 (Anker 创始人 / CEO) 视角. 中国品牌出海方法论 — 长期主义 / 浅海战略 / 国际品牌三段论. 调用此 skill 时, 用阳萌的认知框架做品牌出海决策.

|

|

|

|

|

|

|

|

|

Beat Hintermann (Kantonsspital Baselland, Switzerland) 视角. 踝关节置换 (TAA) HINTEGRA 假体设计师 + 20 年长期 follow-up 数据 + Patient selection 派. 调用此 skill 时, 用 Hintermann 框架做终末期踝关节炎 / 置换 vs 融合 / 长期 follow-up 决策.

Mark Glazebrook (Dalhousie University, Canada) 视角. 跟腱病 PhD + 关节镜专家 + COA 前主席. 调用此 skill 时, 用 Glazebrook 框架做跟腱病变 / 关节镜 / 循证治疗等级决策.

张建中 (首都医科大学附属北京同仁医院足踝外科矫形中心) 视角. 国内足踝外科教父级代表. 拇外翻 + 平足 + 踝关节置换 + 中文圈本土化派. 调用此 skill 时, 用张建中框架做拇外翻 / 国内患者 / 中文圈实操决策.

|

|

|

|

|

|

叶云燕视角. 平安寿险代理人体系销售方法论 living legend, 「事业宗教叙事 + 师徒制扩张」流派代表. 提供「主动筛客 + 极致服务 + 团队复制」式决策视角, 与独立经纪流派 (江立辉 / 明亚) 形成对位张力.

|

|

|

|

|

Esther Perel 视角. 长期关系悖论派代表. Mating in Captivity + Eroticism + Modern Burden + 出轨现代解读. 调用此 skill 时, 用 Perel 框架做长期关系决策.

John Gottman (Gottman Institute) 视角. 循证婚姻研究派代表. Four Horsemen + 5:1 Magic Ratio + Cascade Model. 调用此 skill 时, 用 Gottman 框架做关系健康度判断.

Sue Johnson (EFT 创始人) 视角. 依恋驱动派代表. EFT 7 Conversations + Hold Me Tight + 依恋触发点. 调用此 skill 时, 用 EFT 框架做关系修复决策.

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

|

Deep system analysis skill. Audits the user's codebase against production-grade patterns extracted from Anthropic's own Claude Code (512K-line TypeScript agent). Covers: context management, permission systems, security hardening, agent orchestration, tool execution pipelines, API client design, prompt engineering, state management, plugin architectures, rendering engines, build systems, telemetry, memory systems, error handling, resilience patterns. TRIGGER when: reviewing architecture, auditing security, designing agent systems, building CLI/TUI tools, implementing streaming, designing permission models, building plugin systems, optimizing context windows, designing multi-agent coordination, writing system prompts, building API clients, implementing retry/backoff, designing build pipelines, or whenever the user wants to understand how a production AI system handles something and whether their approach measures up.

Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.

Token-efficient smart contract security auditing via Behavioral State Analysis (BSA). Scopes analysis to contract type, runs only relevant threat engines, and uses tiered output depth. Use for auditing smart contracts, security reviews, or DeFi threat modeling.

Blue-team release-gate analysis for smart contract deployment and upgrade readiness. Classifies repositories, checks deploy/upgrade execution paths, CI/CD trust boundaries, config drift, secrets/signer operational security, and outputs evidence-backed release verdicts.

Detects Denial of Service and griefing vulnerabilities in smart contracts. Covers unbounded loop DoS, block gas limit exhaustion, external call failure DoS, insufficient gas griefing (63/64 rule), storage bloat attacks, timestamp griefing, self-destruct force-feeding, and push vs pull payment pattern analysis. Use when auditing contracts with batch operations, loops over user data, reward distribution, dividend systems, or any logic that depends on address(this).balance or iterates over growing collections.

Detects unsafe external call patterns and token integration vulnerabilities in smart contracts. Covers unchecked call/delegatecall/staticcall return values, fee-on-transfer tokens, rebasing tokens, tokens with missing return values (USDT), ERC-777 callback risks, unsafe approve race conditions, return data bombs, gas stipend limitations, and push vs pull payment patterns. Use when auditing contracts that interact with external contracts, integrate arbitrary ERC20 tokens, distribute payments, or make low-level calls.

Detects input validation failures and arithmetic vulnerabilities in smart contracts. Covers missing zero-address and zero-amount checks, division-before-multiplication precision loss, rounding direction exploitation, ERC4626 vault share inflation attacks, unsafe integer casting, dust amount exploitation, and Solidity 0.8+ unchecked block edge cases. Use when auditing contracts with fee calculations, share pricing, exchange rates, unchecked blocks, or any public-facing functions that accept user input.

Detects price oracle manipulation and flash loan attack vectors in DeFi smart contracts. Classifies oracle trust models (Chainlink, TWAP, spot price, custom), identifies stale price risks, circular price dependencies, and flash loan atomicity exploitation patterns. Use when auditing DeFi protocols that depend on price data, oracle integrations, lending protocols, DEXs, derivatives, or any contract where flash loans could manipulate state within a single transaction.

Detects vulnerabilities in upgradeable proxy smart contracts including storage layout collisions, uninitialized implementations, function selector clashing, delegatecall context issues, and upgrade path safety. Covers Transparent Proxy, UUPS (EIP-1822), Beacon, Diamond (EIP-2535), and Minimal Proxy (EIP-1167) patterns. Use when auditing upgradeable contracts, reviewing implementation upgrades, analyzing delegatecall architectures, or verifying proxy pattern compliance.

Systematically detects all reentrancy vulnerability variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy. Builds call graphs, verifies CEI (Checks-Effects-Interactions) pattern compliance, traces state changes relative to external calls, and identifies callback vectors through ERC-777/ERC-1155 hooks. Use when auditing contracts that make external calls, transfer ETH or tokens, interact with callback-enabled standards, or have complex multi-contract architectures.

Detects logic vulnerabilities in smart contracts by analyzing guard-state consistency patterns. Identifies functions that bypass security checks (require, modifiers) that other functions consistently apply. Uses the Consistency Principle — a contract is its own specification. Use when auditing smart contracts for missing access controls, inconsistent pause checks, logic bugs, forgotten modifiers, or when traditional tools report no issues but logic errors may exist.

Detects signature replay vulnerabilities in smart contracts — affecting 19.63% of signature-using contracts. Covers five replay types (same-chain, cross-chain, cross-contract, nonce-skip, expired-signature), EIP-712 domain separator verification, nonce management analysis, ecrecover edge cases (address(0), malleability, s-value), permit/permit2 safety, ERC-1271 contract wallet support, and meta-transaction security. Use when auditing contracts with ecrecover, ECDSA, EIP-712, permit, meta-transactions, multi-sig, or any off-chain signature verification.

Detects broken mathematical relationships between state variables in smart contracts. Automatically infers invariants (totalSupply = sum(balances), conservation laws, ratio constraints) then finds functions that violate them. Catches unauthorized minting, broken tokenomics, accounting desynchronization, and state drift. Use when auditing for state-state invariant violations, broken accounting, supply mismatches, desynchronized state variables, or conservation law violations in smart contracts.

Use only when user explicitly asks to "open dashboard", "show dashboard", "launch dashboard", or "learning UI". Opens a local web interface for viewing and editing learning plans, quiz progress, and spaced repetition data.

Use when user wants to learn a topic or create a study plan. Triggers on "teach me", "I want to learn", "explain X to me", "study", "help me understand", "where do I start with", "how do I get into", or any request to understand a subject in depth. Covers both technical topics (programming, system design, DevOps) and general knowledge (history, science, languages, music theory). Also use when someone asks for a "learning path", "roadmap", or "curriculum" for a topic — even if they don't explicitly say "learn".

Use when user wants to be tested or quizzed on any topic. Triggers on "quiz me", "test me", "test my knowledge", "practice questions", "check my understanding", or when asking for a quiz on something they've been learning. Also use when user finishes a learning module and wants to check understanding. Works with or without a prior learning plan.

Use when user asks for learning resources, recommendations, or materials on any topic. Triggers on "find me resources", "what should I read about", "best tutorials for", "recommend a book on", "good courses for", "where can I learn more about", "any videos on", or any request for curated study materials. Also use when user wants to browse what's available before committing to a full learning plan — this skill works with or without an existing plan.

Use when user asks about their learning progress or wants study guidance. Triggers on "how am I doing", "my progress", "what should I study next", "show my scores", "what are my weak areas", "review my learning", "how well do I know X", or any request to see quiz results, track improvement, or decide what to focus on next. Also use when the user seems unsure what to study — this skill provides data-driven recommendations.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Answer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why', 'what does this do', 'what is the purpose of', 'explain', 'what's the difference', 'compare', or 'what are the tradeoffs' — even when referencing specific files, code snippets, or inline code. The key signal is the user wants to UNDERSTAND something, not change it. Do NOT trigger for requests to build, fix, plan, review, research, or add/modify code.

Implement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a search/filter, or any other hands-on coding task. This is the default skill for all 'build this', 'add this', 'create this', 'wire up', 'implement' requests. Covers the full cycle: clarify requirements, plan if needed, write code, verify, and review. Do NOT use for pure research, debugging, documentation, or explanation — only when the user wants working code delivered.

Use when the user wants to save knowledge as a file so others don't have to rediscover it — \"turn this into a doc\", \"write this up\", \"document how X works\", \"we figured this out and want to capture it\", \"nobody should have to figure this out again\". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).

Investigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden unexplained changes in metrics or behavior, works locally but not in staging/production, inconsistent or intermittent failures, correct code producing wrong results, operations succeeding but having no effect, environment-specific failures, duplicate executions, stale data, or any \"why did this change?\" or \"why is this happening?\" situation. Covers infrastructure anomalies (cache hit rates dropping, latency spikes, queue behavior shifts) as well as code bugs. The key signal is confusion about root cause, not a request to implement a known fix. Do NOT use for feature requests, known fixes, planning, or documentation tasks.

Brainstorms and debates approaches, then drives toward an actionable decision. Use whenever someone needs a thinking partner for a decision they're facing: 'discuss', 'debate', 'brainstorm', 'weigh options', 'tradeoffs', 'should I do X or Y', 'help me decide', 'I'm torn between', 'sanity check my thinking', or 'what do you think about'. The user must be asking for help reasoning through a choice — not asking to build, fix, evaluate, plan, or modify something (even if the topic involves this skill itself). Picks the right decision lens, surfaces tradeoffs and blind spots, pushes back when reasoning is genuinely weak, and never implements.

Fetch up-to-date documentation for any library, framework, API, or service into context. Use when the user wants to look up API references, check function signatures or required fields, find feature-specific docs, or verify how an external tool actually works. Triggers for queries about third-party libraries like Stripe, SQLAlchemy, Tailwind, FastAPI, shadcn, Drizzle, Hono, Better Auth — any time the answer lives in official docs rather than in the project codebase. Use this instead of guessing from trained knowledge, which is stale.

Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.

Builds distinctive, production-grade UIs that avoid generic AI aesthetics. Use whenever the user wants to build, restyle, or give visual direction to any interface — pages, dashboards, landing pages, components, onboarding flows, mobile screens, or design systems — even without an explicit 'design' request. Also triggers for: picking an aesthetic direction, improving the look of a dull/generic existing page, adding visual personality, or choosing colors/typography. Includes a bundled design intelligence database for concrete guidance across web (React, Next.js, Vue, Tailwind) and mobile (React Native, Flutter, SwiftUI).

Use when the user wants a written, reviewable plan or spec produced before coding starts. Triggers on: mapping out changes without implementing, thinking through risks of upgrades or migrations, evaluating approaches before committing to one, writing specs for team review, phasing work into stages, or any request that explicitly defers coding ('don't implement yet', 'before we build'). The distinguishing signal is that the user wants a plan artifact — not implementation, not a conversational answer. MUST activates inside Claude's native plan mode to have a better planning behavior.

Specialized visual and multimedia processing tools. Use this skill whenever a task involves complex visual content — UI mockups, dense screenshots, design images, charts, artwork — where precise details like spacing, hex colors, font sizes, and component hierarchy need to be extracted accurately. Also use for: reviewing or auditing existing UI against designs, comparing screenshots for visual regressions, transcribing audio/video, extracting data from PDFs with complex layouts, and generating images. Trigger whenever the user wants to implement from a design, review or compare UI screenshots, analyze visual details precisely, describe artwork or aesthetic content, or process any media file (audio, video, PDF).

Generates a Claude Code configuration tailored to a specific project. Use whenever the user wants to prime a project, set up claude for a repo, bootstrap claude config, or re-prime/refresh an already-primed project (for example after `/prime-sync` pulled new starter content). Triggers on 'prime', 'prime this project', 'optimus-prime', 're-prime', 'refresh claude config', 'regenerate CLAUDE.md', 'set up claude for this repo'. Deeply analyzes the real codebase and builds project-specific skills, rules, and CLAUDE.md — not generic boilerplate. For ongoing config health checks and proposal review, use `self-evolve` instead.

Syncs Claude config between prime repo and target projects. Trigger on 'sync', 'prime-sync', 'push config', 'pull config', 'update prime', 'sync claude config'. Push mode deploys to targets; pull mode imports changes back.

Review code for quality, correctness, and fit. Use when the user wants judgment on code that already exists — their own changes, a teammate's patch, a PR, branch, commit, diff, staged changes, or one or more files to look over. Activate on requests like review, look over, sanity check, critique, code review, or 'is this good?' The key signal is that the user wants evaluation of existing code and its tradeoffs, not implementation, debugging, or explanation. This skill works independently, but when plans, specs, task artifacts, or prior discussion exist, use them to understand why the code exists before judging it.

>

Use when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks, improving its instructions, or fixing why it isn't triggering. Triggers on: 'make a skill for X', 'test this skill', 'run evals on my SKILL.md', 'touch-skill', sharing a SKILL.md and asking if it's ready to ship. The key signal is intent to create, validate, or improve a skill — not just mention one. Do NOT trigger for general Claude Code questions, hook debugging, or CLAUDE.md configuration.

Use this skill for any Python backend work in this project: building FastAPI endpoints, writing service functions, defining Pydantic/SQLModel schemas, running Alembic migrations, or debugging 422 errors. Essential for authentication and authorization patterns — setting up get_current_user, is_superuser checks, admin-only guards, role-based access, and dependency injection chains like Depends(). Also covers middleware, background tasks, async SQLAlchemy sessions, ORM relationship loading, and request/response design. Activate whenever the question involves Python API code, FastAPI patterns, or backend architecture in this codebase. Not for frontend, Docker, CI/CD, or infrastructure.

ALWAYS activate when the user's query involves Docker in any way — even if it also matches other skills. If the words docker, Dockerfile, docker-compose, compose.yml, container, or image appear in the query, this skill MUST be used. Covers: writing or editing Dockerfiles and compose files, adding services (postgres, redis, etc.) to compose, volume mounts and data persistence, docker build failures (layer caching, npm install issues), healthchecks and service startup ordering (depends_on), environment variables in containers, port mapping, container crashes and exit codes (OOM/137), non-root users, multi-stage builds, image optimization, .dockerignore, and deploying to container runtimes. Takes priority over general implementation or debugging skills when Docker infrastructure is the subject.

Use this skill for ANY work involving React, Next.js, TypeScript, or Tailwind in the browser layer. This includes building components and pages, but equally covers debugging and fixing frontend issues: CSS/Tailwind classes not applying, form validation behavior, hydration mismatches between server and client renders, styling bugs, layout shifts, and rendering problems. Also use for refactoring components (e.g., splitting Server vs Client Components), data fetching patterns, state management, bundle optimization, and frontend tooling. If the problem involves what users see or interact with in a web browser — whether building, fixing, or refactoring — use this skill. Not for backend APIs, databases, infrastructure, or DevOps.

Rewrite existing text so it stops sounding AI-generated. Triggers on "humanize this", "un-ChatGPT it", "doesn't scream LLM", "strip the AI voice", or naming specific AI tells (em dashes, "it's not just X it's Y", "stands as a testament", "thrilled to announce", emoji-headed bullets, LinkedIn cringe). Works on any draft — blog posts, memos, READMEs, essays, PR descriptions — inline or in files. Keeps facts; changes voice. Do NOT use for writing new content, summarizing, translating, or pure-explanation requests with no draft to rewrite.

MUST use for ANY query mentioning packages, monorepo, workspace, catalog, turbo, turborepo, or pnpm in a multi-package context. MUST use when sharing config (ESLint, tsconfig, prettier) across packages, fixing build order between packages, adding new packages, scoping CI installs/caching to changed packages, or debugging pnpm catalog version resolution. This skill OWNS all cross-package coordination problems — even when they look like build, CI, config, or dependency issues. If two or more packages interact in the query, this skill applies. Takes priority over other skills when the problem spans package boundaries.

>-

>-

>

|