测试与安全技能

The science of learning through controlled experimentation. A/B testing isn't about picking winners—it's about building a culture of validated learning and reducing the cost of being wrong. This skill covers experiment design, statistical rigor, feature flagging, analysis, and building experimentation into product development. The best experimenters know that every test, positive or negative, teaches something valuable. Use when "a/b test, experiment, hypothesis, statistical significance, sample size, feature flag, variant, control, treatment, p-value, conversion rate, test winner, split test, experimentation, testing, statistics, feature-flags, hypothesis, growth, optimization, learning, validation" mentioned.

中文简介正在准备中。当前显示原文说明。

World-class character and art style consistency for AI-generated images and videos - ensures visual coherence across series, maintains character identity, and provides rigorous QA before deliveryUse when "character consistency, art style, same character, consistent character, visual continuity, series, turnaround sheet, character sheet, reference image, character bible, style guide, anime character, consistent look, face consistency, outfit consistency, lora training, ip-adapter, flux kontext, visual qa, art quality, generation review, style drift, character drift, character-consistency, art-style, visual-qa, ai-art, image-generation, video-generation, anime, illustration, lora, ip-adapter, flux, midjourney, stable-diffusion" mentioned.

中文简介正在准备中。当前显示原文说明。

Authentication and authorization expert for OAuth, sessions, JWT, MFA, and identity securityUse when "authentication flow, login system, oauth integration, jwt tokens, session management, password hashing, mfa setup, refresh tokens, social login, role-based access, authentication, authorization, oauth, oidc, jwt, sessions, mfa, passkeys, nextauth, supabase-auth, clerk" mentioned.

中文简介正在准备中。当前显示原文说明。

Discovery, download, and configuration hub for the entire aelf agent skill ecosystem. Use when the user wants to: (1) explore or list available aelf skills, (2) install/bootstrap aelf skills into Cursor, Claude Desktop, OpenClaw, Codex, or Claude Code, (3) route an aelf-related intent to the correct skill, (4) check health or audit installed skills, (5) onboard a new skill into the aelf ecosystem. Covers domains: Portkey CA wallet, Portkey EOA wallet, Awaken DEX, eForest NFT marketplace, AelfScan explorer, TomorrowDAO governance, aelf node interaction.

中文简介正在准备中。当前显示原文说明。

Use when working on the Bolt repository and you need to configure or compile code correctly and efficiently. This skill defines the canonical Bolt build workflow, including when and how to run `make`, `cmake --build ...`, and when build reconfiguration is necessary due to added files and test or build target changes.

中文简介正在准备中。当前显示原文说明。

Use when asked to set up, install, or refine an agent quality framework in a repository (rules with gates, architecture contracts, proven-red tests, ratchets, playbooks), or when the user says "gap-trap", "gap-trap setup", "gap-trap refine", "gate the rules", or "make the agents' code match the rules".

中文简介正在准备中。当前显示原文说明。

Define test cases BEFORE implementation, ensuring every API, business rule, and user journey has verifiable acceptance criteria during PRD v0.7 Build Execution. Triggers on requests to define tests, plan test coverage, create test cases, or when user asks "define tests", "test planning", "what to test?", "test cases", "test coverage", "TEST-", "test-first". Consumes EPIC- (scope), API-, DBT-, BR-, UJ-. Outputs TEST- entries with Given-When-Then format. Feeds v0.7 Implementation Loop.

中文简介正在准备中。当前显示原文说明。

Execute implementation within EPICs following test-first development, continuous SoT updates, and code traceability during PRD v0.7 Build Execution. Triggers on requests to start building, implement an epic, begin coding, or when user asks "start building", "implement epic", "coding", "development", "build execution", "implementation", "write code". Consumes EPIC- (context), TEST- (acceptance criteria). Updates existing IDs and creates code. Outputs working code with @implements traceability tags.

中文简介正在准备中。当前显示原文说明。

Apply Rob Fitzpatrick's Mom Test discipline to customer interviews during PRD v1.0 Market Adoption. Triggers on requests to interview customers, run discovery calls, validate ideas with users, or when user asks "how do I interview customers?", "Mom Test", "Rob Fitzpatrick", "customer interview", "user research without lies", "talking to humans", "discovery conversation". Outputs CFD-* discovery entries with Mom Test-calibrated confidence.

中文简介正在准备中。当前显示原文说明。

Audit how AI search engines (ChatGPT, Perplexity, Google AI Overviews, Claude) describe and recommend your product, then propose fixes. Triggers on requests to audit AI search visibility, improve AEO/GEO, check ChatGPT/Perplexity coverage, or when user asks "do we show up in AI search?", "AEO audit", "generative engine optimization", "AI discoverability", "how does ChatGPT describe us?", "Perplexity ranking". Outputs GTM-AEO-* entries and a Coverage Matrix.

中文简介正在准备中。当前显示原文说明。

Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution. Triggers on requests to create epics, scope work, break down implementation, or when user asks "create epics", "scope work", "break down work", "context window sizing", "what to build first?", "implementation planning", "epic breakdown". Consumes API-, DBT-, FEA-, ARC-. Outputs EPIC- entries with objectives, ID references, dependencies, and context windows. Feeds v0.7 Test Planning.

中文简介正在准备中。当前显示原文说明。

Surface risks through guided questioning, helping users consider pivots, constraints, and prioritization during PRD v0.5 Red Team Review. Triggers on requests to identify risks, stress-test the idea, perform red team review, or when user asks "what could go wrong?", "identify risks", "red team", "risk assessment", "challenge assumptions", "stress test the idea". Consumes all prior IDs (CFD-, BR-, FEA-, PER-, UJ-, SCR-) as interview context. Outputs RISK- entries with owner decisions and mitigations. Feeds v0.5 Technical Stack Selection.

中文简介正在准备中。当前显示原文说明。

Assess competitor defensibility and define our own moat strategy during PRD v0.3 Commercial Model. Triggers on requests to analyze competitor moats, define our defensibility, assess switching costs, identify vulnerabilities, find wedge opportunities, or when user asks "what's our moat?", "how defensible are they?", "where can we compete?", "switching costs?", "defensibility", "who to target". Consumes Competitive Landscape (v0.2) CFD- entries. Outputs CFD- entries for competitor moats and BR- entries for targeting rules and our defensibility strategy.

中文简介正在准备中。当前显示原文说明。

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

中文简介正在准备中。当前显示原文说明。

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

中文简介正在准备中。当前显示原文说明。

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

中文简介正在准备中。当前显示原文说明。

Manage environment variables and secrets across development, staging, and production environments. Use when someone needs to audit env vars, sync secrets between environments, detect missing or mismatched variables, rotate credentials, or set up a new environment from an existing one. Trigger words: env vars, environment variables, secrets, .env file, dotenv, config management, secret rotation, missing variable, environment sync.

中文简介正在准备中。当前显示原文说明。

Audits and troubleshoots DNS records for domains including A, AAAA, CNAME, MX, TXT, SPF, DKIM, DMARC, CAA, and NS records. Use when someone needs to verify DNS configuration, debug DNS propagation issues, check email authentication records, or audit domain security. Trigger words: DNS records, dig, nslookup, SPF, DKIM, DMARC, MX records, DNS propagation, nameservers, CAA, domain configuration.

中文简介正在准备中。当前显示原文说明。

Django is a batteries-included Python web framework with an ORM, admin site, authentication, forms and templates. Use when asked to start a Django project, write models, views, URLs or admin, add a REST API with Django REST framework, run migrations, configure settings for production, or write Django tests.

中文简介正在准备中。当前显示原文说明。

Detox is a gray-box end-to-end testing framework for React Native apps: it runs Jest tests against the app on an iOS simulator or Android emulator and waits for the app to go idle before each step. Use when the user wants to set up Detox, write or fix React Native E2E tests, debug a test that hangs or cannot find an element, or run Detox in CI. Also use when the user mentions "detox," "React Native E2E," "gray-box testing," "detox build," or "Wix Detox." For black-box testing of any mobile app, see appium; for simple YAML UI flows, see maestro.

中文简介正在准备中。当前显示原文说明。

Audit project dependencies for outdated packages, security vulnerabilities, and breaking changes. Use when someone asks to "check for outdated packages", "audit dependencies", "find vulnerable dependencies", "plan dependency upgrades", "detect breaking changes", or "update npm packages safely". Analyzes package.json/lock files, cross-references changelogs, and produces ordered upgrade plans.

中文简介正在准备中。当前显示原文说明。

DeepEval is an open-source Python framework that unit-tests LLM applications with pytest-style test cases and LLM-as-a-judge metrics. Use when a user asks to evaluate a RAG chatbot, test LLM answers for relevancy, faithfulness or hallucination, write a custom metric, or run LLM quality checks in CI.

中文简介正在准备中。当前显示原文说明。

Write CI/CD pipelines as code with Dagger — portable, cacheable, container-based pipelines that run locally and in any CI system. Use when someone asks to "write CI pipeline in TypeScript", "portable CI/CD", "run GitHub Actions locally", "Dagger pipeline", "CI as code", "containerized build pipeline", or "test my CI locally before pushing". Covers Dagger SDK (TypeScript/Python), pipeline composition, caching, secrets, and multi-stage builds.

中文简介正在准备中。当前显示原文说明。

Cucumber runs behavior-driven (BDD) tests written as plain-language Gherkin feature files and matches each Given/When/Then step to code. Use when the user wants to write feature files, implement step definitions in JavaScript or TypeScript with cucumber-js, share state through a World, add hooks, tags and profiles, or run BDD scenarios in CI. Also use when the user mentions "cucumber," "BDD," "Gherkin," "feature files," "given-when-then," "step definitions," or "behavior-driven." For contract testing, see pact.

中文简介正在准备中。当前显示原文说明。