测试与 QA

car-sales-data-engineering-analytics

5testing-qa

Process, clean, and analyze car sales data with statistical modeling and interactive Streamlit dashboards for business insights.

reason-machines

troubleshooting-flows

4testing-qa

Diagnose and resolve Celigo flow failures -- total failures, partial errors, stuck jobs, empty runs, and performance issues. Use when a flow is failing, producing errors, returning no data, or running slowly.

celigo

layer-quality

4testing-qa

Use when judging Layer output before it ships: scoring generated files against a workspace's output scoring rules, reading back verdicts on a file, reviewing a batch against the brief, or choosing which candidate to deliver. Also when a studio has automated quality standards, or a set must be checked for consistency before handoff. Keywords: quality gate, scoring, review, batch, verdict, approve, QA, consistency check.

layerai

screenci

Create, show, and guide with ScreenCI videos in an already-initialized project by editing `.screenci.ts` files and running the Screenci workflow.

screenci

web-debug

You MUST use this when interacting with or testing local web applications with Playwright - verifying frontend functionality, debugging UI behavior, capturing browser screenshots, or viewing browser console logs.

typescript

You MUST use this when configuring tsconfig, resolving compiler errors, debugging slow type-checking, fixing module resolution or ESM/CJS issues, hardening strictness, migrating JavaScript or a new compiler major, or setting up type-checking in monorepos. Not for general feature work in TypeScript code.

vitest

You MUST use this when configuring, writing, debugging, running, migrating, or auditing Vitest tests in JavaScript/TypeScript projects - Vite, Vue, Nuxt, React, Next.js, Node libraries, workspaces, coverage, mocks, snapshots, flaky tests, CI parity, or Jest migration.

scope-triage

You MUST use this when a request needs design decisions before code - new features, product or UX behavior, architecture changes, unclear success criteria, or two materially different approaches. Explicitly specified mechanical refactors, localized fixes with known expected behavior, and single-outcome config changes go straight to implementation.

plan-crafting

You MUST use this when an approved design or settled requirements need a detailed multi-step implementation plan before code changes begin.

anti-detect-browser

启动和管理反检测浏览器，使用独特的真实设备指纹，用于多账户操作、网页抓取、广告验证和AI代理自动化。当用户需要运行多个具有不同身份的浏览器会话、管理持久化浏览器配置文件、跨账户自动化任务或构建需要浏览器指纹隔离的代理工作流时使用。当用户提到 antibrow、反检测浏览器或指纹浏览器时也使用。

antibrow

gpt-image-2

完整的 OpenAI 兼容 GPT Image 2 覆盖，涵盖 images/generations、images/edits 以及使用 image_generation 工具的 responses。当一次性图像助手不够用时使用——文本转图像、蒙版编辑、多图像批次、流式传输、partial_images 以及混合文本+图像的 Responses 流程。读取 .env 并尊重进程环境变量；可与任何 OpenAI 兼容网关配合使用。

gargantuax

is-this-photo-real

Verify whether an image or video is authentic, original and correctly captioned — provenance checks, error level analysis, noise and JPEG compression analysis, clone and copy-move detection, lighting and shadow consistency, C2PA Content Credentials, deepfake and AI-generation tells, and the honest limits of AI-detector tools. Use when fact-checking a photo or video, checking for a deepfake or AI-generated image, spotting manipulation, or testing whether footage is recycled or miscaptioned. Applies to KYC and onboarding fraud, insurance claim review, disinformation analysis, and evidence admissibility. Reference at useosint.com/skills/is-this-photo-real.

useosint

dotnet-10-csharp-14

Use when building .NET 10 or C# 14 applications; when using minimal APIs, modular monolith patterns, or feature folders; when implementing HTTP resilience, Options pattern, Channels, or validation; when seeing outdated patterns like old extension method syntax

mhagrelius

task-workflow

Canonical workflow for a task. Read and follow strictly end to end while working on the task.

customware-ai

review-fix-address-bots

Integrate the PR base, run persistent read-only reviewers, fix and re-review findings, validate with repo-native commands, address review bots, and compare model quality.

biw

developer-tutorial

Writes or audits a teaching tutorial for a developer product - one new concept per step, checkpoints the learner can verify and resume from, guidance that fades, troubleshooting hooks, and a demonstrable skill at the end. Use whenever the user mentions a tutorial, a build-along or hands-on guide, a "learn X by building Y" article, a workshop or lab handout, a developer course lesson, or says nobody finishes their tutorial - even if they just say "write a guide that teaches this". Do NOT use for a zero-to-first-success quickstart (samber/developer-relations-skills@developer-quickstart-guide) or a video script (samber/developer-relations-skills@technical-video-script).

api-reference-quality

Audit a published API reference at the endpoint level against its spec surface - every operation, parameter, response code, and error documented, request/response examples present, per-language code snippets in parity, try-it affordances working - and install the source-of-truth gates that stop reference drift (spec-driven generation, OpenAPI lint, contract tests, snippet parity in CI). Use whenever the user mentions API reference docs, OpenAPI docs completeness, undocumented endpoints or error codes, stale or drifting docs, or docs CI gates - even if they never say "reference quality". Endpoint-level reference only. Do NOT use for portal IA and onboarding - use samber/developer-platform-skills@developer-portal-design instead.

update-docs

前回更新コミット (_/.last-update-docs で追跡) からの差分をもとに CLAUDE.md のスキル一覧・リポジトリ構造ツリーを更新する。新スキル追加時、.claude/agents/ や .claude/rules/ の変更時、「ドキュメント更新して」「CLAUDE.md を更新して」などで使用。コード内コメント・ドキュメンテーションコメントの補強を依頼された場合にも参照する指針を含む。

fandhe-ai

event-format-selection

Choose a technical event's structure before anything is scheduled - the event shape (recurring meetup, hackathon, unconference day, single-day or multi-day conference), one program or several (single versus multi-track), workshop-day ratios, the session-format mix (curated talks, workshops, open space, ignite, fireside chats, panels), delivery mode (in-person, virtual, hybrid), and hackathon demo/judging structure. Use whenever asked to pick an event format or concept, decide single-track versus multi-track, weigh hybrid or virtual delivery, compose a session mix, or graduate a meetup into a conference. Structural choice only. Do NOT use for schedule grids, clash avoidance or room-capacity matching - use samber/dev-event-organizer-skills@event-schedule-design.

event-talk-selection

Run the review and selection process on CFP submissions a technical event already collected - committee composition, how blind review executes (platform hiding versus a dedicated anonymizer role) and what it cannot fix, scoring rubrics, multi-round score-to-shortlist-to-program-fit cascades, conflict-of-interest recusal, diversity and first-time-speaker balancing, acceptance-rate management, and accept/decline/waitlist communication. Use whenever the user mentions a program committee, a talk rating grid, blind CFP review, choosing which submitted talks make the programme, reviewer conflicts of interest, or acceptance and rejection emails - even if they never say "selection". Do NOT use to design the call itself - use samber/dev-event-organizer-skills@event-cfp-design.

indexion-sdd

1testing-qa

Generate SDD requirements from RFCs/specs and quantitatively verify implementation conformance. spec draft → spec align → spec verify → automated validation loop with codex/claude. Operate spec-to-impl drift gates as CI checks.

trkbt10

indexion-kgf

1testing-qa

调试和检查 KGF 规范——查看源文件的词法分析结果、解析树和提取的边。在添加/修复语言支持或 indexion 的分析输出异常时使用。

trkbt10

claude-brainrot

1testing-qa

始终在线的自动梗图投放器。一个 UserPromptSubmit 钩子在每次用户消息时触发，指示 Claude 在每次回复中投放多个梗图——1-3 个图像+声音组合加上 1-5 个纯声音触发，根据回复长度缩放。每个回答都带有脑腐。无需调用；自动加载并保持激活。吐槽通过梗图本身传达，从不使用文字。自包含技能——目录和资源位于此技能文件夹中。

marks97