测试设计、漏洞检测、质量保证（1.3万 个）
Evaluate work produced in the current conversation in two stages: one agent creates criteria tailored to the work, and another scores it with cited evidence. You receive a structured report; the skill does not change the evaluated work.
中文简介正在准备中。当前显示英语简介。
Choose a testing strategy based on an artifact’s behavior, risk, and deployment context. The guide uses decision gates to select test types, then helps shape dependencies and concrete test cases with examples and structured output.
中文简介正在准备中。当前显示英语简介。
Review a previous answer or deliverable for completeness, correctness, risks and opportunities to improve it. The skill adjusts review depth to task complexity, checks claims and dependencies, and turns identified issues into prioritized, actionable refinements.
中文简介正在准备中。当前显示英语简介。
Use this skill after business logic changes, refactoring, or dependency updates to identify failing tests and coordinate repairs. It aims to keep tests aligned with the current implementation while preserving their original purpose and checking the full suite again.
中文简介正在准备中。当前显示英语简介。
Apply a methodology based on public WooYun vulnerability cases to assess business logic in web apps, APIs, and business systems. Map workflows and trust boundaries, form domain-specific hypotheses, perform targeted manual checks, and document evidence, business impact, and remediation.
中文简介正在准备中。当前显示英语简介。
Audit an AIOS by checking how it retrieves information, connects to tools and data, performs key workflows, and runs scheduled work. The skill scores evidence of operational reliability and saves a dated report with prioritized findings and practical improvement checks.
中文简介正在准备中。当前显示英语简介。
Write, review, and fix React Native component tests with React Native Testing Library. Get guidance on rendering, finding elements, simulating user actions, Jest matchers, and async behavior, with patterns matched to RNTL v13 or v14.
中文简介正在准备中。当前显示英语简介。
Inspect and interact with apps on iOS, tvOS, macOS, and Android. The skill can capture screen snapshots, tap, type, and scroll, or extract visible interface information to help with app navigation, verification, and device-based QA.
中文简介正在准备中。当前显示英语简介。
Explore an iOS or Android app, find bugs and usability problems, and document each finding with reproducible steps and screenshots, with optional videos. The result is a structured report that helps teams review observed issues.
中文简介正在准备中。当前显示英语简介。
Generate cloned narration for the content workspace. Use local IndexTTS2 with the canonical lossless Pluviobyte reference for every local video, voice audition, digital-human narration, and subtitle-ready audio render. Preserve MiniMax only for public-facing articles or tutorials that teach users to connect through the relay service; never use MiniMax for local video production.
中文简介正在准备中。当前显示原文说明。
Agent 工作台迁移。把任意项目整理成 Claude Code / Codex / Grok 三端一致、可长期维护的 Agent 工作台：审计规则文件、识别真源、统一命名并生成 bridge。 触发方式：/dbs-agent-migration、/agent迁移、「迁移到 Codex」「迁移到 Claude Code」「迁移到 Grok」「统一 AGENTS.md」「整理 skill bridge」「我的 Agent 工作台很乱」「帮我统一 Claude 和 Codex 和 Grok」 Agent workspace migration. Turn any project into a maintainable Claude Code / Codex / Grok three-host workspace by auditing rule files, establishing source-of-truth skills, normalizing names, and generating bridges. Trigger: /dbs-agent-migration, /agent-migration, "migrate to Codex", "migrate to Claude Code", "migrate to Grok", "fix AGENTS.md", "organize skill bridges"
中文简介正在准备中。当前显示原文说明。
dontbesilent 内容结构化系统。把本地大量文稿、推文、选题、案例和课程稿搭成一个可持续生长的内容结构化工程：先审计内容规模与边界，再建立新工程、复制素材、抽取内容单元、生成主题地图与选题装配稿。 触发方式：/dbs-content-system、/内容结构化系统、「把我的内容做成结构化系统」「把本地素材变成可重组系统」「帮我搭内容资产工程」「我想把旧内容变成可复用资产」 Content structuring system. Audits local content volume, then builds a reusable content knowledge project with units, topic maps, and assembly drafts. Trigger: /dbs-content-system, "build a content structuring system", "turn my archive into reusable assets"
中文简介正在准备中。当前显示原文说明。
dontbesilent 目标清晰化。用维特根斯坦的语言哲学把模糊的目标审计成可检查的交付物。 触发方式：/dbs-goal、/目标、「帮我搞清楚目标」「我想做个人 IP」「我的目标是成为...」「我想变得更...」 Goal clarification using Wittgenstein's philosophy of language. Audits fuzzy goals into checkable deliverables. Trigger: /dbs-goal, "help me clarify my goal", "I want to become...", "my goal is..."
中文简介正在准备中。当前显示原文说明。
When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.
中文简介正在准备中。当前显示原文说明。
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
中文简介正在准备中。当前显示原文说明。
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
中文简介正在准备中。当前显示原文说明。
Adversarial visual-layout audit of a Quarto `.qmd` or Beamer `.tex` deck. Flags overflow, font inconsistency, box fatigue, spacing, and alignment issues. Use when user says "visual audit", "check the layout", "does this overflow?", "look for visual issues", "audit the slides", or after reworking a deck's appearance. Does NOT check writing or pedagogy — pair with `/proofread` or `/pedagogy-review`.
中文简介正在准备中。当前显示原文说明。
Qualify a check before it is allowed to clear anything — prove it can detect the failure it is meant to catch. Seeds known defects into a copy of a real artifact plus a clean control, runs the checker, and reports recall and false-positive rate into a qualification ledger. Use when the user says "does this check work", "qualify the gate", "test my reviewer", "seed defects", "vaccinate", "qualify the checks", "can I trust this review", "does it pass for the right reason", or before relying on any automated check or referee simulation for a decision that matters. NOT a code fixer and NOT a reviewer itself — it grades the grader.
中文简介正在准备中。当前显示原文说明。
Extract a written voice profile from your own prior papers, then use it to keep new drafts sounding like you. Reads a corpus one document at a time via subagents, produces a reusable profile on disk (lexicon, sentence rhythm, how you open and close, hedging habits, deliberate quirks), and audits a draft against it. Use when the user says "make this sound like me", "match my voice", "profile my writing", "why does this draft not sound like my papers", or before drafting prose that will carry their name. The positive counterpart to /humanize, which only detects AI tells.
中文简介正在准备中。当前显示原文说明。
Translate a Beamer `.tex` lecture to a Quarto RevealJS `.qmd` mirror. Multi-phase: TikZ extraction → slide-by-slide translation → citation conversion → automatic QA parity check. Use when user says "translate to quarto", "port to revealjs", "make an html version", "convert this beamer to quarto", "mirror this lecture in qmd", or after a Beamer deck is ready for web publication. Output lands in `Quarto/`.
中文简介正在准备中。当前显示原文说明。
Prove that the file you are about to send, publish, or hand off IS the thing you mean — before it leaves your hands. Rebuild from source, check integrity, diff the derived artifact against its source, and require the recipient to echo what they received. Use before sending a paper/PDF for review, shipping a release or replication package, handing files to a coauthor or collaborator, uploading anything to an external reviewer or model, or publishing. Prevents an entire review/QA cycle from being spent on defects that exist only in the artifact, not in the work.
中文简介正在准备中。当前显示原文说明。
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
中文简介正在准备中。当前显示原文说明。
Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit findings, or a critique you did not write yourself, especially when the reviewer is a model or when the volume is too large to check by feel.
中文简介正在准备中。当前显示原文说明。
Keeps a project's to-do list and memory in GitHub issues — files each finding (from a review, an audit, or the user) as its own issue without duplicates, lists the open issues that bear on the current work, and closes an issue with a comment recording what was wrong, what was tried, what worked, and how it was fixed. Use when review findings or a list of problems should become tracked work (a paper's misleading claims, a codebase's bugs, improvements for later), when starting or resuming work and deciding what to do next, or when a fix has landed and its issue should be closed with a record. Needs the GitHub CLI; warns before posting to a public repository.
中文简介正在准备中。当前显示原文说明。