测试设计、漏洞检测、质量保证（1.3万 个）
Analyze catastrophe modeling systems for natural disaster exposure, PML estimation, and reinsurance optimization. Use when: 'assess cat model', 'evaluate disaster exposure', 'review PML calculations', 'audit reinsurance program', 'check exposure data quality', 'analyze hurricane/earthquake risk models', 'evaluate Oasis or RMS setup'.
中文简介正在准备中。当前显示原文说明。
Analyzes mobile app binary size -- asset audit for unused images and font subsetting, code stripping with ProGuard and tree-shaking, on-demand resources, dynamic feature modules, and app thinning strategies..
中文简介正在准备中。当前显示原文说明。
Audit curriculum management software for learning outcome alignment, pacing guide optimization, standards coverage mapping (Common Core, NGSS, state standards), differentiation support, assessment design quality, and content gap detection across grade levels and subjects..
中文简介正在准备中。当前显示原文说明。
Audit legal case prediction systems for bias, fairness, accuracy, and ethical guardrails. Use when: 'check my prediction model for bias', 'audit case outcome fairness', 'evaluate legal ML model', 'review sentencing prediction ethics', 'analyze bail risk algorithm', 'fairness metrics for justice system AI'.
中文简介正在准备中。当前显示原文说明。
Audit construction project management software for budget tracking accuracy, earned value management (EVM) formula correctness, risk factor modeling, schedule-cost integration, change order workflow completeness, and early warning detection..
中文简介正在准备中。当前显示原文说明。
Analyze content engagement metrics, audience retention, attribution models, A/B test results, and recommendation engine effectiveness. Triggers: 'audit content metrics', 'evaluate recommendation engine', 'review retention curves', 'assess content A/B tests'.
中文简介正在准备中。当前显示原文说明。
Audit an ecommerce checkout flow against the 2026 conversion playbook. Triggers: "checkout audit", "checkout optimization", "Shopify checkout", "Stripe checkout", "Apple Pay".
中文简介正在准备中。当前显示原文说明。
Audit mental health crisis monitoring systems for risk signal detection accuracy, escalation protocol completeness, safety planning integration, crisis team coordination, and ethical guardrail enforcement..
中文简介正在准备中。当前显示原文说明。
Analyze commodity pricing and trading systems including forward curves, option models, position management, risk metrics, and regulatory reporting. Triggers: 'review pricing models', 'audit trading system', 'evaluate VaR implementation', 'check commodity risk management'.
中文简介正在准备中。当前显示原文说明。
Analyze compliance operations for regulatory change tracking, control mapping, policy management, audit readiness, and training compliance. Triggers: 'audit compliance program', 'assess GRC platform', 'review regulatory change management', 'check control framework'.
中文简介正在准备中。当前显示原文说明。
Audit emergency and crisis triage systems for call prioritization accuracy, resource dispatching algorithm quality, severity classification model evaluation, response time optimization, geographic coverage analysis, mutual aid protocol readiness, and post-incident review workflows..
中文简介正在准备中。当前显示原文说明。
Implement or change ROS 2 Jazzy packages, nodes, interfaces, launch files and configuration in a colcon workspace. Use for building and validating a development change, including tests that report success without running. For a live QoS, TF, IMU or odometry fault, use ros2-troubleshooting.
中文简介正在准备中。当前显示原文说明。
N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' / 'adversarial empirical review'. Do NOT auto-trigger on generic 'review my results', 'check my tables', or manuscript-editing requests. For prose-style refinement use style-emulation instead; this skill AUDITS WHETHER THE TABLES ARE CORRECT — that each number in the tables is what the analysis code computes, reproduces from the data, and is internally consistent. It is an empirical + code review: the manuscript is read only to resolve table numbering, and prose is not examined.
中文简介正在准备中。当前显示原文说明。
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
中文简介正在准备中。当前显示原文说明。
Audit Apple-platform applications, proposed features, code changes, App Store metadata, privacy practices, and submission readiness against Apple's current App Review Guidelines. Use during feature planning, PR review, pre-release QA, App Store rejection triage, or whenever StoreKit, HealthKit, permissions, authentication, user-generated content, or App Review policy matters.
中文简介正在准备中。当前显示原文说明。
Use @vercel/error to design, implement, migrate, audit, or review structured TypeScript errors. Trigger when a project uses or adopts the package, or when work involves its codes, fields, factories, HTTP APIs, telemetry, or terminal output. Use native Error for local failures that need no stable identity, recovery guidance, observability, or transport.
中文简介正在准备中。当前显示原文说明。
Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-local` skill + script, and the installed driver skill. Use when someone says "set up verification", "make this repo verifiable", "scaffold a verify skill", "set up the verifier".
中文简介正在准备中。当前显示原文说明。
Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.
中文简介正在准备中。当前显示原文说明。
Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want system-level tests — "set up e2e", "add end-to-end tests", "scaffold a test gate".
中文简介正在准备中。当前显示原文说明。
Short alias for external-site-profile-learning. Use this when investigating, adding, validating, or debugging external website profiles for the 99idea Playwright browser demo.
中文简介正在准备中。当前显示原文说明。
**WORKFLOW SKILL** — Risk awareness before action. USE FOR: assessing risks (security, data integrity, compatibility, operational, reversibility) of any task at variable depth. Accepts weight: Light (quick scan), Standard (dimensional analysis), Deep (full Risk Radar with evidence). Can be invoked multiple times in the same flow with increasing weight. DO NOT USE FOR: penetration testing, compliance audits, static security analysis tools.
中文简介正在准备中。当前显示原文说明。
Spin up a new loop (domain) in a file-based knowledge base — bootstrap the substrate if it's missing, gather the loop's charter, scaffold domains/<loop>/README.md, then do ONE real test run and record it in the loop's Timeline and LOG.md. Use when the user says "set up a new loop", "create a domain", "start a new beat/workstream", or names a recurring job they want the agent to own.
中文简介正在准备中。当前显示原文说明。
Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup. Each agent gets its own full stack (own DB + dev server) and an in-box browser for e2e, so concurrent loops never collide on ports/state. Sets up the snapshot image, .crabbox.yaml, an idempotent setup.sh (also boots the stack locally), and a cbx.sh wrapper. Use when the user says "set up crabbox", "give each agent its own box", "add cloud testing", "make this repo testable in the cloud / on Daytona", "parallel-test this", or when setup-codebase-harness needs true per-agent isolation.
中文简介正在准备中。当前显示原文说明。
Use this skill to audit CLI adapter projects (like opencli) for missing output fields, then batch-generate fixes and submit PRs. Turns AI agents into adapter quality reviewers.
中文简介正在准备中。当前显示原文说明。