economical-visual-tests
Author economical visual tests — full visual coverage in the fewest billable snapshots. Applies to any per-snapshot visual tool (UI Verify, Chromatic, Percy,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-24 00:15
Testing & quality
12,613 results
snmp-pentesting
SNMP service (ports 161/162) penetration testing methodology. Covers SNMP service discovery and version identification, community string enumeration and brute forcing, MIB information extraction (system information/network interfaces/processes/software/users), SNMP write exploitation (configuration modification/command execution), known vulnerability exploitation. When the Agent scans and finds UDP ports 161/162 open, and needs to use SNMP...
hermes-executor-verification
Ad-hoc verification tempfile pattern for executor turns that trigger 'Verification status: unverified'.
workleap-chromatic-best-practices
Workleap's Chromatic best practices for snapshot cost control and CI optimization. Use when auditing, setting up, or fixing Chromatic configurations —…
component-testing
Isolated component testing for React, Vue, and Svelte with Playwright. Use when testing UI components in isolation, testing component interactions, or building…
multi-ai-verification
Multi-layer quality assurance with 5-layer verification pyramid (Rules → Functional → Visual → Integration → Quality Scoring). Independent verification with…
mobile-testing-maestro
Maestro mobile E2E testing - YAML flows, selectors, flow control, environment variables, JavaScript expressions, device interactions, Maestro Studio, Maestro…
app-testing
Test app functionality and mobile responsiveness on localhost or remote live sites using Playwright MCP. Navigates pages, clicks buttons, fills forms, checks…
ai-ab-testing
The A/B testing design assistant is suitable for marketing, product, operations, and software when users ask questions such as "Is this change worth testing?" and need to quickly break down goals, determine priorities, and form executable results. It helps generate conversion issue priorities, copy-ready revisions, and experiment or follow-up action checklists based on input materials.
ai-content-quality-auditor
The copy diagnosis assistant is suitable for content creators, marketing, operations, and content media when users ask questions such as "Can this copy be persuasive?" and need to quickly break down goals, determine priorities, and form executable results, helping generate content diagnosis, structured optimization suggestions, and an executable publishing checklist based on input materials.
ai-minimalist-ui
The visual quality diagnostic assistant is suitable for content creators, marketing professionals, operations teams, and content media when users ask questions such as "Is this image good enough to publish?" and need to quickly break down goals, determine priorities, and form actionable results, helping generate visual/creative diagnostics, prompts or storyboard plans, and publishing specification checks based on input materials.
ai-page-cro
The page conversion diagnostic assistant is suitable for marketing, product, operations, and software when users raise questions such as "why isn't the page converting," need to quickly break down goals, determine priorities, and form actionable results, and helps generate CRO priorities, AB test hypotheses, and CTA rewrites based on input materials.
ai-web-quality-audit
The website quality audit assistant is suitable for technical, product, marketing, and software when users ask questions such as "Is the website quality good enough?" and need to quickly break down goals, determine priorities, and form actionable results, helping generate issue attribution, service improvement suggestions, SOPs, or FAQ checklists based on input materials.
gov-service-faq-quality-check
The Business Diagnosis Assistant is suitable for human resources, managers, operations, and software when users raise questions such as "how should this be done," requiring rapid decomposition of goals, identification of priorities, and formation of executable results, helping generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables based on input materials.
spec-test
Create and run tests for a spec task implementation. Reads task completion criteria from tasks.md, detects existing test patterns, creates test cases, runs…
web3-grep-arsenal
Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific…
5-Whys Root Cause Analysis
This skill should be used when the user asks to "find the root cause", "找根因", "为什么会出现这个问题", "why did this happen", "debug this issue", "排查问题", "analyze this…
chrome-devtools
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance,…
jb-tdd
Use when the user asks for TDD, red-green-refactor, tests-first implementation, or a bug fix/feature with tests first.
release
Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step…
aliyun-chatbot-manage-test
Smoke test for aliyun-chatbot-manage. Validate minimal authentication, API reachability, and one read-only query path.
aliyun-live-manage-test
Smoke test for aliyun-live-manage. Validate minimal authentication, API reachability, and one read-only query path.
aliyun-openapi-discovery-test
Minimal smoke test for product API discovery skill. Validate product pull, merge, and one metadata fetch.
aliyun-qwen-coder-test
Minimal coding-model smoke test for Model Studio Qwen Coder.