메뉴
Search the web, evaluate sources, and synthesize findings with citations
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
PR-focused code review with structured checklist, severity ratings, and actionable feedback
Use when a code review finding needs proof — write a focused test in JavaScript or Go that either confirms the issue is real or exposes it as over-engineering hyperbole. Trigger after code-review or code-review-skill findings are presented and evidence is requested.
Use when reviewing Dependabot alerts, npm audit findings, govulncheck output, or CVE reports on a JavaScript/Node.js or Go project — especially when triaging multiple alerts across direct and transitive dependencies to assess real-world risk and produce a remediation plan.
Produce data-driven software delivery estimates by analyzing historical JIRA tickets, git activity, and engineer track records, then matching the new work against the most similar past tickets. Use this skill whenever the user asks "how long will this take", wants to estimate a piece of work, scope an epic, plan a sprint, or estimate delivery for JIRA stories or a Figma design. Also use whenever the user wants developer-to-work assignment recommendations based on history, wants to optimize an estimate by adding or reallocating engineers, or asks "what's the fastest way to ship this" or "who should work on this". Especially trigger when the user provides JIRA ticket IDs, JIRA story links, or Figma designs together with any indication of a team that will execute the work.
Use when auditing an existing test suite for quality and coverage gaps, evaluating Playwright migration readiness, scoring automation against a world-class e-commerce standard, or guiding the creation of new tests. Applicable to Selenium, WebdriverIO, and Playwright suites.
AI-powered observability with Grafana MCP — translates natural language to metrics, logs, and trace queries to diagnose issues like a senior SRE
| name | search-web |
| description | Search the web, evaluate sources, and synthesize findings with citations |
Search the web and synthesize an answer for: $ARGUMENTS
Parse the Query - Extract the core question or topic from $ARGUMENTS. Identify keywords and intent.
Search - Use the WebSearch tool to find relevant results. Run multiple searches with varied keywords if the first set of results is insufficient.
Evaluate Sources - Prioritize official documentation, peer-reviewed sources, and well-known technical references. Discard results that are outdated, low-quality, or irrelevant.
Fetch Key Pages - Use WebFetch on the most promising URLs to get full content when search snippets are not enough.
Synthesize Findings - Combine information from multiple sources into a clear, direct answer. Resolve conflicting information by noting the disagreement and which source is more authoritative.
Cite Sources - Include URLs for every claim so the user can verify.
## Answer
[Clear, direct answer to the query in 1-3 paragraphs]
## Sources
1. [Source title](URL) - [one-line summary of what this source contributed]
2. [Source title](URL) - [one-line summary]
3. [Source title](URL) - [one-line summary]