메뉴
Your AI development radar — scan the ecosystem for new tools and techniques, then get personalized recommendations. Combines radar-scan and radar-recommend in one command.
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
Scan external sources for AI tools, features, and techniques. Builds a discovery catalogue from dependency changelogs, HN (targeted + firehose), GitHub, YouTube, a people-to-watch list, and your inbox.
Match catalogued AI tools and techniques against your goals and usage patterns. Surfaces personalized recommendations.
Review your radar catalogue in a local web UI — browse, star, dismiss, annotate, and filter discovered tools and insights.
Analyze your Claude Code and Cowork session history to surface actionable workflow insights. Diagnoses failures, identifies automation opportunities, aligns time allocation with goals, and flags repeated knowledge worth saving.
| name | radar |
| description | Your AI development radar — scan the ecosystem for new tools and techniques, then get personalized recommendations. Combines radar-scan and radar-recommend in one command. |
Combined scan + recommend pipeline. Scans external sources for new AI tools and techniques, then matches them against your usage patterns to surface personalized recommendations.
This skill is self-contained — it does not depend on or use the Open Brain plugin, ai-brain MCP, or any external memory service.
This is the default entry point. Use /radar-scan or /radar-recommend separately if you need different scheduling cadences (e.g., scan daily, recommend weekly).
$ARGUMENTS — Optional:
--days N — Lookback window for both scan and recommend (default: 7 for scan, 14 for recommend)--sources <all|feeds|manual> — Source filter for scan phase (default: all). "feeds" = structured external sources (Anthropic, HN, GitHub, YouTube, dependency changelogs). "manual" = process user-added inbox items only.--focus <category> — Category filter for recommend phase (claude-code, mcp, api, agent-sdk, prompting, tooling, workflow, general-ai)Parse from $ARGUMENTS if provided.
Execute the full /radar-scan workflow with the --sources and --days arguments.
Print a brief summary of scan results (new items catalogued, notable finds) before proceeding.
Execute the full /radar-recommend workflow with the --days and --focus arguments.
This phase uses the freshly updated catalogue from Phase 1, ensuring recommendations reflect the latest scan.
Execute the /radar-review workflow with --status new. This lets the user immediately act on freshly scanned and scored items — star the good ones, dismiss noise, add notes.
If there are no new items to review (everything was already reviewed), skip this phase and note: "No new items to review."
After the review session ends (user says "done" or moves on), output a combined summary: