菜单
Evaluate multiple choices side-by-side based on relevant criteria, then present a comparison the user can act on. Use when the user asks to compare options, choose between alternatives, or weigh up X vs Y.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Day-of-week rotating proactive sweep — Mon=connections / Tue=routines / Wed=skills / Thu=memories / Fri=findings / Sat=cross-cutting / Sun=weekly summary. Forces outward scan instead of inward thrash. Routine-only; load this skill into a daily routine that fires AssistantAgent. Adapted from goanna's caretaker.
Use when an agent has had N consecutive quiet runs with nothing to do. Pivots to bounded inward consolidation (promote findings, refresh memory, audit asks) anchored in own data — NOT generic news summarisation. Adapted from goanna's reverie cycle. Routine-only; loaded by the routine that detects the quiet condition.
Use to track open questions you owe the user (asks) and time-bounded commitments you owe yourself (tasks). Write OPEN entries when you commit; promote to CLOSED when answered/done. Survives session compaction. Adapted from goanna's asks.md/tasks.md pattern.
Reviewer criteria for AI-generated code via with_review. Checks for security issues (injection, auth bypass, secret leakage), correctness, and project conventions. Use as criteria.skill when generating code that touches data, auth, or external systems.
Reviewer criteria for outbound email drafts via with_review. Checks tone-recipient match, professionalism, no AI tells, no placeholder leakage. Use as criteria.skill argument when reviewing email drafts before send.
Reviewer criteria for AI-generated summaries via with_review. Checks faithfulness to source, no hallucinated facts, appropriate length, key points preserved. Use as criteria.skill when summarising articles, documents, transcripts, or batch-task outputs.
| name | compare-options |
| description | Evaluate multiple choices side-by-side based on relevant criteria, then present a comparison the user can act on. Use when the user asks to compare options, choose between alternatives, or weigh up X vs Y. |
Identify the options and criteria:
ask_questions.ask_questions (multi-select).Research each option in parallel:
web_search for reviews + browser_extract on official pages for specsweb_research skill on each optionScore each option against each criterion:
run_skill_script with this skill and path scripts/score.js,
passing {"weights": {...}, "options": [{"name", "scores": {...}}]}
as stdin (scores 0-10). It returns the ranked totals, winner, and
margin deterministically.Display the comparison:
show_comparison with each option as a card, features as the criteriahighlight: true)cta buttons so the user can pickAdd a recommendation — one paragraph explaining your top pick and why, including who would prefer the alternative. Be specific about the trade-offs.
Offer to dig deeper via offer_choices: