一键导入
autoresearch
Use when you want to benchmark and improve an existing repo skill through repeated evals, prompt mutations, and score tracking.
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。
菜单
Use when you want to benchmark and improve an existing repo skill through repeated evals, prompt mutations, and score tracking.
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
Use when you want a complete Product Hunt launch package for a developer tool, including listing assets (tagline, description, maker comment, visual spec, social proof) and a dated launch plan with workstreams, runsheet, and post launch sequence.
End to end Product Hunt launch skill for developer tools. Generates listing assets (tagline, description, maker comment, visual asset spec, social proof) and a dated launch plan with workstreams, asset inventory, day of runsheet, and post launch sequence. Use when: prepare a Product Hunt launch, plan a PH launch, write PH listing copy, build PH launch checklist, generate PH launch plan.
6-step framework for engineering viral product launches on X. Covers emotional positioning, copy scoring, algorithmic gamification, and 48-hour engagement strategy. Use when: prepare for a launch, launch playbook, viral marketing campaign, launch on X, product launch strategy, write launch copy.
6-step framework for engineering viral product launches on X. Covers emotional positioning, copy scoring, algorithmic gamification, and 48-hour engagement strategy. Use when: prepare for a launch, launch playbook, viral marketing campaign, launch on X, product launch strategy, write launch copy.
Use when you want campaign performance reviewed against benchmarks, with a health score and prioritized optimization recommendations.
Use when you want paid ad copy for Google, Meta, or LinkedIn, including headlines, descriptions, and image briefs.
| name | autoresearch |
| description | Use when you want to benchmark and improve an existing repo skill through repeated evals, prompt mutations, and score tracking. |
This is a Codex compatibility wrapper.
Follow the canonical workflow in:
../../../.claude/skills/autoresearch/SKILL.mdBefore starting:
../../../AGENTS.md../../../.claude/rules/content-guidelines.mddocs/inputs-local/ over docs/inputs/ when the local directory existsCompatibility rule:
../../../.claude/skills/autoresearch/SKILL.md as the source of truth for the workflow