iamzifei/aikey / skills/aikey-topic
aikey-topic
VerifiedAI KEY·今天拍什么 ——短视频选题技能。先探寻现象、检验假设、比较解释,把问题转成观众在意的选择。交互式选题:供需判定 + 对标信号 + 本人真实数据佐证 + 配比检查,不一键生成选题清单。 触发方式:/aikey-topic、/拍什么、/选题、/aikey-选题、「今天拍什么」「帮我出选题」「这个题能不能做」「有个想法你帮我判断下」「这题只有一头」「这题没劲」「帮我把它讲出两头来」 Topic selection for short videos: supply-demand test, benchmark signals, real data evidence. Trigger: /aikey-topic, "what topic should I shoot", "is this topic worth making" —— AI KEY · 不给公式,给判据。每条规则都标了实测代价。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 20.0 KB |
| evals/README.md | markdown | 1.2 KB |
| evals/sample-01-找拉力.md | markdown | 422 B |
| evals/sample-01-答案.md | markdown | 1.1 KB |
| evals/sample-02-三选一.md | markdown | 515 B |
| evals/sample-02-答案.md | markdown | 952 B |
| references/常识缺口法.md | markdown | 37.9 KB |
| references/找拉力.md | markdown | 7.3 KB |
| references/挖真事.md | markdown | 3.3 KB |
| references/规则卡.md | markdown | 11.7 KB |
| references/议程与合集.md | markdown | 11.0 KB |
| references/选题三路.md | markdown | 8.4 KB |
| references/问题探寻与共鸣.md | markdown | 6.1 KB |
evals/sample-01-答案.md
View on GitHub# 测试稿 01 · 答案(只给评分者)
## 必须做到(5)
| # | 要求 |
|---|---|
| T1 | 判定「35 岁转行」是话题不是题,先写出目标观众的默认答案(例如「转行风险太大 / 不转就废了」之一) |
| T2 | 拉力来源三选一并说清(多半是「两个时间尺度打架」:前两年腰斩 vs 第三年回本;或「有人在付账但不在场」:家人 / 房贷) |
| T3 | 替对面写一句讲得通的话(「不转」那一方的合理理由),且对面不是目标观众本人 |
| T4 | 压成一句会有人反驳的话,并写出谁会反驳、会说什么 |
| T5 | 给出三个版本(稳 / 带刺 / 押注),并注明推出来的题仍要回模式 B 过供需 |
## 不许出现(3)
| # | 要求 |
|---|---|
| N1 | 不出现「六型冲突」「四层争点」之类的分类表 |
| N2 | 不把「不转行的人」或「35 岁的中层」立成靶子 / 敌人 |
| N3 | 不用「利益冲突」「认知差」这类抽象词收尾,第五问必须是画面句 |
## 评分
T1–T5 各 1 分;N 违反各扣 1 分。满分 5,通过线 4 且 N 不扣。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |