iamzifei/aikey / skills/aikey-mvp
aikey-mvp
VerifiedAI KEY·选题先试水 ——选题 MVP 测试技能。碎片输入(一句话想法/聊天记录/X 见闻/候选选题)→ 生成发 X 用的纯文字测试内容(篇幅不限,内容需要多长写多长,排版清晰)→ 登记测试管道 → 用真实互动数据决定该题进抖音、扩公众号还是淘汰。验证一个想法只花一条文本,不花一条真视频。 触发方式:/aikey-mvp、/发条测试、/试水、/aikey-测试、「发条推测试」「写个 X 短文」「这个想法先试试水」「值不值得拍一条」 MVP text-testing: turn a fragment into a plain-text X post (length as the idea needs, well formatted) to cheaply validate a topic before it costs a real video. Trigger: /aikey-mvp, "test this idea on X", "write a short post to validate" —— 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 | 12.0 KB |
| scripts/top_posts.shexecutable | script | 1.2 KB |
scripts/top_posts.sh
View on GitHub#!/bin/bash
# Voice calibration for /aikey-mvp: print your own top-10 X posts by bookmark rate.
# Filters: canonical author + impressions >= 1000 (drop small-sample noise) + not a reply.
# CSV fields: role,bookmark_rate,bookmarks,impressions,url,text
#
# CSV 路径按这个顺序找,第一个存在的就用:
# 1. $ZMM_XPOSTS_CSV (直接指定)
# 2. config.yaml 的 paths.vault_root 下 01-原始素材区/数据/候选池/*素材候选池.csv
# 3. 报错退出 —— 不猜路径
set -euo pipefail
CSV="${ZMM_XPOSTS_CSV:-}"
if [ -z "$CSV" ]; then
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
VAULT="$(sed -n 's/^[[:space:]]*vault_root:[[:space:]]*//p' "$ROOT/config.yaml" 2>/dev/null | tr -d '"'"'"' ' | head -1)"
VAULT="${VAULT/#\~/$HOME}"
[ -n "$VAULT" ] && CSV="$(find "$VAULT/01-原始素材区/数据/候选池" -name '*素材候选池.csv' 2>/dev/null | head -1)"
fi
if [ -z "$CSV" ] || [ ! -f "$CSV" ]; then
echo "找不到 X 帖子 CSV。用 ZMM_XPOSTS_CSV 指一个,或在 config.yaml 里设 paths.vault_root。" >&2
exit 1
fi
awk -F, '$1=="本人(canonical)" && $4>=1000 && $6 !~ /^@/' "$CSV" | sort -t, -k2 -rn | head -10
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: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | 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 |