jianshuo/claude-skills / wjs-x-increasing-follower
wjs-x-increasing-follower
VerifiedUse when 王建硕 wants to systematically grow his X (Twitter) followers by running numbered, A/B-testable growth experiments and tracking which ones actually work. Every action gets a number, a hypothesis, a target metric, a before-state (for rollback), and a verdict. The North-Star metric is the new-follower ÷ profile-visit ratio (conversion) — every profile change is judged against it. Daily it ingests the X Analytics CSV export, scores each running experiment, and recommends keep / rollback. Triggers — "涨粉", "增加 X 粉丝", "X 涨粉实验", "follower growth", "A/B test my profile", "今天的涨粉检查", "/wjs-x-increasing-follower".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.3 KB |
| inbox/.gitignore | other | 12 B |
| scripts/_common.pyexecutable | script | 1.8 KB |
| scripts/daily-check.shexecutable | script | 1.1 KB |
| scripts/evaluate.pyexecutable | script | 6.6 KB |
| scripts/ingest-csv.pyexecutable | script | 4.7 KB |
| scripts/ledger.pyexecutable | script | 5.3 KB |
| scripts/scoreboard.pyexecutable | script | 4.7 KB |
| state/.gitignore | other | 6 B |
| state/SCOREBOARD.md | markdown | 1.9 KB |
| state/actions.jsonl | other | 3.0 KB |
| state/daily.jsonl | other | 45.0 KB |
scripts/daily-check.sh
View on GitHub#!/usr/bin/env bash
# Mechanical half of the daily check. The agent runs this, then reviews verdicts
# and ASKS before rolling anything back (rollbacks are never silent).
#
# 1. ingest any CSVs sitting in inbox/ (then move them to inbox/done/)
# 2. evaluate active experiments, writing directional verdicts into the ledger
# 3. regenerate state/SCOREBOARD.md
#
# Usage: scripts/daily-check.sh
set -euo pipefail
DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$DIR"
mkdir -p inbox/done
shopt -s nullglob
csvs=(inbox/*.csv inbox/*.CSV)
if (( ${#csvs[@]} )); then
for f in "${csvs[@]}"; do
echo "== ingesting $f =="
python3 scripts/ingest-csv.py "$f"
mv "$f" "inbox/done/$(date +%Y%m%d-%H%M%S)-$(basename "$f")"
done
else
echo "No new CSV in inbox/ — using existing daily data."
fi
echo; echo "== evaluation =="
python3 scripts/evaluate.py --write-verdict
echo; echo "== scoreboard =="
python3 scripts/scoreboard.py >/dev/null
echo "Wrote state/SCOREBOARD.md"
echo
echo ">> If any experiment verdicts as ❌ rollback, surface it to 王建硕 and ASK before reverting."
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 |