jianshuo/claude-skills / wjs-x-improving-content
wjs-x-improving-content
VerifiedUse when 王建硕 wants to systematically improve his X (Twitter) content by iterating on the content-generation prompt (prompts/x/prompt.md, used by the every-6h tweet Action) and finding which prompt version produces the highest-reach tweets. Each prompt edit is a git-SHA-versioned, numbered experiment with a hypothesis; tweets are attributed to the version live at post time and judged on median impressions per tweet. Also mines per-tweet impression data for content-feature signals (angle / length / topic) that feed the next prompt edit. North-star = impressions per tweet. Triggers — "改 X 的 prompt", "X 内容改进", "哪版 prompt 最好", "什么内容 impression 高", "improve my tweets", "A/B test the X prompt", "/wjs-x-improving-content".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.2 KB |
| inbox/.gitignore | other | 12 B |
| scripts/_common.pyexecutable | script | 1.5 KB |
| scripts/analyze-content.pyexecutable | script | 4.1 KB |
| scripts/evaluate.pyexecutable | script | 3.1 KB |
| scripts/ingest-tweets.pyexecutable | script | 4.3 KB |
| scripts/ledger.pyexecutable | script | 2.9 KB |
| scripts/scoreboard.pyexecutable | script | 3.7 KB |
| state/.gitignore | other | 6 B |
| state/SCOREBOARD.md | markdown | 1.1 KB |
| state/tweets.jsonl | other | 42.1 KB |
| state/versions.jsonl | other | 523 B |
scripts/ledger.py
View on GitHub#!/usr/bin/env python3
"""Annotate prompt versions with intent + verdict (state/versions.jsonl).
The version *identity* comes from git (prompts/x/prompt.md short-SHA). This ledger
adds the human layer the SHA can't carry: the hypothesis behind each edit and the
final verdict. One line per version.
Subcommands:
register SHA --hypothesis "..." # record a new prompt version + why you changed it
keep SHA [--note ...] # this version won → leave it live
rollback SHA [--note ...] # this version lost → git checkout the prior SHA, mark it
list
Typical flow:
# 1. edit prompts/x/prompt.md, commit it → new SHA appears
# 2. register that SHA with the hypothesis
# 3. let tweets accrue, then evaluate.py → keep / rollback
"""
import argparse, sys
from datetime import date
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent))
from _common import VERSIONS, read_jsonl, write_jsonl # noqa: E402
def save(rows): write_jsonl(VERSIONS, rows)
def get(rows, sha):
for r in rows:
if r["prompt_sha"] == sha:
return r
return None
def cmd_register(a):
rows = read_jsonl(VERSIONS)
if get(rows, a.sha):
sys.exit(f"version {a.sha} already registered.")
n = max((r.get("id", 0) for r in rows), default=0) + 1
rows.append({"id": n, "prompt_sha": a.sha, "hypothesis": a.hypothesis,
"registered": date.today().isoformat(), "status": "active",
"verdict": None, "notes": ""})
save(rows)
print(f"Registered v{n} ({a.sha}): {a.hypothesis}")
def _close(a, status):
rows = read_jsonl(VERSIONS)
r = get(rows, a.sha) or sys.exit(f"version {a.sha} not registered.")
r["status"] = status
if a.note:
r["notes"] = (r["notes"] + " " + a.note).strip()
save(rows)
print(f"{a.sha} -> {status}.")
if status == "rolled_back":
print(f" 还原命令: git -C ~/code/wechat-publish checkout <prior-sha> -- prompts/x/prompt.md")
def cmd_list(a):
rows = read_jsonl(VERSIONS)
for r in rows:
print(f" v{r['id']} {r['prompt_sha']} [{r['status']}] {r.get('verdict') or ''} — {r['hypothesis']}")
if not rows:
print(" (none) — 还没登记任何 prompt 版本")
def main():
ap = argparse.ArgumentParser()
sub = ap.add_subparsers(dest="cmd", required=True)
p = sub.add_parser("register"); p.set_defaults(fn=cmd_register)
p.add_argument("sha"); p.add_argument("--hypothesis", required=True)
p = sub.add_parser("keep"); p.set_defaults(fn=lambda a: _close(a, "kept"))
p.add_argument("sha"); p.add_argument("--note")
p = sub.add_parser("rollback"); p.set_defaults(fn=lambda a: _close(a, "rolled_back"))
p.add_argument("sha"); p.add_argument("--note")
p = sub.add_parser("list"); p.set_defaults(fn=cmd_list)
a = ap.parse_args(); a.fn(a)
if __name__ == "__main__":
main()
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 |