LeoYeAI/agent-master-skills / skills/awesome-poetize-open-blog-automation
poetize-blog-automation
Verified专为开源版 awesome-poetize-open 设计的 POETIZE 博客自动化技能。通过 `/api/api/*` 接口完成文章发布、更新、隐藏、分类标签维护、主题切换、数据分析和 SEO 运维。Use only when the task explicitly targets a POETIZE site or POETIZE admin API workflow. Do not use for generic writing, generic SEO advice, or non-POETIZE CMS work.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.0 KB |
| _meta.json | config | 489 B |
| agents/openai.yaml | config | 656 B |
| assets/article-brief.template.json | config | 526 B |
| assets/ops-brief.template.json | config | 289 B |
| references/creativity-workflow.md | markdown | 944 B |
| references/decision-matrix.md | markdown | 1.2 KB |
| references/evaluation-scenarios.md | markdown | 1.3 KB |
| references/openclaw-setup.md | markdown | 10.8 KB |
| references/poetize-api.md | markdown | 12.9 KB |
| references/strategy-playbook.md | markdown | 1.9 KB |
| scripts/blog_strategy.py | script | 10.0 KB |
| scripts/manage_blog.py | script | 18.2 KB |
| scripts/openclaw_smoke_test.py | script | 2.7 KB |
| scripts/publish_post.py | script | 38.6 KB |
| scripts/render_openclaw_config.py | script | 6.6 KB |
| scripts/run_strategy_evals.py | script | 6.0 KB |
scripts/openclaw_smoke_test.py
View on GitHub#!/usr/bin/env python3
"""Run a read-only smoke test for the Poetize OpenClaw skill runtime contract."""
from __future__ import annotations
import argparse
import json
import os
from typing import Any
from manage_blog import build_url
from publish_post import normalize_base_url, request_json
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Validate the Poetize OpenClaw skill wiring with a read-only API call."
)
parser.add_argument(
"--base-url",
default=os.getenv("POETIZE_BASE_URL"),
help="Poetize base URL. Defaults to POETIZE_BASE_URL.",
)
parser.add_argument(
"--api-key",
default=os.getenv("POETIZE_API_KEY"),
help="Poetize API key. Defaults to POETIZE_API_KEY.",
)
parser.add_argument(
"--size",
type=int,
default=1,
help="How many articles to request in the read-only list call.",
)
parser.add_argument(
"--search-key",
help="Optional search filter passed to list-articles.",
)
return parser.parse_args()
def die(message: str, code: int = 1) -> None:
print(message, file=sys.stderr)
raise SystemExit(code)
def extract_records(response: dict[str, Any]) -> list[dict[str, Any]]:
data = response.get("data")
if isinstance(data, dict):
records = data.get("records")
if isinstance(records, list):
return [item for item in records if isinstance(item, dict)]
return []
def main() -> None:
args = parse_args()
base_url = normalize_base_url(str(args.base_url or ""))
api_key = str(args.api_key or "").strip()
if not base_url:
die("Missing --base-url or POETIZE_BASE_URL.")
if not api_key:
die("Missing --api-key or POETIZE_API_KEY.")
params: dict[str, Any] = {"current": 1, "size": args.size}
if args.search_key:
params["searchKey"] = args.search_key
checked_endpoint = build_url(base_url, "/api/api/article/list", params)
response = request_json(
"GET",
checked_endpoint,
api_key,
)
if response.get("code") != 200:
die(
"Smoke test API call did not return code 200:\n"
+ json.dumps(response, ensure_ascii=False, indent=2)
)
records = extract_records(response)
summary = {
"status": "ok",
"checkedEndpoint": checked_endpoint,
"baseUrl": base_url,
"recordsReturned": len(records),
"responseCode": response.get("code"),
"responseMessage": response.get("message"),
}
print(json.dumps(summary, ensure_ascii=False, indent=2))
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies. | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |
| meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要". | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |