Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yehyakin/hermes-skills/jianying-editor-skill)<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/jianying-editor-skill"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/jianying-editor-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/jianying-editor-skill"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/jianying-editor-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.04958 |
| Opus 5 | $0.00021 | $0.02479 |
| Sonnet 5 | $0.00008 | $0.00992 |
| Haiku 4.5 | $0.00004 | $0.00496 |
Grade A, and why
jianying-editor-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JianyingPro/CapCut 草稿生成 (Mac)
关键发现
Mac CapCut 只认 draft_content.json + draft_meta_info.json 是不够的! 必须在同一目录补充完整的 Mac 必需文件,否则草稿不会出现在 CapCut 草稿列表中。
完整文件清单(Mac CapCut 必须全部存在)
| 文件/文件夹 | 类型 | 说明 |
|---|---|---|
draft_content.json |
文件 | 素材+轨道数据 |
draft_meta_info.json |
文件 | 草稿元信息 |
draft_info.json |
文件 | 最关键 — 完整草稿信息(id/name/fps/duration/last_modified_platform) |
draft_settings |
文件 | [General] 格式配置(不是目录) |
attachment_pc_common.json |
文件 | 空结构 JSON |
Resources/ |
目录 | 空目录 |
common_attachment/ |
目录 | 空目录 |
matting/ |
目录 | 空目录 |
smart_crop/ |
目录 | 空目录 |
draft_info.json 关键字段(❗ 容易出错的地方)
{
"canvas_config": {"width": 1080, "height": 1920, "ratio": "original"},
"fps": 30.0,
"duration": 0,
"id": "<UUID>",
"name": "", # ❗ 必须为空字符串!不要写草稿名称
"platform": { # ❗ 必须是 dict,不是字符串 "mac"
"app_id": 3704,
"app_source": "lv",
"app_version": "5.9.0",
"os": "mac",
"os_version": "15.7.5",
"device_id": "b7e0901c24cde96c267ceb6a0787cd5c", # 从工作草稿复制
"hard_disk_id": "a693e420c4f4598ec002ce5dc1615c10",
"mac_address": "9ce451a57ee1c922b745dbb022d91152"
},
"source": "default", # ❗ 必须是 "default",不是 "local"
"last_modified_platform": {
"app_id": 3704,
"app_source": "lv",
"app_version": "5.9.0",
"os": "mac",
"os_version": "15.7.5",
"device_id": "b7e0901c24cde96c267ceb6a0787cd5c", # 从工作草稿复制
"hard_disk_id": "a693e420c4f4598ec002ce5dc1615c10",
"mac_address": "9ce451a57ee1c922b745dbb022d91152"
},
"materials": <从draft_content.json>,
"tracks": <从draft_content.json>,
}
常见错误及症状
| 错误 | 症状 |
|---|---|
platform 写成字符串 "mac" |
CapCut 显示「暂无访问权限」 |
source 写成 "local" |
草稿不显示 |
name 写了草稿名称(非空字符串) |
可能影响识别,必须为空字符串 |
完整生成步骤
import json
import os
import time
draft_dir = "/Users/yehya/Movies/JianyingPro/User Data/Projects/com.lveditor.draft/草稿名称"
os.makedirs(draft_dir, exist_ok=True)
# 1. 已有 draft_content.json + draft_meta_info.json(skill生成)
# 2. 构建 draft_info.json(Mac CapCut 必须)
draft_content = json.load(open(f"{draft_dir}/draft_content.json"))
draft_info = {
"canvas_config": draft_content.get("canvas_config"),
"color_space": -1,
"config": {...}, # 标准 config 对象
"duration": draft_content.get("duration", 0),
"fps": draft_content.get("fps", 30.0),
"id": "<新UUID>",
"name": "草稿名称",
"last_modified_platform": {
"app_id": 3704,
"app_source": "lv",
"app_version": "5.9.0",
"os": "mac",
"os_version": "15.7.5"
},
"materials": draft_content.get("materials", {}),
"tracks": draft_content.get("tracks", []),
"version": "6.0.0"
}
with open(f"{draft_dir}/draft_info.json", "w") as f:
json.dump(draft_info, f, ensure_ascii=False)
# 3. 创建目录
for folder in ["Resources", "common_attachment", "matting", "smart_crop"]:
os.makedirs(f"{draft_dir}/{folder}", exist_ok=True)
# 4. 创建 draft_settings(文件,非目录!)
draft_settings_content = f"""[General]
cloud_last_modify_platform=mac
draft_create_time={int(time.time())}
draft_last_edit_time={int(time.time())}
real_edit_keys=1
real_edit_seconds=0
"""
with open(f"{draft_dir}/draft_settings", "w") as f:
f.write(draft_settings_content)
# 5. 创建 attachment_pc_common.json
attachment_pc_common = {
"ai_packaging_infos": [],
"ai_packaging_report_info": {
"caption_id_list": [],
"task_id": "",
"text_style": "",
"tos_id": "",
"video_category": ""
},
"commercial_music_category_ids": [],
"pc_feature_flag": 0,
"recognize_tasks": [],
"template_item_infos": [],
"unlock_template_ids": []
}
with open(f"{draft_dir}/attachment_pc_common.json", "w") as f:
json.dump(attachment_pc_common, f)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 427 lines · 42 tokens per session scan A 1508d4f942ac
jianying-editor-skill is a skill published in the GitHub repository yehyakin/hermes-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 4,958 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
capcut-edit
Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draftcontent.json, draftinfo.json, or cutting videos.
rough-cut-wiki-video
Create editable rough cuts for any step-by-step tutorial from MP4/MOV footage plus pasted procedure text or a text/Markdown guide. Use for how-to videos, assembly or repair, crafts, cooking, product demonstrations, workplace procedures, training, unboxing, speech-cue trimming, filename ordering, procedure-grounded…
skills
An agent skill that turns a natural-language video topic into a short video with voice-over, subtitles, and transitions. It also creates a Jianying editing-project draft; Jianying is a video-editing app widely used in China.
awesome-mac-maintainer
Maintain the Awesome Mac repository when adding, updating, or relocating app entries across README.md, README-zh.md, README-ja.md, and README-ko.md. Use this when the task requires category selection, multilingual sync, concise listing copy, ordering consistency, or repository-specific curation rules.
subtitle_imitation_skill
A video-writing workflow that rewrites a script to match the style of reference text supplied by the user. It uses the footage analysis and reference sample while keeping the script tied to what is actually shown.
create_profile_style_skill
A workflow for turning a person's video-editing habits into a reusable editing skill file. It examines choices such as pacing, storytelling, audio, subtitles, colour, transitions, and recurring editing rules.