Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HK-hub/AgentSkillsnpx agentmods add skills/hk-hub/agentskills/report-generatorWrote 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/hk-hub/agentskills/report-generator)<a href="https://agentmods.dev/skills/hk-hub/agentskills/report-generator"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/report-generator.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01097 |
| Opus 5 | $0.00044 | $0.00549 |
| Sonnet 5 | $0.00018 | $0.00219 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
report-generator 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 3d 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.
This is a copy
100% identical to report-generator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频分析报告生成 (Report Generator)
概述
视频分析报告生成技能将分镜拆解数据和(可选的)钩子分析结果整合为一份专业的 Markdown 格式分析报告。报告包含视频基本信息、前三秒钩子评分、分镜概览表格、BGM 分析、场景分析和平台推荐等章节。
适用场景
- 视频分析交付:为客户或团队生成完整的视频分析文档
- 创意复盘:生成结构化的视频内容复盘报告
- 竞品报告:批量生成竞品视频分析报告
使用步骤
完整报告(分镜 + 钩子分析)
# 1. 准备分镜拆解数据和钩子分析数据(JSON 文件)
# 2. 生成报告
python scripts/generate_report.py breakdown.json hook_analysis.json
# 3. 保存到文件
python scripts/generate_report.py breakdown.json hook_analysis.json > report.md
仅分镜报告(无钩子分析)
python scripts/generate_report.py breakdown.json
报告结构
生成的报告包含以下章节:
# 视频分析报告
## 基本信息
- 视频时长、分镜数量、分辨率
## 前三秒钩子分析(核心)
- 综合评分
- 5维度评分表格
- 钩子类型
- 优势/不足/优化建议
- 留存预测
## 分镜概览
- 前10个分镜的概览表格
## BGM 分析
- 音乐风格、情绪基调、节拍
## 场景分析
- 主要场景、视频风格、目标受众
- 平台推荐
报告生成时间
输入格式
breakdown.json(必需)
{
"duration": 30.5,
"segment_count": 12,
"resolution": "1920x1080",
"segments": [...],
"bgm_analysis": {
"music_style": {"primary": "流行"},
"emotion": {"primary": "欢快"},
"tempo": {"bpm_estimate": 120, "pace": "中速"}
},
"scene_analysis": {
"primary_scene": "室内",
"video_style": {"overall": "生活方式", "target_audience": ["年轻人"]},
"platform_recommendations": [...]
}
}
hook_analysis.json(可选)
{
"overall_score": 7.5,
"visual_impact": 8.0,
"visual_comment": "评价...",
"language_hook": 7.0,
"language_comment": "评价...",
"emotion_trigger": 7.5,
"emotion_comment": "评价...",
"information_density": 7.0,
"info_comment": "评价...",
"rhythm_control": 8.0,
"rhythm_comment": "评价...",
"hook_type": "好奇型",
"strengths": ["优点1", "优点2"],
"weaknesses": ["不足1"],
"suggestions": ["建议1", "建议2"],
"retention_prediction": "中:50-70%,因为..."
}
输出格式
Markdown 格式的完整报告文本,直接输出到 stdout。
示例
# 完整流程
python ../video-breakdown-skill/scripts/process_video.py "https://example.com/video.mp4" > breakdown.json
cat breakdown.json | python ../hook-analyzer-skill/scripts/analyze_hook_segments.py - > hooks.json
# (hooks.json 需经 LLM 评分后得到 hook_analysis.json)
python scripts/generate_report.py breakdown.json hook_analysis.json > report.md
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 141 lines · 89 tokens per session scan A 8cf6a4ccf7b7
report-generator is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 19d ago), licensed MIT. It adds 89 tokens to every session and 1,097 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to report-generator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
minimax-h3-reference-video-prompt
Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference role. Use the official six-section full-reference format for character/person/object consistency, scene/style/action/camera/storyboard/voice/audio…
minimax-h3-keyframe-video-prompt
Narrow downstream MiniMax H3 specialist for pure I2VA, FL2VA, and L2VA boundary-frame prompts. Use only after minimax-h3-creative-director verifies that the user explicitly declared the images as literal first/last frames and that they have no character, identity, person, object, costume, scene, style, voice, action…
minimax-h3-multishot-planner
Non-skippable planning-only MiniMax H3 subskill used by minimax-h3-creative-director before final prompt formatting. Invoke when the user explicitly requests multiple shots, scenes, cuts, montage, or shot-by-shot design, or when a video of at least 10 seconds has no declared single-shot/multishot preference and the…
minimax-h3-text-video-prompt
Downstream MiniMax H3 specialist for professional text-to-video (T2VA) prompts using the official three-field format. Use after minimax-h3-creative-director routes a request with no image, video, or audio reference asset, or when this skill is explicitly invoked for a text-only idea, script, or storyboard requiring an…
minimax-h3-creative-director
Primary mandatory entrypoint for every MiniMax H3 video-generation request. Use before any other H3 skill for creation, animation, extension, editing, restyling, reference, or prompt review. It reads the official h3-prompt-writing specification, defaults image-based work to full-reference consistency, permits pure…
minimax-h3-prompt-reviewer
Downstream MiniMax H3 specialist that audits, repairs, and rewrites T2VA, I2VA, FL2VA, L2VA, and full-reference prompts into an official structured format. Use after minimax-h3-creative-director routes an existing prompt for diagnosis or repair, or when explicitly invoked for formatting, timeline, camera, dialogue…