Skip to content
cccskills
FreePublished on GitHub

skill-post-scorer

Evaluate an SNS post draft before publishing with a five-part scorecard. Use past engagement data or general benchmarks to assess the opening, account voice, useful detail, formatting, and readiness, then identify specific improvements.

OriginalShow the original description

对社媒帖子草稿进行互动潜力评分,基于历史表现数据输出结构化评分卡。当用户说"帖子打分""评分""这条能火吗""发布前评估""内容质量分""评分卡""草稿评估"时使用。

和 skill-topic-evaluator 的区别:evaluator 评还没做的选题潜力,本 SKILL 评已写好的草稿质量; 和 skill-social-performance-review 的区别:本 SKILL 评单条草稿(发布前),review 做月度组合复盘(发布后)。

See how to install

Good for

  • Review a post draft before publishing
  • Compare a draft with past high-performing posts
  • Find weaknesses in the opening or structure
  • Revise a weak section and compare scores

Files included (5)

  • SKILL.md6.0 KB
  • EASEL-META.md1.2 KB
  • references/fallback-benchmarks.md3.9 KB
  • references/scoring-criteria.md4.8 KB
  • scripts/score.py4.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

帖子表现评分

对社媒帖子草稿进行互动潜力评分,基于历史表现数据输出结构化评分卡。

加载后立即开始评分流程,不做摘要或等待确认。

输入

用户 prompt 中提供待评分的帖子草稿,支持以下形式:

  • 文本内容:直接粘贴帖子文案
  • 文件路径:指向 outputs/ 中的草稿文件
  • 平台指定:可选,指定目标平台(小红书、抖音、微博、知乎、公众号、B站等)

示例 prompt:

Execute /skill-post-scorer
帖子:
我花了3年时间才明白一个道理:
最好的内容不是"写"出来的,而是"提炼"出来的。
以下是我总结的5个内容提炼方法...

输出

输出代码块格式的评分卡:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
帖子表现评分卡
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
钩子强度        ██████████  8/10
声音匹配度      ███████░░░  7/10
价值密度        ████████░░  8/10
结构与格式      ███████░░░  7/10
发布就绪度      ██████░░░░  6/10
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
总分            36/50
判定            值得发布,建议优化钩子
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

改进建议:
1. [最弱维度] 具体修改建议
2. ...

执行步骤

第一步:获取帖子

读取用户粘贴的帖子内容。如果 prompt 中没有帖子文本,主动询问用户提供。

第二步:加载评分数据

按优先级获取表现数据:

  1. Profile 中的历史数据:检查 === EASEL ACCOUNT PROFILE === 标记,读取 performance_data 路径指向的历史帖子数据
  2. 用户提供数据:询问用户是否有历史帖子导出数据(各平台创作者中心/后台可导出 CSV/Excel,或整理成 JSON 数组)
  3. 通用基准:以上都没有时,使用 references/fallback-benchmarks.md 中的基准数据

第三步:分析高表现帖子

互动分与 Top 10% 筛选交给脚本,LLM 只做特征提炼。 由 scripts/score.py 完成(复用 ../../shared/scripts/social_stats.py 的 engagement_score)。

有历史/用户数据时,把帖子整理成 JSON 数组(每条含点赞与评论字段),调用:

python3 skills/builtin/skill-post-scorer/scripts/score.py top --input history.json
python3 skills/builtin/skill-post-scorer/scripts/score.py top --input history.json --top-pct 5

脚本自动:按 互动分 = 点赞 + 评论×3 逐条计算(字段兼容 likes/reactions/点赞、 comments/评论)、按互动分降序、算出 Top N% 门槛与分布(均值/中位数/最高/最低)、 样本量不足警告。LLM 拿到脚本输出的 Top 帖子后,提取其共性特征:

  • 开头钩子类型(提问、数据、故事、反常识)
  • 文本长度和段落节奏
  • 格式特征(列表、分隔、emoji 使用)
  • 行动号召(CTA)类型
  • 主题分类
  • 句式节奏(长短交替、断句频率)

无历史数据时跳过本步,直接用 references/fallback-benchmarks.md 的通用模式特征。

第四步:五维评分

按 5 个维度打分,每项 1-10 分,总分 50 分。

评分标准详见 references/scoring-criteria.md。

维度评判重点
钩子强度前两句是否能阻止滑动,制造好奇或共鸣
声音匹配度是否契合账号一贯的语气、人设和表达习惯
价值密度每段是否提供具体洞察,而非空泛陈述
结构与格式排版是否适配目标平台的阅读习惯
发布就绪度能否直接发布,还是需要润色或补充

评分纪律:

  • 诚实评分,不做讨好
  • 除非帖子确实匹配 Top 10% 的模式特征,否则不给 8 分以上
  • 有真实数据时用数据说话,没有时明确标注"基于通用基准"

第五步:输出评分卡

按照上方「输出」部分的格式输出评分卡,包含:

  • 五维分数(含进度条可视化)
  • 总分和判定结论
  • 针对最弱维度的具体改进建议

判定标准:

  • 40-50:优秀,直接发布
  • 30-39:值得发布,建议优化标注的弱项
  • 20-29:需要修改,重点改进最弱的 1-2 个维度
  • < 20:建议重写

更细分档(含各边界档的判定措辞)见 references/fallback-benchmarks.md,两处口径一致。

第六步:提供改写服务

输出评分卡后,主动提出:

是否需要我改写得分最低的部分?

如果用户同意,针对最弱维度进行定向改写,保留其他部分不变,改写后重新评分对比。

Profile 感知

有 Profile

  • 读取 voice / tone 字段,作为「声音匹配度」的评判标准
  • 读取 platform 字段,调整「结构与格式」的平台适配规则
  • 读取 performance_data 字段指向的历史数据文件,用真实数据替代通用基准
  • 读取 topics / niche 字段,评估内容是否在账号定位范围内

无 Profile

  • 「声音匹配度」退化为通用可读性评估
  • 「结构与格式」使用通用社媒最佳实践
  • 使用 references/fallback-benchmarks.md 中的基准数据
  • 评分卡末尾附注:"如提供账号 Profile(含历史表现数据),评分将更精准"

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

ai-image-gen

FreeSummary

Generate images from written descriptions, transform existing images with editing instructions, or create several variations. Choose image dimensions and quantity, then save the results using an OpenAI-compatible service or apimart with your own API key.

  • Generating an illustration from a written description
  • Changing an image's background using instructions
  • Creating several variations of an existing image
ZJU-REAL/Easel4KUpdated Oct 21, 2026

ai-music

FreeSummary

Generate background music for short videos, vlogs, and social posts from descriptions of mood, style, and instruments. Download MP3 audio, optionally include sung lyrics, and use shared scripts to trim tracks, adjust loudness, or add music to videos.

  • Generating background music for a vlog intro
  • Creating instrumental music to match a social post
  • Generating a sung track from supplied lyrics
ZJU-REAL/Easel4KUpdated Oct 21, 2026

ai-video-gen

FreeSummary

Create new videos from written scene descriptions or still images using external AI services. Set the aspect ratio and duration, animate a character image, and request generated audio when the selected model supports it.

  • Generate a short video from a scene description
  • Animate a still image
  • Create character motion from a starting image
ZJU-REAL/Easel4KUpdated Oct 21, 2026

asset-manager

FreeSummary

Organize generated images, videos, and text in outputs/ by date, platform, and type. Add tags, search filenames and content, produce asset lists and reports, and preview archive moves before applying them to make past work easier to reuse.

  • Organizing generated assets by date, platform, and type
  • Finding past content through keywords and tags
  • Listing assets for a specific account or platform
ZJU-REAL/Easel4KUpdated Oct 21, 2026

audio-denoise

FreeSummary

Reduce background noise in audio recordings or video soundtracks with three processing levels. Keep the original file, create a cleaned version, and receive a report of the settings used and file details before and after processing.

  • Reducing fan or air conditioner noise in recordings
  • Cleaning speech in podcasts and interviews
  • Reducing noise in a video's audio track
ZJU-REAL/Easel4KUpdated Oct 21, 2026

audio-editing

FreeSummary

Edit audio files by trimming sections, converting formats, matching loudness, or extracting sound from videos. You can also join recordings, add fades, and change playback speed while keeping the original pitch.

  • Trim a recording to the section you need
  • Convert audio formats and match loudness
  • Extract audio from a video
ZJU-REAL/Easel4KUpdated Oct 21, 2026

See all skills by ZJU-REAL

Report a problem with this skill