BD tencentcloud-cos
腾讯云对象存储(COS)和数据万象(CI)集成技能。覆盖文件存储管理、AI处理和知识库三大核心场景。 存储场景：上传文件到云端、下载云端文件、批量管理存储桶文件、获取文件签名链接分享、查看文件元信息、查询数据万象及子服务开通状态。 图片处理场景：图片质量评估打分、AI超分辨率放大、AI智能裁剪、二维码/条形码识别、添加文字水印、获取图片EXIF信息、缩放、裁剪、旋转、格式转换。 文档处理场景：Word/Excel/PPT等办公文档转PDF、文档预览。 媒体处理场景：视频智能封面提取、视频转码、视频截帧、获取媒体信息。 内容审核场景：图片/视频/音频/文本/文档内容审核，检测违规内容。 智能语音场景：语音识别（音频转文字）、语音合成（文字转语音）、音频降噪、人声分离。 文件处理场景：文件哈希计算、文件压缩打包、文件解压。 内容识别场景：描述单个图片或视频文件的内容、图片标签识别、OCR文字识别、视频ASR/OCR和粗分类。 知识库场景：一键创建知识库、上传文档到知识库、从知识库检索内容片段。 智能检索场景：MetaInsight以图搜图、以文搜图、以文搜视频片段、人脸搜索、元数据检索、多模态检索（文档/图片/视频）。 控制台功能引导场景：当前 Skill 无法直接满足时，为大量数据迁移、数据导出、拓展功能、数据备份、SDK、 具身智能生态和湖仓生态提供对应的 COS 控制台入口。 当用户提到以下关键词或口语化表述时应触发此技能： 上传到COS、腾讯云存储、对象存储、云存储、存储桶、Bucket、 图片处理、图片压缩、图片放大、超分辨率、抠图、裁剪、二维码识别、水印、 文档转换、转PDF、视频封面、智能封面、以图搜图、图片搜索、MetaInsight、 COS上传、COS下载、签名URL、腾讯云文件、数据万象、CI处理、 内容审核、图片审核、视频审核、文本审核、语音识别、语音合成、降噪、人声分离、 OCR、文字识别、图片标签、文件内容描述、这个文件讲了什么、图片里有什么、视频讲了什么、 创建知识库、建一个知识库、上传到知识库、往知识库里加文件、查询知识库、 从知识库找、搜索知识库、知识库检索、文档检索、文档搜索、数据迁移、批量迁移、 数据导出、数据备份、COS SDK、具身智能生态、湖仓生态、COS 拓展功能。 即使用户没有明确提到COS或腾讯云，只要涉及"把文件传到云上"、"生成下载链接"、 "处理云端图片"、"帮我建个知识库"、"把文档放进知识库"、"从知识库里搜一下"、 "加密COS凭证"、"COS密钥不安全"、"加密一下COS密钥"、"保护COS密钥"等意图，也应该触发此技能。
As a process D 37/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1111 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7153 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "message" - note
frontmatter-keyunknown frontmatter key "client_commands" - note
frontmatter-keyunknown frontmatter key "conditions" - note
frontmatter-keyunknown frontmatter key "defaultMode"
Process rating: all ten parameters 37/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 49 mutating operations with no state check
- 40Consistency. Frontmatter name (tencentcloud-cos) differs from the folder (tencent-cos-skill)
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 7153 tokens
- 100Steps. 101 steps
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1110: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -220 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Structure: 42 headings
- +3Step-by-step instructions: 101 items
- +4Has examples (27 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 41.