SKILLEMALL.ai
GitHub ↗ RU Sign in

BF yinxiang-skill

This skill should be used when the user says "授权印象笔记"、"印象笔记授权"、"配置印象笔记" to guide the authorization flow. Use this skill when the user says "记一下"、"帮我记录"、"存到笔记"、"记录一下"、"保存到笔记"、"帮我存一下"、"记到 XX 笔记本"、"存到 XX 笔记本" to save content to Evernote via API. Use this skill when the user says "更新笔记"、"修改笔记"、"编辑笔记"、"给笔记添加标签"、"删除笔记标签"、"清空笔记标签"、"修改笔记本"、"移动笔记" to update note title, Markdown content, notebook, or tags by note GUID; when updating tags, pass the complete final tag set in tagNames, and pass clearTags=true if the final tag set is empty or the user wants to clear all tags. Use this skill when the user asks to "批量创建笔记本"、"创建一套笔记本"、"创建笔记本体系"、"批量移动笔记"、"整理笔记" to decompose the request and call existing note APIs multiple times. Use this skill when the user sends a URL with "保存"、"剪藏"、"收藏" to clip the webpage. Use this skill when the user says "列出笔记"、"有哪些笔记"、"有什么笔记" to list notes. Use this skill when the user says "最近笔记"、"最近的笔记"、"查找最近笔记" to search notes created in the last 3 days. Use this skill when the user says "搜一下"、"搜下"、"帮我搜索"、"找找我哪些笔记提到了 XX" to search notes, or asks "有多少篇"、"一共多少篇"、"总数" for notes filtered by keyword, title, tag, notebook, note GUID, or created-time range. Use this skill when the user says "有哪些笔记本"、"有什么笔记本"、"列出笔记本" to list notebooks. Use this skill when the user says "创建笔记本"、"新建笔记本"、"建一个笔记本" to create a notebook. Use this skill when the user says "创建标签"、"新建标签"、"建一个标签" to create a standalone tag. Use this skill when the user says "有哪些标签"、"有什么标签"、"列出所有标签" to list tags. Use this skill when the user says "笔记详情 XXX"、"XXX 笔记详情" to get note detail.

ClawHub Agent Skills author: Yinxiang Team v1.0.4 MIT-0 28 files · 24 scripts body ≈ 2 622 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

This skill should be used when the user says "授权印象笔记"、"印象笔记授权"、"配置印象笔记" to guide the authorization flow.

As a process F 39/100 · Will not run — References files that are not bundled: scripts/*.ps1, scripts/*.sh, templates/cursorrules

IntegrationSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
100
Quality 40%
52
Run on models
none yet
Process rating
F
39/100
Will not run
References files that are not bundled: scripts/*.ps1, scripts/*.sh, templates/cursorrules
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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: 28. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1569 chars, limit 1024
  • warning missing-ref reference to a missing file: scripts/*.ps1
  • warning missing-ref reference to a missing file: scripts/*.sh
  • warning missing-ref reference to a missing file: templates/cursorrules
  • note description-budget description takes 1569 of the ~15000-char shared budget for all skills
  • note frontmatter-key unknown frontmatter key "trigger"

Process rating: all ten parameters 39/100

Will not run. References files that are not bundled: scripts/*.ps1, scripts/*.sh, templates/cursorrules
  • 0Tools and files. 3 referenced file(s) missing: scripts/*.ps1, scripts/*.sh, templates/cursorrules
  • 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
  • 30Running it twice. 6 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 100 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2622 tokens
  • low 18 top-level sections: this looks like several domains in one skill

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 1569: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 24 example trigger phrases
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 100 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 24 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.

External checks

ClawHub: suspicious
The skill matches its note-taking purpose, but it asks users to paste an account token into chat and stores that credential locally while enabling note reading and modification.
LLM: suspicious (high) · 16 Jul 2026