SKILLEMALL.ai
GitHub ↗ RU Sign in

BC usa-business-migration-planner

Help users with Validated demand: People repeatedly need a practical, repeatable way to handle Claude Code 的 Prompt Cache 到底怎么工作？ 5 个让缓存失效的坑. This requirement is supported by 12 separate online signals across 3 source families, so it represents broader demand rather than a single isolated request.. Use when a user asks for software-and-data, v2ex, programmer, claude, code, or needs a practical workflow, artifact, checklist, analysis, or implementation support for this requirement.

ClawHub Agent Skills author: Kyro v0.20260729.110214 MIT-0 7 files body ≈ 623 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Help users with Validated demand: People repeatedly need a practical, repeatable way to handle Claude Code 的 Prompt Cache 到底怎么工作？ 5 个让缓存失效的坑.

As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

AnalyzerAI and agentsSoftware developmenttype 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
82/100
safety, quality, tests
Safety 60%
80
Quality 40%
84
Run on models
none yet
Process rating
C
62/100
Has gaps
Failures and branches w 10
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Obfuscation obf-hex-escape-chain README.md:25
      Escaped/char-code string obfuscation
      - csdn-search: [面试官问我：“你了解 Claude Code 的缓存机制？”，我：“何止了解，我深入研究过”，面试官：“先入职，后面细聊！！”](https://blog.csdn.net/weix…619/article/details/162849575?ops_request_misc=…&request_id=…
    • medium Obfuscation obf-hex-escape-chain README.zh-CN.md:25
      Escaped/char-code string obfuscation
      - csdn-search：[面试官问我：“你了解 Claude Code 的缓存机制？”，我：“何止了解，我深入研究过”，面试官：“先入职，后面细聊！！”](https://blog.csdn.net/weix…619/article/details/162849575?ops_request_misc=…&request_id=…
    • medium Obfuscation obf-hex-escape-chain references/requirement-plan.md:43
      Escaped/char-code string obfuscation
      - csdn-search (2026…:00+00:00): [面试官问我：“你了解 Claude Code 的缓存机制？”，我：“何止了解，我深入研究过”，面试官：“先入职，后面细聊！！”](https://blog.csdn.net/weix…619/article/details/162849575?ops_request_misc=…
    • medium Obfuscation obf-hex-escape-chain skill-card.md:31
      Escaped/char-code string obfuscation
      - [Claude Code prompt-cache CSDN article](https://blog.csdn.net/weix…619/article/details/162849575?ops_request_misc=…&request_id=…&biz_id=0&utm_

    Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 62/100

    • 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
    • 40Result and completion. Does not say what the result is
    • 40Consistency. Frontmatter name (usa-business-migration-planner) differs from the folder (usa-business-migration-planner-235619)
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 16 steps
    • 100Execution cost. Instruction body is 623 tokens
    • 100Running it twice. No mutating operations

    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

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 485: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 16 items
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    The skill appears to be a prompt-cache workflow helper published under an unrelated business-migration name, with broad implicit activation that could misroute user requests.
    LLM: suspicious (high) · 29 Jul 2026