Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →This skill provides a way to retrieve information from the AgentScope library for analysis and decision-making.
.claude/skills/microck-analyzing-agentscope-library/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -50% | 0% |
This guide covers the essential operations for retrieving and answering questions about the AgentScope library. If you need to answer questions regarding the AgentScope library, or look up specific information, functions/classes, examples or guidance, this skill will help you achieve that.
The skill provides the following key scripts:
When being asked an AgentScope-related question, you can follow the steps below to find the relevant information:
First decide which of the three scripts to use based on the user's question.
consider what functions are needed and search in the guide/tutorial
consider to search for the corresponding modules, classes, or functions in the library.
First ask for the user's permission to clone the agentscope GitHub repository if you haven't done so:
bashgit clone -b main https://github.com/agentscope-ai/agentscope
In this repo, the examples folder contains various examples demonstrating how to use different features of the AgentScope library. They are organized in a tree structure by different functionalities. You should use shell command like ls or cat to navigate and view the examples. Avoid using find command to search for examples, as the name of the example files may not directly relate to the functionality being searched for.
Similarly, first ensure you have cloned the agentscope GitHub repository.
The source agentscope tutorial is located in the docs/tutorials folder of the agentscope GitHub repository. It's organized by the different sections. To search for guidance, go to the docs/tutorials folder and view the tutorial files by shell command like ls or cat.
First, ensure you have installed the agentscope library in your environment:
bashpip list | grep agentscope
If not installed, ask the user for permission to install it by command:
bashpip install agentscope
Then, run the following script to search for specific modules, classes, or functions. It's suggested to start with agentscope as the root module name, and then specify the submodule name you want to search for.
bashpython view_agentscope_module.py --module agentscope
About detailed usage, please refer to the ./view_agentscope_module.py script (located in the same folder as this SKILL.md file).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 15,347 | 4,948 | -68% | 1 | 1 | 0% | 2,094 | 1,561 | -25% | 0 | 0 | — |
case-01 | fail→fail | 14,531 | 6,554 | -55% | 1 | 1 | 0% | 2,403 | 919 | -62% | 0 | 0 | — |
case-02 | fail→fail | 15,896 | 26,662 | +68% | 1 | 1 | 0% | 2,920 | 4,972 | +70% | 0 | 0 | — |
case-03 | pass→fail | 16,063 | 5,172 | -68% | 1 | 1 | 0% | 3,341 | 967 | -71% | 0 | 0 | — |
case-04 | fail→pass | 21,807 | 4,225 | -81% | 1 | 1 | 0% | 949 | 1,318 | +39% | 0 | 0 | — |
case-05 | pass→pass | 9,144 | 5,059 | -45% | 1 | 1 | 0% | 1,458 | 1,397 | -4% | 0 | 0 | — |
case-07 | pass→pass | 5,653 | 3,068 | -46% | 1 | 1 | 0% | 790 | 1,059 | +34% | 0 | 0 | — |
case-08 | fail→fail | 7,501 | 2,077 | -72% | 1 | 1 | 0% | 1,171 | 995 | -15% | 0 | 0 | — |
case-09 | fail→pass | 14,191 | 3,615 | -75% | 1 | 1 | 0% | 2,096 | 1,223 | -42% | 0 | 0 | — |
case-10 | fail→pass | 5,014 | 2,817 | -44% | 1 | 1 | 0% | 781 | 1,167 | +49% | 0 | 0 | — |
case-11 | pass→pass | 9,573 | 2,434 | -75% | 1 | 1 | 0% | 1,484 | 1,100 | -26% | 0 | 0 | — |
case-12 | pass→pass | 7,674 | 1,919 | -75% | 1 | 1 | 0% | 1,267 | 967 | -24% | 0 | 0 | — |
case-13 | fail→fail | 7,596 | 3,381 | -55% | 1 | 1 | 0% | 1,232 | 1,199 | -3% | 0 | 0 | — |
case-14 | pass→pass | 3,276 | 2,121 | -35% | 1 | 1 | 0% | 425 | 1,003 | +136% | 0 | 0 | — |
case-15 | pass→pass | 8,183 | 3,787 | -54% | 1 | 1 | 0% | 1,411 | 1,202 | -15% | 0 | 0 | — |
case-16 | pass→pass | 4,797 | 2,382 | -50% | 1 | 1 | 0% | 873 | 979 | +12% | 0 | 0 | — |
case-17 | pass→pass | 7,547 | 2,867 | -62% | 1 | 1 | 0% | 1,187 | 1,135 | -4% | 0 | 0 | — |
case-18 | fail→pass | 14,874 | 3,584 | -76% | 1 | 1 | 0% | 2,334 | 1,174 | -50% | 0 | 0 | — |
case-19 | pass→fail | 2,980 | 6,931 | +133% | 1 | 1 | 0% | 385 | 952 | +147% | 0 | 0 | — |
case-20 | pass→fail | 3,969 | 7,063 | +78% | 1 | 1 | 0% | 554 | 910 | +64% | 0 | 0 | — |
case-21 | pass→pass | 3,065 | 8,805 | +187% | 1 | 1 | 0% | 451 | 1,551 | +244% | 0 | 0 | — |
case-22 | pass→pass | 2,810 | 7,083 | +152% | 1 | 1 | 0% | 384 | 1,234 | +221% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 17 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 17 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.