AB alibabacloud-bailian-memory
Manages conversation memories and user profiles in Alibaba Cloud Bailian (Model Studio) Memory Library via DashScope REST APIs. Covers memory extraction from conversations, direct content saving, semantic memory search, memory fragment maintenance, user profile queries and updates, plus memory project and profile schema administration. Use when the user requests memory library ("记忆库") operations such as "add memory", "search memory" or "user profile". Prerequisites: (1) Configure DashScope API Key (2) Activate Bailian Memory Library service. Do NOT use for Bailian RAG knowledge base retrieval or document search.
Manages conversation memories and user profiles in Alibaba Cloud Bailian (Model Studio) Memory Library via DashScope REST APIs.
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6519 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 61 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 6519 tokens
- 100Steps. 50 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +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 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 619: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 50 items
- +4Has examples (17 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 13 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.