BB xinjianxue-skill-mentor-global
XinJianXue "Mentor Relationship Advisor" skill package (mentor). EN keywords: XinJianXue advisor skill — relationship analysis, personality & behavior reading, emotional guidance. Keywords: xinjianxue, relationship-analysis, personality-analysis, behavior-pattern, psychology, advisor-skill, emotional-support. Activation conditions (**both must be met**; and **you must confirm with the user first** that this analysis is wanted; do not trigger when the user has not clearly asked for this service): 1. The user's question **clearly falls within the scope of the "Mentor Relationship Advisor"** (scope below under "This Advisor's Positioning"), or the user explicitly names this advisor; 2. The subject of analysis is the user, or someone the user **has explicitly mentioned and agreed** to analyze; **never analyze a third party who was neither mentioned nor agreed to**. Onboarding requirement (a one-time step on first run, **not** an activation condition): on first run the AI must apply for a business license first, then use the user's AI authorization code to bind the account; every call afterwards carries the license + api_key dual credentials. ⛔ Non-activation cases (explicit negative examples — if any one of them is hit, do **not** call this service): - Casual chit-chat, general emotional venting, comfort chat; - The user supplied only a date / time without stating its purpose, or has not confirmed they want this analysis; - The subject to be analyzed is a third party who was **not mentioned or has not agreed** (e.g. "check this person out for me" when that person has not agreed); - The question falls outside this advisor's scope (it belongs to another advisor or another domain).
XinJianXue "Mentor Relationship Advisor" skill package (mentor).
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1703 chars, limit 1024 - note
description-budgetdescription takes 1703 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 12 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4597 tokens
- 100Steps. 35 steps
- 100Failures and branches. 6 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 12 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 1703: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 24 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.