SKILLEMALL.ai
GitHub ↗ RU Sign in

BF insurance-advisor-china

中国大陆AI保险顾问。为个人和家庭提供全方位的保险咨询、产品对比、方案设计、投保指导。当用户询问保险配置、保险方案、产品对比、重疾险/医疗险/寿险/意外险/储蓄险推荐、保费计算、保障缺口分析、需求分析、核保合规、理赔等问题时使用。

ClawHub Agent Skills author: mnetfairy v2.0.108 MIT-0 25 files body ≈ 2 335 tokens Open the sourceclawhub.ai↗ analyzed 7 h ago

中国大陆AI保险顾问。为个人和家庭提供全方位的保险咨询、产品对比、方案设计、投保指导。当用户询问保险配置、保险方案、产品对比、重疾险/医疗险/寿险/意外险/储蓄险推荐、保费计算、保障缺口分析、需求分析、核保合规、理赔等问题时使用。

As a process F 35/100 · Will not run — References files that are not bundled: references/products.json, references/products_v2.json, scripts/*.py

ProcedureAI 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
76/100
safety, quality, tests
Safety 60%
88
Quality 40%
59
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: references/products.json, references/products_v2.json, scripts/*.py
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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  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 · 12

✓ No critical or high findings

Medium and low: 12
  • low Secrets in code secret-high-entropy-token scripts/datafix/fix_P1-4_validity_consistency.py:110
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X1_D…ive": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/fix_P1-4_validity_consistency.py:111
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X2_D…ull": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/fix_P1-4_validity_consistency.py:112
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X2_D…ate": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/fix_P1-4_validity_consistency.py:113
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X3_V…ing": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/fix_P1-4_validity_consistency.py:114
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X4_d…ive": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/fix_P1-5_coverage_period_split.py:293
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    bk = backup_v2("pre_…lit")
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/fix_phase0_coverage_period_none.py:97
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    bk = backup_v2("pre_…one")
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/reports/P1-4_validity_consistency_report.json:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X1_D…ive": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/reports/P1-4_validity_consistency_report.json:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X2_D…ull": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/reports/P1-4_validity_consistency_report.json:19
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X2_D…ate": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/reports/P1-4_validity_consistency_report.json:20
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X3_V…ing": 0,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/datafix/reports/P1-4_validity_consistency_report.json:21
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "X4_d…ive": 0,
    quoted

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/products.json
  • warning missing-ref reference to a missing file: references/products_v2.json
  • warning missing-ref reference to a missing file: scripts/*.py
  • warning missing-ref reference to a missing file: references/products*.json
  • warning missing-ref reference to a missing file: references/backups*/
  • note frontmatter-key unknown frontmatter key "last_published"
  • note frontmatter-key unknown frontmatter key "permissions"
  • note frontmatter-key unknown frontmatter key "scope"

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/products.json, references/products_v2.json, scripts/*.py
  • 0Tools and files. 5 referenced file(s) missing: references/products.json, references/products_v2.json, scripts/*.py
  • 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
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 82 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2335 tokens
  • 100Running it twice. No mutating operations
  • 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 115: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -218 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 31 headings
  • +3Step-by-step instructions: 82 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (2 of 4)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
The skill is mostly a local China insurance advisor, but it forces recommendations to show one specific insurance agency contact and the premium calculator can include discontinued products.
LLM: suspicious (high) · 13 Sept 2026