SKILLEMALL.ai

BB linkfoxagent

Cross-border e-commerce AI Agent with 79 specialized tools for Amazon/TikTok/eBay/Walmart/Shopee/Ozon product research, competitor analysis, keyword tracking, review insights, patent deep-dive (claims, legal status, family, citations, figures, translations), trend analysis, 1688 sourcing, AI image generation, image recognition, PDF analysis, real-time web search, historical sales & price trend tracking, and AI-powered Amazon opportunity reports. Amazon Ads SP/SB performance reports are orchestrated via the sibling skill linkfox-amazon-ads-report (scripts); report-type column specs are mirrored in this skill under references/amazon-ads-report-types/; see references/amazon-ads-report.md. Optional packaged workflows: SellerSprite extras in references/seller-sprite.md; Lingxing ERP OpenAPI (linkfox-lingxing-erp, ~373 endpoints, direct openapi.lingxing.com) in references/lingxing-erp.md. Use when: (1) product selection and market analysis, (2) competitor research and ASIN lookup, (3) keyword and traffic analysis, (4) review mining and consumer insights, (5) patent/trademark/copyright detection and deep patent research, (6) Google/TikTok trend research, (7) 1688 supplier sourcing, (8) data aggregation and report generation, (9) cross-platform product search (Amazon/Walmart/eBay/TikTok/Shopee/Ozon), (10) product image analysis, similarity grouping, and image recognition, (11) AI product image generation, (12) PDF file analysis, (13) Amazon opportunity reports, (14) Lingxing ERP data (ads, orders, listings, inventory, finance, FBA, etc.) when user has Lingxing OpenAPI credentials.

ClawHub Agent Skills author: linkfox-ai v1.1.4 MIT-0 25 files body ≈ 6 277 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice

ProcedurePDFProcurementData and analyticstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
95
Quality 40%
53
Run on models
none yet
Process rating
B
66/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 5

✓ No critical or high findings

Medium and low: 5
  • low Secrets in code secret-high-entropy-token scripts/lingxing.py:186
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Plat…tV2": "/basicOpen/plat…sV2/saleStat/pageList",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lingxing.py:236
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "v1ge…ist": "/erp/sc/data/mws_…_v1/getAmazonFulfilledShipmentsList",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lingxing.py:237
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "v1ge…ist": "/erp/sc/data/mws_…_v1/getFbaInventoryEventDetailList",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lingxing.py:428
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Plat…tV2": ("page", "length"),
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lingxing.py:514
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Plat…tV2", "ProfitMsku",
    quoted

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

Against the Agent Skills spec

  • error description-long description is 1599 chars, limit 1024
  • warning body-long SKILL.md body ≈ 6277 tokens (recommended < 5000); move details to references/
  • note description-budget description takes 1599 of the ~15000-char shared budget for all skills

Process rating: all ten parameters 66/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 4 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 6277 tokens
  • 100Steps. 46 steps
  • 100Failures and branches. 4 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 The response is described with custom markup (6 tags): a typed call is more reliable

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 1599: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 46 items
  • +3Output format is stated explicitly
  • +4Has examples (16 code blocks)
  • +4Reference files are cited in the instructions (18 of 19)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.

External checks

ClawHub: suspicious
This appears to be a real e-commerce research skill, but it needs Review because it can publish task traces publicly and includes broad business/ERP API authority without strong user controls.
LLM: suspicious (high) · 8 Jul 2026