Amazon Listing Audit Pro

Comprehensive listing health check and optimization engine for Amazon sellers. Scores listings across 8 dimensions, benchmarks against category leaders, iden...

Security Scan

The skill's requested credential and runtime behavior align with its stated purpose: it calls the APIClaw service using APICLAW_API_KEY and runs the included CLI script to produce listing audits.

Purpose & Capability

Name/description (Amazon listing audit) match the required credential (APICLAW_API_KEY) and the SKILL.md which documents calls to APIClaw endpoints. The included script (scripts/apiclaw.py) implements the documented API calls and composite workflows; nothing required by the skill appears unrelated to Amazon listing analysis.

Instruction Scope

SKILL.md and references explicitly instruct the agent to call APIClaw endpoints, produce reports, and include provenance/credit metadata. Instructions do not direct the agent to read unrelated system files or additional environment variables beyond APICLAW_API_KEY; the CLI script optionally reads a local config.json for an API key, which is consistent with credential lookup behavior described in SKILL.md.

Install Mechanism

No install spec or remote downloads are present — the skill is instruction-only with a bundled CLI script. No external archives, URL shorteners, or unknown installers are invoked. This is low install risk.

Credentials

Only a single credential (APICLAW_API_KEY) is declared and used. The script checks that environment variable and falls back to a local config.json in the skill directory for an API key; both uses are proportional to the stated need to authenticate to api.apiclaw.io. No additional secret-like env vars or unrelated credentials are requested.

Persistence & Privilege

The skill is not forced-always, does not request elevated privileges, and does not modify other skills or system-wide agent settings. It does not appear to persist data or install services beyond optionally reading a local config.json. Autonomous invocation is allowed by default but is not combined with other concerning privileges.

Assessment

This skill will call api.apiclaw.io using the APICLAW_API_KEY you provide (either via the APICLAW_API_KEY environment variable or via a config.json file placed in the skill directory). Before installing: (1) Confirm you trust APIClaw (apiclaw.io) and the GitHub repo owner (SerendipityOneInc) because your key and request data are sent to that service; (2) Be aware audits (especially bulk mode) consume API credits — check costs and quotas; (3) Prefer setting the key as an env var rather than dropping it in a repo/config file to avoid accidental leakage; (4) Review the GitHub homepage/source to ensure it matches your expectations because the skill package source is listed as unknown here; (5) If you require tighter control, run the included script locally on a machine you control and inspect logs/requests before granting the key to an autonomous agent.

APIClaw — Amazon Listing Audit Pro

8-dimension health check. Benchmark against leaders. Fix what matters most. Respond in user's language.

Files

File	Purpose
{skill_base_dir}/scripts/apiclaw.py	Execute for all API calls (run --help for params)
{skill_base_dir}/references/reference.md	Load for exact field names or response structure

Credential

Required: APICLAW_API_KEY. Get free key at apiclaw.io/api-keys.

Input

Required: my_asin. Optional: keyword, category. Category is auto-detected from ASIN via realtime/product if not provided. If category_source is inferred_from_search, confirm with user before proceeding.

API Pitfalls (CRITICAL)

1. Category auto-detection: categoryPath is auto-detected from ASIN. If category_source in output is inferred_from_search, confirm with user
2. All keyword-based endpoints MUST include --category; ASIN-specific endpoints do NOT
3. Use API fields directly: revenue=sampleAvgMonthlyRevenue (NEVER price×sales), sales=monthlySalesFloor, opportunity=sampleOpportunityIndex
4. reviews/analysis: needs 50+ reviews; ASIN mode first, category fallback
5. Sales null fallback: Monthly sales ≈ 300,000 / BSR^0.65, tag 🔍

Execution

1. listing-audit --my-asin X [--keyword Y] [--category Z] (composite, auto-detects category from ASIN)
2. Score 8 dimensions → generate report with improvements

8 Scoring Dimensions

Dimension	Weight	90-100	60-89	30-59	0-29
Title	15%	150+ chars, top 3 KW, brand first	100-150, 2 KW	<100 or stuffed	Missing key terms
Bullets	15%	5+, benefit-led, KW each	5, features only	3-4, generic	<3 bullets
Images	15%	7+, infographic+lifestyle	5-6, decent	3-4, basic	1-2 images
A+ Content	10%	Rich A+, comparison, brand story	Basic A+	No A+ w/ description	Nothing
Reviews	15%	1000+, 4.5+, <5% 1-star	200-1K, 4.0-4.5	50-200, 3.5-4.0	<50 or <3.5
Keywords	10%	Top 5 competitor KW covered	3-4 covered	1-2 covered	None matched
Category Fit	10%	Optimal category, top 1% BSR	Top 5%	Suboptimal	Wrong category
Pricing	10%	In opportunity band, margin >25%	Hottest band	Outside top bands	Overpriced/<10% margin

Score each 0-100, calculate weighted total. Include "Basis" column explaining each score.

Output Spec

Sections: Overall Score (X/100, A-F grade) → 8-Dimension Scorecard → Title Audit (analysis + suggested rewrite) → Bullets Audit (vs leaders, missing points, rewrites) → Image Audit → Review Health → Keyword Gap Analysis (vs Top 5 leader titles/bullets) → vs Category Leaders (side-by-side Top 3) → Priority Fix List (lowest scores first) → Data Provenance → API Usage.

Suggested rewrites should incorporate high-frequency positive review language.

Language (required)

Output language MUST match the user's input language. If the user asks in Chinese, the entire report is in Chinese. If in English, output in English. Exception: API field names (e.g. monthlySalesFloor, categoryPath), endpoint names, technical terms (e.g. ASIN, BSR, CR10, FBA, credits) remain in English.

Disclaimer (required, at the top of every report)

Data is based on APIClaw API sampling as of [date]. Monthly sales (monthlySalesFloor) are lower-bound estimates. This analysis is for reference only and should not be the sole basis for business decisions. Validate with additional sources before acting.

Confidence Labels (required, tag EVERY conclusion)

• 📊 Data-backed — direct API data (e.g. "CR10 = 54.8% 📊")
• 🔍 Inferred — logical reasoning from data (e.g. "brand concentration is moderate 🔍")
• 💡 Directional — suggestions, predictions, strategy (e.g. "consider entering $10-15 band 💡")

Rules: Strategy recommendations are NEVER 📊. User criteria override AI judgment.

Bulk audit: share market data across ASINs, run audit per ASIN.

Data Provenance (required)

Include a table at the end of every report:

Data	Endpoint	Key Params	Notes
(e.g. Market Overview)	markets/search	categoryPath, topN=10	📊 Top N sampling, sales are lower-bound
...	...	...	...

Extract endpoint and params from _query in JSON output. Add notes: sampling method, T+1 delay, realtime vs DB, minimum review threshold, etc.

API Usage (required)

Endpoint	Calls	Credits
(each endpoint used)	N	N
Total	N	N

Extract from meta.creditsConsumed per response. End with Credits remaining: N.

API Budget: ~20-25 credits

Audit target(1) + Categories/Products/Competitors(3) + Realtime×5(5) + Market/Brand(3) + Price(2) + Reviews(2) + History(1) + Buffer(3-8).