CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shopping-copilot

Hosted shopping copilot that turns a natural-language shopping request into evidence-backed recommendations and affiliate deeplinks. Use when the user wants an agent to reason about product fit or directly search shopping results. Trigger even without the explicit `shopping-copilot` prefix when the user is clearly asking to buy, compare, search, or recommend a physical product. Strong triggers include 쇼핑 추천, 상품 추천, 뭐 사야 해, 골라줘, 추천해줘, 찾아줘, 검색해줘, 보여줘, 링크 줘, 어디서 사, 쿠팡에서, 가성비, 최저가, 제일 긴, 제일 싼, 평점 높은, 리뷰 많은, big size/대두/큰 머리, 착용감, 편하게 쓸 수 있는, 마스크, 청소기, 양말, 케이블, 오트밀크, 책, 도서, 자기계발서, 소설, 경제경영, 내 스타일, 내 취향, 나한테 맞는 같은 product-seeking phrases. Also triggers on 골드박스, 오늘 특가, 지금 특가, 타임딜, 당일 특가, 베스트, 인기상품, 카테고리 베스트, 전자제품 베스트, 로켓배송만, 로켓만, 로켓으로, 로켓 상품만. Example shopping queries include "30만원 이하 무선청소기, 소음 적고 원룸용", "쿠팡에서 AUX 선 제일 긴거 제품 찾아줘", "머리가 큰 사람도 고통 없이 쓸 수 있는 미세먼지 마스크 찾아줘", "쿠팡에서 요즘 볼만한 자기계발서 3개만 찾아줘. 내 스타일을 알아보고 추천해라", "오늘 골드박스 뭐야?", "전자제품 베스트 보여줘", "로켓배송만 무선청소기 10만원 이하".

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw_skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers genuinely actionable, executable guidance — real commands, flags, a routing table, and payload examples — and the workflow is clearly sequenced. However, a copy-paste artifact left the goldbox and best sections duplicated with broken numbering (1, 3, 4, 5, 2, 3, 4), and the trigger examples and purpose sections restate the description, wasting tokens and muddying navigation.

Suggestions

Deduplicate the Commands section: goldbox and best each appear twice (once as 'best --category', again as 'best-products --category-id') and the numbering runs 1, 3, 4, 5, 2, 3, 4 — collapse to a single numbered list of the five distinct subcommands.

Show how the 'vertical': 'book' and persona payloads are actually passed to the recommend command (a flag, a JSON file, or an inline argument), since the CLI examples never connect to those payloads.

Move the long trigger-phrase and category catalogs (which duplicate the frontmatter description) into a references/ file, keeping SKILL.md as a lean overview with the routing table and command examples.

DimensionReasoningScore

Conciseness

Noticeable redundancy: the goldbox and best command sections each appear twice with full code blocks, section numbering runs 1, 3, 4, 5, 2, 3, 4, and both the "What this skill is for" bullets and the 14-item "Trigger examples" list largely restate the frontmatter description. This matches level 2 (several unnecessary or padded sections) rather than level 3, where only isolated tightening would be needed; roughly a quarter of the body is duplicative.

2 / 5

Actionability

Commands are concrete and executable with real flags (--rocket-only, --max-price, --sort SALE, category lists, routing table), and the persona JSON payloads are copy-paste ready. It falls short of level 5 because the "vertical"/"persona" payloads are never connected to an actual CLI invocation — the recommend example shows only --query/--price-max/--limit, leaving unclear how the assist payload is passed.

4 / 5

Workflow Clarity

The routing table plus 8 numbered steps give a clear intent-first sequence with sensible checkpoints ("ask for constraints if missing", prefer short_deeplink). These are read-only API calls so the destructive-operation validation cap does not apply, but explicit error recovery (what to do on {"ok": false}) is absent, matching level 4 (minor validation gaps) rather than level 5 (explicit feedback loops).

4 / 5

Progressive Disclosure

Section headers and the routing table provide structure and the single referenced script exists, but the body inlines ~160 lines including duplicated command sections, two full trigger-phrase catalogs, and detailed persona/category reference material that belongs in a separate file. The duplicated and mis-numbered sections exceed the "minor organization gaps" of level 4, matching level 3 (content that should be separate is inline, organization could be better).

3 / 5

Total

13

/

20

Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: explicit what-and-when structure, third-person voice, and an unusually thorough catalog of natural Korean trigger phrases with concrete example queries. The only weaknesses are slightly incomplete action coverage in the what-clause and a few overly broad trigger nouns that could fire outside the shopping context.

DimensionReasoningScore

Specificity

Concrete actions are named — "turns a natural-language shopping request into evidence-backed recommendations and affiliate deeplinks", "reason about product fit or directly search shopping results" — but coverage stops just short of the full capability set (goldbox deals, category bestsellers, rocket-filtered search are only implied via triggers, not stated as actions). This sits above the level-3 anchor (only 1-2 actions) and below level 5 (comprehensive action coverage).

4 / 5

Completeness

Both questions are explicitly answered: what ("evidence-backed recommendations and affiliate deeplinks") and when ("Use when the user wants an agent to reason about product fit or directly search shopping results", reinforced with trigger phrases and example queries). This directly matches the level-5 anchor; level 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

The description exhaustively catalogs natural user phrases with synonyms and variations — 쇼핑 추천, 추천해줘, 찾아줘, 검색해줘, 골라줘, 가성비, 최저가, 제일 긴, 로켓배송만, 골드박스, 타임딜 — plus full example queries like "쿠팡에서 AUX 선 제일 긴거 제품 찾아줘". This matches the level-5 anchor (comprehensive natural-term coverage including synonyms); nothing obvious is missing for the Korean shopping domain.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (Coupang shopping, affiliate deeplinks, 로켓배송/골드박스-specific triggers) and mostly distinct, but very broad trigger nouns like 책, 도서, 소설, 마스크, 양말, 케이블 and generic verbs like 찾아줘/보여줘 create some overlap risk with generic search or book-recommendation skills, keeping it below the minimal-conflict level-5 anchor. The guard clause "clearly asking to buy, compare, search, or recommend a physical product" mitigates this above level 3.

4 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

retention-corp/coupang_partners

Path

openclaw_skill/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.