CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shop

Shop catalog search, checkout, order tracking, returns.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 skill body is a strong operating guide: fully executable commands, a clearly sequenced shopping flow with explicit validation gates before purchases, and clean progressive disclosure into four verified reference files. The only room for improvement is trimming a small amount of rationale and tabular detail that could be tightened without losing guidance.

DimensionReasoningScore

Conciseness

The body is dense with shop-specific rules, flag semantics, and executable commands that Claude could not know on its own, with only minor instances of over-explanation (e.g. the sign-in benefits rationale and the channel-override table) that could be trimmed. It is not a 5 because a few passages restate rationale that could be cut without losing guidance; it is well above a 3 since nearly all content is novel and non-padded.

4 / 5

Actionability

Full CLI syntax blocks, copy-paste-ready bash and JSON-pipe examples for checkout create/update/complete, complete auth flow commands, a product message template, and a channel-override table cover the common cases concretely. It is not a 4 because there are no gaps: placeholders like CHECKOUT_ID are clearly marked and every workflow has executable commands.

5 / 5

Workflow Clarity

The "Shopping flow" section gives a six-step numbered sequence, each linked to its rules section, with explicit validation checkpoints: STOP-and-wait on sign-in, re-run poll while pending, a pre-complete confirmation checklist (intent, variant, quantity, price, address, method, total) enforced by the --confirm gate, and mandatory warning disclosure. Feedback loops for error recovery are present (retry search with dropped --ships-from, refine query over deep paging), and the destructive-operation cap does not apply because validation before money-moving steps is thorough.

5 / 5

Progressive Disclosure

The body is an operating overview that points to four well-labeled, one-level-deep reference files (catalog-mcp.md, direct-api.md, safety.md, legal.md), each summarized in the Reference files list and also linked at the point of need; all referenced paths were verified to exist as real bundle files. The single sibling cross-link (catalog-mcp.md to direct-api.md) does not bury content since direct-api.md is directly listed, so navigation is easy; not a 4 because no content that belongs in references is inlined and no reference is buried.

5 / 5

Total

19

/

20

Passed

Description

71%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.

The description is concise and specific, naming four concrete actions that fully cover the skill's domain. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness and slightly weakens trigger quality. Adding explicit trigger guidance and a few natural synonyms would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to find, compare, buy, or track products, or when they mention shopping, checkout, orders, or returns."

Include natural synonyms users would say such as "buy", "purchase", "reorder", and "exchange" to broaden trigger-term coverage.

Scope the domain explicitly (e.g. "Shop app catalog") to reduce overlap risk with generic e-commerce or web-search skills.

DimensionReasoningScore

Specificity

"Shop catalog search, checkout, order tracking, returns" lists four concrete actions (search, checkout, order tracking, returns) that comprehensively cover the skill's capability areas, matching the anchor for multiple specific concrete actions. It is not a 4 because no meaningful capability area from the body (search, checkout, orders, returns) is left uncovered.

5 / 5

Completeness

The description clearly answers "what" (catalog search, checkout, order tracking, returns) but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Terms like "search", "checkout", "order tracking", and "returns" are natural phrases users would say when shopping, giving good keyword coverage. It is not a 5 because common synonyms and variations such as "buy", "purchase", "reorder", or "exchange" are missing.

4 / 5

Distinctiveness Conflict Risk

The Shop e-commerce niche with actions like checkout and order tracking is mostly distinct with only minor overlap risk against generic shopping or retail skills. It is not a 5 because broad terms like "search" and "returns" lack the trigger scoping that would minimize conflict with closely related skills.

4 / 5

Total

16

/

20

Passed

Validation

75%

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

Validation — 12 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

12

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/productivity/shop/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.