CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

refunds

Check refund eligibility and use the refund-order tool safely

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./libraries/typescript/packages/server/examples/skills-over-mcp/skills/refunds/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 content is exceptionally lean and well-structured as an overview pointing to bundled references, and it gives a concrete tool call. Its weaknesses are a missing validation checkpoint before the destructive refund action (capping workflow clarity) and a broken reference to a template file that does not exist.

Suggestions

Add an explicit validation/confirmation checkpoint before calling refund-order (e.g., 'Confirm the order ID and that eligibility criteria from the policy are met before calling refund-order; if the purchase date is unavailable or outside 30 days, ask for clarification rather than refunding').

Create the missing templates/confirmation.md file (or fix the link) so the referenced confirmation template actually resolves.

Show the concrete refund-order invocation syntax/parameters so the actionability reaches fully copy-paste ready guidance.

DimensionReasoningScore

Conciseness

The body is three lean lines that assume Claude already knows what refunds are, with no padding or over-explanation, matching 'lean and efficient; every token earns its place'. It is not a 4 because there are no instances of over-explanation to trim.

5 / 5

Actionability

It gives a concrete tool call ('call refund-order with its order ID') plus references to a policy and template, which is mostly executable guidance with minor gaps. It is not a 5 because the invocation is not fully copy-paste ready (no parameter syntax) and the referenced template file does not exist, and not a 3 because the guidance is concrete rather than pseudocode.

4 / 5

Workflow Clarity

A rough sequence is present (read policy → confirm eligible → call tool → use template) but there are no explicit validation checkpoints before the destructive refund action, so per the rubric cap for destructive operations workflow_clarity cannot exceed 3. It fits the 'steps listed but validation gaps; checkpoints missing or implicit' anchor.

3 / 5

Progressive Disclosure

The body is a clear, concise overview with well-signaled one-level-deep references (policy.md, confirmation template), and references/policy.md exists. It is not a 5 because the link to templates/confirmation.md points to a non-existent file, an organization/navigation gap; it is not a 3 because no inlinable bulk content is crammed into the overview.

4 / 5

Total

16

/

20

Passed

Description

53%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 specific and names a concrete tool, but it omits any 'when to use' trigger guidance and relies on a single keyword family, capping completeness and trigger term quality. It is concise and distinct but not comprehensive as a triggerable skill description.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks for a refund, wants their money back, or requests to cancel/reverse an order').

Broaden trigger keywords beyond 'refund' to include synonyms users actually say, such as 'money back', 'return', or 'cancel order'.

Consider listing the concrete eligibility criteria briefly to lift specificity from 1-2 actions toward fuller coverage.

DimensionReasoningScore

Specificity

Names two concrete actions — 'Check refund eligibility' and 'use the refund-order tool' — but offers no broader coverage, matching the '1-2 concrete actions but not comprehensive' anchor. It is not a 2 because the actions are specific rather than generic, and not a 4 because there are not several specific actions.

3 / 5

Completeness

It clearly states what the skill does ('Check refund eligibility and use the refund-order tool safely') but includes no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3. It is not a 4 because 'when' is entirely absent rather than weakly present.

3 / 5

Trigger Term Quality

The only natural keyword is 'refund' (repeated as 'refund eligibility' and 'refund-order'), which is relevant but lacks common variations like 'money back', 'return', or 'cancel order'. This matches 'some relevant keywords but missing common variations or synonyms' rather than the broader coverage required for a 4.

3 / 5

Distinctiveness Conflict Risk

It names a specific named tool ('refund-order') in a narrow niche, making it mostly distinct with only minor overlap risk against generic order/customer-service skills. It is not a 5 because the description lacks explicit distinct trigger phrases that would fully separate it from neighboring skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

mcp-use/mcp-use

Path

libraries/typescript/packages/server/examples/skills-over-mcp/skills/refunds/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.