return-refund
Help return an item or request a refund from any retailer. Identifies the item, finds the return policy, navigates the process, and handles shipping labels or phone calls.
62
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/return-refund/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with specific actions and good natural trigger terms that users would actually say. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude more confidently select this skill. The description is concise, uses third person voice correctly, and carves out a distinct niche.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to return a purchase, get a refund, check a return policy, or deal with a retailer's return process.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: identifies the item, finds the return policy, navigates the process, handles shipping labels or phone calls. These are clear, actionable steps. | 3 / 3 |
Completeness | The 'what' is well covered with specific actions, but there is no explicit 'Use when...' clause or equivalent trigger guidance. The description implies when to use it but doesn't state it explicitly, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'return an item', 'request a refund', 'retailer', 'return policy', 'shipping labels'. These closely match how users naturally phrase return/refund requests. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche around retail returns and refunds with distinct triggers like 'return', 'refund', 'return policy', 'shipping labels'. This is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured, clearly sequenced workflow for handling returns with good confirmation checkpoints and fallback logic. Its main weaknesses are moderate verbosity, lack of truly executable/concrete guidance (no specific commands, API calls, or code for email searching or portal navigation), and all content being monolithic rather than leveraging supporting files for detailed sub-procedures.
Suggestions
Add concrete, executable examples for key actions — e.g., specific email search queries for order confirmations, example browser automation steps for common return portals, or a template for the phone call script.
Extract detailed sub-procedures (phone call scripts, common retailer-specific return policies, escalation templates) into separate referenced files to improve progressive disclosure.
Trim explanatory text that Claude can infer — e.g., remove the enumerated return reason list and instead say 'Ask the return reason (fit, defect, changed mind, etc.) — this affects eligibility and shipping cost responsibility.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity — e.g., listing all possible return reasons, explaining that 'the reason matters,' and the warm/advocate tone instructions that Claude can infer. Some tightening is possible without losing clarity. | 2 / 3 |
Actionability | The skill provides a clear process flow with specific tool references (ask_user_input_v0) and concrete scenarios, but lacks executable code, specific URLs/commands, or concrete examples of how to navigate return portals or search emails. Guidance like 'navigate the retailer's return portal' and 'search recent emails' is directional rather than executable. | 2 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit confirmation checkpoints (steps 2, 5, 9), fallback/pivot logic (step 10), and branching paths for different return methods (online, phone, in-store). The feedback loop of 'if any step fails, pivot to next-best path' addresses error recovery well. | 3 / 3 |
Progressive Disclosure | All content is inline in a single file with no references to supporting materials. For a skill of this complexity — covering multiple retailer types, return methods, and escalation paths — some content (e.g., common retailer-specific policies, escalation scripts, phone call templates) could be split into referenced files. However, the content is well-organized with clear sections. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- douglasvought/wiggle-skills
- Commit
b27906e
- 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.