cancel-unsubscribe
Cancel a subscription or unsubscribe from a service. Works from a description, a pasted charge line, a URL, or a photo/screenshot. Can also audit a full statement for recurring charges and cancel several at once. Finds the right contact method and handles the cancellation — including phone calls.
78
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/cancel-unsubscribe/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 excellent specificity, covering multiple input modalities and concrete actions. The trigger terms are natural and comprehensive, and the skill occupies a distinct niche. The main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to cancel a subscription, stop recurring charges, unsubscribe from a service, or review a bank/credit card statement for unwanted charges.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: cancel subscriptions, unsubscribe from services, audit statements for recurring charges, find contact methods, handle cancellations including phone calls. Also specifies multiple input types (description, pasted charge line, URL, photo/screenshot). | 3 / 3 |
Completeness | The 'what' is thoroughly covered with specific capabilities and input types. However, there is no explicit 'Use when...' clause or equivalent trigger guidance — the when is only implied through the action descriptions. Per rubric guidelines, this caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'cancel a subscription', 'unsubscribe', 'charge line', 'recurring charges', 'screenshot', 'statement', 'phone calls'. These cover a wide range of how users would naturally describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | This skill occupies a very clear niche — subscription cancellation and recurring charge management. The specific triggers (cancel, unsubscribe, recurring charges, cancellation) are 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 has strong workflow clarity with well-sequenced steps, explicit confirmation gates, and good error recovery paths — critical for a destructive operation. However, it's moderately verbose with some stylistic padding, and lacks concrete executable examples (e.g., a sample summary card, example IVR navigation, or tool invocation patterns). The monolithic structure would benefit from splitting detailed sub-procedures into referenced files.
Suggestions
Add a concrete example of the summary card output (step 8) so Claude produces consistent, structured results.
Include a specific example of how to invoke ask_user_input_v0 with the checklist format described in step 3, rather than describing it abstractly.
Split the audit workflow (step 3) and phone cancellation script (step 7) into separate referenced files to improve progressive disclosure and reduce the main file's length.
Trim stylistic/personality instructions ('Act like a concierge', 'be warm but efficient') — Claude can infer tone from the procedural content itself.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-written but includes some unnecessary verbosity — e.g., the opening 'Act like a concierge — calm, determined, and always looking for the fastest path to done' and the closing paragraph about being 'warm but efficient' are stylistic padding. Some steps could be tightened, but most content earns its place given the complexity of the task. | 2 / 3 |
Actionability | The skill provides a clear procedural framework with specific steps, but lacks concrete executable examples — no specific URLs, no example IVR navigation scripts, no example summary card format, and no code or tool invocation syntax. Guidance like 'navigate to the cancellation flow' and 'place the call' is directional rather than fully concrete. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (steps 1-10) with explicit confirmation checkpoints at steps 2, 5, and 7 via ask_user_input_v0. There are feedback loops (step 6 pivots to phone if online fails, step 10 offers next-best path on failure). The destructive nature is acknowledged with plan-confirm requirements before execution. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no references to supporting documents. For a skill this long (~80+ lines of substantive content), the audit workflow (step 3), phone script guidelines (step 7), and summary card template (step 8) could be split into separate referenced files. However, the internal structure with numbered steps and bold headers provides reasonable organization. | 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.