call-to-book
Make a phone call to book an appointment or reservation. Checks calendar first, gets explicit consent before dialing, discloses AI identity on the call, and adds the booking to calendar when done.
87
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
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 that clearly communicates a unique and specific capability — making phone calls to book appointments. It lists concrete actions in a logical workflow and uses natural trigger terms. The main weakness is the absence 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 asks to call a business, book an appointment, make a reservation, or schedule something by phone.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: make a phone call, book an appointment/reservation, check calendar, get consent, disclose AI identity, add booking to calendar. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with the full workflow description, but lacks an explicit 'Use when...' clause. The triggers are implied through the description but not stated explicitly, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'phone call', 'book', 'appointment', 'reservation', 'calendar'. These are terms a user would naturally use when requesting this kind of task. | 3 / 3 |
Distinctiveness Conflict Risk | This skill occupies a very clear niche — making phone calls to book appointments/reservations. The combination of phone calling + booking + calendar integration is highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides clear, actionable guidance for a complex multi-step phone booking workflow. Its main weakness is moderate verbosity — the conversational, personality-driven tone ('like a concierge,' 'the babysitting I'm trying to avoid') adds flavor but wastes tokens. The workflow design is excellent, with thorough edge-case handling and explicit consent/validation gates.
Suggestions
Trim conversational/motivational language (e.g., 'Act like a concierge,' 'the babysitting I'm trying to avoid') to save tokens while preserving the same behavioral instructions.
Convert the inline explanations of why steps matter into terse directives — Claude doesn't need persuasion, just instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-written but somewhat verbose for what it conveys. Phrases like 'Act like a concierge: calm, prepared, and always one step ahead' and 'A call that has to be redone because you were missing my insurance — or that stalls because you didn't know whether you could leave a voicemail — is the babysitting I'm trying to avoid' are stylistic padding that don't add actionable value. The conversational tone adds tokens without adding clarity. | 2 / 3 |
Actionability | The skill provides highly specific, concrete guidance at every step: which tool to use (ask_user_input_v0), what information to gather (insurance, callback number), exact behaviors on the call (disclose AI identity immediately, hang up after 2-3 minutes on hold), and post-call actions (add to calendar with business address). The instructions are directly executable without ambiguity. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced into before/during/after phases with explicit validation checkpoints: check calendar for conflicts, gather all required info before dialing, get explicit consent before calling, handle edge cases (AI refusal, missing info, hold times, unavailable slots). Error recovery paths are well-defined throughout. | 3 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized into three clear sections (Before/On/After the call) with logical progression. The skill is under 80 lines and doesn't need external references — everything is appropriately contained in a single file with good structural organization. | 3 / 3 |
Total | 11 / 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.