hire-help
Help find and book a service provider for a task — cleaning, handyman, moving, assembly, yard work, errands, etc. Searches TaskRabbit, Handy, Thumbtack, and similar platforms.
78
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/hire-help/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 and trigger term coverage, listing concrete service categories and platform names that users would naturally mention. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude more confidently select this skill. Adding that clause would elevate this from good to excellent.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to hire someone for a home task, find a local service provider, or mentions platforms like TaskRabbit or Thumbtack.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions ('find and book a service provider') and enumerates specific task types (cleaning, handyman, moving, assembly, yard work, errands) along with specific platforms (TaskRabbit, Handy, Thumbtack). | 3 / 3 |
Completeness | Clearly answers 'what' (find and book service providers across platforms) but lacks an explicit 'Use when...' clause. The when is only implied through the task examples and platform names, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes many natural keywords users would say: 'cleaning', 'handyman', 'moving', 'assembly', 'yard work', 'errands', plus platform names like 'TaskRabbit', 'Thumbtack', 'Handy'. These are terms users would naturally use when seeking help with home services. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of home service tasks, specific platform names, and the 'find and book a service provider' framing creates a clear niche that 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 concierge workflow with clear sequencing and good validation checkpoints, particularly around booking confirmation and error recovery. Its main weaknesses are the vagueness of the core search/booking action (no concrete mechanism for actually searching platforms) and moderate verbosity in areas where Claude could infer context. The platform mapping is useful but the skill would benefit from concrete instructions on how to interact with each platform.
Suggestions
Add concrete, executable guidance for how to actually search each platform — browser automation commands, specific URLs to navigate, or API endpoints to call — rather than just saying 'search for providers.'
Trim the common task type list and prep tips, which Claude can generate contextually; focus token budget on the platform-specific booking mechanics that Claude wouldn't know.
Consider splitting platform-specific booking flows into separate reference files (e.g., TASKRABBIT.md, THUMBTACK.md) to keep the main skill lean and enable progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary verbosity — e.g., listing common task types Claude could infer, explaining why finding help is stressful, and providing prep tips that are general knowledge. The platform-to-task mapping and summary card format earn their place, but overall it could be tightened. | 2 / 3 |
Actionability | The skill provides a clear step-by-step flow with specific tool calls (ask_user_input_v0) and structured output formats (summary card), but lacks concrete executable code or commands. The 'search for providers across relevant platforms' step is vague — there's no indication of how to actually search these platforms (API calls, browser automation, specific URLs), making the core action abstract rather than executable. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with 9 numbered steps, includes explicit validation checkpoints (step 7 confirmation before booking, step 9 error recovery with alternatives), and has a clear feedback loop for vague tasks (follow-up questions). The handoff point for login/payment is explicitly marked, and the 'get explicit OK' checkpoint before committing money is well-placed. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no references to supporting materials. For a skill of this complexity — covering multiple platforms, various task types, and booking flows — it would benefit from separate reference files for platform-specific booking instructions or task-type guidance. However, at ~80 lines it's not egregiously long. | 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.