create-bubble
Create a new Bubble integration for Bubble Lab following all established patterns and best practices from CREATE_BUBBLE_README.md
66
48%
Does it follow best practices?
Impact
100%
2.94xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/create-bubble/SKILL.mdQuality
Discovery
32%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 identifies a specific domain (Bubble integrations for Bubble Lab) but lacks concrete action details, natural trigger terms, and an explicit 'Use when...' clause. It reads more like an internal task instruction than a skill description designed for selection among many skills.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'Bubble integration', 'new Bubble plugin', 'Bubble Lab connector', 'add Bubble app'.
List specific concrete actions the skill performs, such as 'scaffolds integration files, configures API endpoints, sets up authentication, and registers the integration in Bubble Lab'.
Remove the internal file reference ('CREATE_BUBBLE_README.md') from the description and instead describe the patterns/best practices in user-facing terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('Bubble integration for Bubble Lab') and a general action ('Create'), but does not list multiple specific concrete actions like setting up API connections, configuring workflows, or defining data types. | 2 / 3 |
Completeness | It describes what (create a Bubble integration) but has no explicit 'Use when...' clause or equivalent trigger guidance, and the 'what' itself is thin. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'Bubble integration' and 'Bubble Lab', but misses common variations a user might say such as 'plugin', 'connector', 'no-code integration', or 'Bubble app'. The reference to 'CREATE_BUBBLE_README.md' is an internal file reference, not a natural user trigger term. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Bubble Lab' and 'Bubble integration' provides some specificity, but 'integration' is a broad term that could overlap with other integration-related skills. The reference to a specific README adds some distinctiveness but is not user-facing. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable, project-specific skill that provides concrete file paths, code templates, and a comprehensive registration checklist. Its main weaknesses are length (some content is repeated or could be offloaded to referenced files) and the lack of intermediate validation checkpoints in a complex multi-step, multi-file workflow. The skill would benefit from trimming redundant sections and adding explicit verification gates between major steps.
Suggestions
Add intermediate validation checkpoints between steps (e.g., 'Run pnpm run typecheck after creating the schema file before proceeding to the main class') to catch errors early in this complex multi-file workflow.
Remove the 'Key Patterns to Follow' section or merge its content into the relevant steps where those patterns are first introduced, to eliminate redundancy.
Consider offloading the 12-location registration checklist to a separate referenced file (e.g., REGISTRATION_CHECKLIST.md) and keeping only a summary in the main skill, improving progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is project-specific registration steps and patterns that Claude wouldn't inherently know. However, some sections like the 'Key Patterns to Follow' repeat guidance already covered in earlier steps (e.g., type safety, schema best practices), and the template code could be more tightly written. Some explanatory text like 'Integration flow tests are complete BubbleFlow workflows that exercise all bubble operations end-to-end' is unnecessary padding. | 2 / 3 |
Actionability | The skill provides concrete folder structures, executable TypeScript code templates, specific file paths for all 12 registration locations, exact commands for verification, and a detailed checklist. The guidance is highly specific and copy-paste ready for someone working in this codebase. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced and includes a verification step with specific commands. However, there are no validation checkpoints between steps 2-6 (e.g., no 'verify the schema compiles before proceeding to the main class'), and the 12-location registration checklist in Step 7 lacks any intermediate verification. For such a complex multi-file operation, missing feedback loops between steps caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill references CREATE_BUBBLE_README.md and several reference implementations by path, which is good. However, the skill itself is quite long (~200 lines) and inlines substantial detail that could be split into referenced files (e.g., the 12-location registration checklist, the integration test template, the key patterns section). The content would benefit from a more concise overview with deeper details offloaded. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- bubblelabai/BubbleLab
- Commit
e64b246
- 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.