Dropbox integration via Apideck's File Storage unified API — same methods work across every connector in File Storage, switch by changing `serviceId`. Use when the user wants to read, write, upload, or search files, folders, and drives in Dropbox. Routes through Apideck with serviceId "dropbox".
77
73%
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 ./connectors/dropbox/SKILL.mdQuality
Discovery
89%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 well-crafted description that clearly identifies its niche (Dropbox via Apideck), includes explicit trigger guidance, and is highly distinguishable from other skills. The main area for improvement is listing more specific concrete actions beyond the general 'read, write, upload, search' to better convey the full range of capabilities.
Suggestions
Expand the action list with more specific operations like 'create folders, move/copy files, delete items, list directory contents, download files' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Dropbox file operations via Apideck) and mentions actions like 'read, write, upload, or search files, folders, and drives', but doesn't list highly specific concrete actions like 'create folders, move files, list directory contents, download attachments'. | 2 / 3 |
Completeness | Clearly answers both 'what' (Dropbox integration via Apideck's File Storage unified API for file/folder/drive operations) and 'when' (explicit 'Use when the user wants to read, write, upload, or search files, folders, and drives in Dropbox'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Dropbox', 'read', 'write', 'upload', 'search', 'files', 'folders', 'drives', 'Apideck', and the specific serviceId. These cover the natural ways users would phrase requests about Dropbox file operations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'Dropbox', 'Apideck', 'File Storage unified API', and 'serviceId "dropbox"'. This clearly distinguishes it from other file storage connectors or generic file handling skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves as a reasonable connector overview with good progressive disclosure and navigation to related resources. However, it sacrifices actionability by lacking complete examples for key operations (download, folder creation, upload sessions) and includes some verbose marketing-style content that doesn't help Claude execute tasks. The coverage table and entity mapping are valuable, but the skill would benefit from tighter prose and more executable examples.
Suggestions
Add complete, executable examples for the most common operations: downloading a file, creating a folder, and listing folder contents with pagination.
Remove or significantly condense the 'Portable across 5 File Storage connectors' section — the portability point is already made in the intro and doesn't need a separate section with marketing language.
Add a brief decision workflow: 'Check coverage table → if supported, use unified API → if not, use Proxy with downstream URL' with a concrete Proxy example for shared links (the most common gap).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity — the 'Portable across 5 File Storage connectors' section repeats the portability message already stated in the intro, and the marketing-style language ('compounding advantage') adds no actionable value. The 'When to use this skill' section over-explains when activation is appropriate. | 2 / 3 |
Actionability | The minimal example and proxy curl command are concrete and executable, but the upload example is incomplete (missing actual file content/stream), and key operations like downloading, creating folders, and using upload sessions lack examples. The skill relies heavily on external references for actual method signatures and parameters. | 2 / 3 |
Workflow Clarity | There's no clear multi-step workflow with validation checkpoints. The entity mapping table and coverage highlights are useful, but operations like uploading large files via sessions have no step-by-step sequence. The escape hatch (Proxy) is mentioned but lacks a decision flow for when to use it versus the unified API. | 2 / 3 |
Progressive Disclosure | The skill is well-structured as an overview with clear one-level-deep references to SDK skills, OpenAPI specs, best practices, and sibling connectors. Navigation is easy with clearly signaled links and a 'See also' section. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
9e04d86
Table of Contents
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.