CtrlK
BlogDocsLog inGet started
Tessl Logo

box-automation

Automate Box operations including file upload/download, content search, folder management, collaboration, metadata queries, and sign requests through Composio's Box toolkit.

46

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/box-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill covers Box operations comprehensively but suffers from significant verbosity and repetition, with pitfalls and parameter details duplicated across sections. It lacks executable examples and validation checkpoints for destructive operations. The monolithic structure would benefit from splitting detailed reference material into separate files, keeping the main SKILL.md as a concise overview.

Suggestions

Remove duplicated content: consolidate pitfalls into one section, remove the Known Pitfalls section that repeats workflow-specific pitfalls, and trim parameter details that would be available from RUBE_SEARCH_TOOLS schemas.

Add explicit validation steps to destructive workflows (delete folder, delete file) such as 'Verify folder contents before deletion' and 'Confirm deletion succeeded by checking folder no longer exists'.

Split the quick reference table and detailed parameter documentation into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with workflow sequences.

Add at least one concrete, executable example showing an actual tool invocation with realistic parameter values rather than just listing parameter names.

DimensionReasoningScore

Conciseness

The skill is significantly verbose with substantial repetition. The 'Known Pitfalls' section rehashes pitfalls already listed under each workflow. The 'Common Patterns' section repeats ID format info mentioned in pitfalls. The quick reference table duplicates tool names and parameters already covered in detail above. Much of this content (what IDs are, how pagination works) is information Claude can infer from tool schemas retrieved via RUBE_SEARCH_TOOLS.

2 / 5

Actionability

The skill provides tool names and parameter lists, which is somewhat concrete, but lacks executable code examples or copy-paste ready command sequences. The guidance is mostly descriptive ('use this tool with these params') rather than showing actual invocations with example values. Since the skill instructs to call RUBE_SEARCH_TOOLS first to get schemas, much of the parameter documentation is redundant with what the tool schemas would provide.

3 / 5

Workflow Clarity

Workflows have clear sequences with labeled steps (Prerequisite, Required, Optional), but lack validation checkpoints and error recovery loops. For destructive operations like folder deletion, there's no explicit 'verify before proceeding' step or feedback loop. The delete workflow mentions pitfalls but doesn't integrate validation into the step sequence itself. Per rubric guidelines, missing validation for destructive operations caps this at 3.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with no references to supporting files. The quick reference table, detailed pitfalls for each workflow, common patterns, and known pitfalls sections result in a very long document that would benefit from splitting into separate reference files. There are no bundle files to offload content to, and the skill doesn't attempt any structural separation.

2 / 5

Total

10

/

20

Passed

Description

58%Scale 1-5

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 does a reasonable job listing specific Box operations and naming the tooling (Composio), providing moderate specificity and distinctiveness. Its main weakness is the complete absence of a 'Use when...' clause, which limits Claude's ability to know when to select this skill. Some trigger terms are too technical or broad to match natural user language.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Box cloud storage, uploading/downloading files to Box, or managing Box folders and collaborations.'

Include natural synonyms and variations users might say, such as 'Box cloud storage', 'Box API', 'share files on Box', or 'e-signature via Box Sign'.

DimensionReasoningScore

Specificity

Lists several specific actions: file upload/download, content search, folder management, collaboration, metadata queries, and sign requests. These are concrete capabilities, though some like 'collaboration' and 'folder management' are somewhat broad.

4 / 5

Completeness

The 'what' is clearly stated with multiple specific operations, but there is no explicit 'when' clause (e.g., 'Use when...'). The absence of a 'when' clause caps this at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes relevant keywords like 'Box', 'file upload/download', 'content search', 'sign requests', and 'Composio'. However, it misses natural user phrases like 'share files on Box', 'Box API', or variations users might say. The term 'Composio's Box toolkit' is more technical than what users would naturally say.

3 / 5

Distinctiveness Conflict Risk

Specifying 'Box' and 'Composio's Box toolkit' makes this fairly distinct from generic file management skills. However, terms like 'file upload/download' and 'folder management' could overlap with other cloud storage or file management skills.

4 / 5

Total

14

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.