one-drive-automation
Automate OneDrive file management, search, uploads, downloads, sharing, permissions, and folder operations via Rube MCP (Composio). Always search tools first for current schemas.
69
58%
Does it follow best practices?
Impact
85%
1.70xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/one-drive-automation/SKILL.mdQuality
Discovery
67%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 good job listing specific OneDrive operations and naming the integration platform, making it distinctive and specific. However, it lacks an explicit 'Use when...' clause that would help Claude know exactly when to select this skill, and some of the terminology (Rube MCP, Composio) is technical rather than user-facing. Adding natural trigger phrases would improve selection accuracy.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about OneDrive files, cloud storage on OneDrive, sharing OneDrive links, or managing OneDrive folders.'
Include more natural user-facing trigger terms like 'cloud storage', 'share a link', 'OneDrive folder', or 'Microsoft OneDrive' to improve matching against common user phrasing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: file management, search, uploads, downloads, sharing, permissions, and folder operations. Also specifies the integration mechanism (Rube MCP / Composio). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with a list of OneDrive operations, but lacks an explicit 'Use when...' clause. The 'when' is only implied by the capabilities listed. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes good keywords like 'OneDrive', 'uploads', 'downloads', 'sharing', 'permissions', and 'folder operations', but misses common user variations like 'cloud storage', 'share a file', 'OneDrive link', or file extension mentions. 'Rube MCP (Composio)' is technical jargon unlikely to be used by end users. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to OneDrive specifically, with the additional qualifier of Rube MCP (Composio). This creates a distinct niche that is unlikely to conflict with other file management or cloud storage skills targeting different platforms. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive OneDrive automation reference with good structural organization and useful pitfall documentation. Its main weaknesses are redundancy (pitfalls repeated in workflows and consolidated section), lack of concrete executable examples showing actual tool invocations with sample payloads, and missing explicit validation/confirmation steps for destructive operations like deletes and permission changes.
Suggestions
Add concrete tool invocation examples with sample parameters and expected response shapes for at least the most common workflows (search, upload, share).
Add explicit validation/confirmation steps after destructive operations (delete, permission changes) — e.g., 'After DELETE, call GET_ITEM to confirm 404' or 'After INVITE, call GET_ITEM_PERMISSIONS to verify the new permission appears'.
Consolidate pitfalls into the single 'Known Pitfalls' section and remove duplicates from individual workflows, or vice versa, to reduce redundancy.
Consider extracting the detailed parameter lists and quick reference table into a separate REFERENCE.md file, keeping SKILL.md focused on workflows and key guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite lengthy (~250 lines) with some redundancy—pitfalls are repeated across individual workflows and then again in a consolidated 'Known Pitfalls' section. The quick reference table duplicates information already covered. However, most content is genuinely informative rather than explaining things Claude already knows. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and clear tool sequences, which is good. However, there are no executable code examples or copy-paste ready commands—everything is described at the tool-call level with parameter lists rather than concrete invocation examples showing actual payloads or responses. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with labeled steps (Prerequisite, Required, Optional), which is strong. However, for destructive operations like DELETE and permission changes, there are no explicit validation/verification checkpoints or feedback loops—just a mention to 'verify first' without specifying how to confirm success after the operation. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a quick reference table, but it's monolithic—all content is inline in one file with no references to separate detailed documents. The repeated pitfalls sections and extensive parameter lists could be split into reference files, keeping the main skill leaner. | 2 / 3 |
Total | 8 / 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
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.