CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

72%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/one-drive-automation/SKILL.md

The canonical home for this skill is one-drive-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%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 body is a strong, actionable reference with concrete tool sequences, parameters, and pitfalls that assume Claude's competence rather than explaining basics. Weaknesses are redundancy between workflow-level pitfalls and the 'Known Pitfalls' section, a vacuous 'When to Use' closer, no explicit validation step before destructive delete, and a monolithic single-file layout where per-workflow detail could be split into reference files.

Suggestions

Consolidate pitfalls into one place (either per-workflow or the 'Known Pitfalls' section) and delete the filler 'When to Use' section to remove duplicated content.

Add an explicit verify-before-delete checkpoint to the folder management workflow (e.g., call ONE_DRIVE_GET_ITEM to confirm the item details before ONE_DRIVE_DELETE_ITEM), and honor the cap guidance for destructive operations.

Split per-workflow parameter/pitfall detail into references/ files (e.g., references/search.md, references/sharing.md) linked one level deep, keeping SKILL.md as an overview plus the Quick Reference table.

DimensionReasoningScore

Conciseness

Mostly dense, useful reference material, but there is real duplication: the 'Known Pitfalls' section repeats workflow-level pitfalls verbatim in substance (no KQL/wildcards, 'drive_id' overrides 'user_id', 'permissions' cannot be expanded, copy is async), and the closing 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview') is pure filler. This matches the score-3 anchor ('mostly efficient but includes some unnecessary explanation or could be tightened'), not score 4, where only minor trimming would be needed.

3 / 5

Actionability

Highly concrete for an instruction-only skill: exact tool slugs, parameter names with example values ('"id,name,webUrl,size"', '{"id": "folder_id"}'), and prerequisites marked per step. It falls short of the score-5 anchor due to minor gaps — no example tool-call payloads (e.g., what a RUBE_SEARCH_TOOLS or connection-management invocation actually looks like) and vague entries like 'link type' for ONE_DRIVE_CREATE_LINK — but it is well above score 3, which would require pseudocode-level vagueness.

4 / 5

Workflow Clarity

Sequences are clearly ordered with [Prerequisite]/[Required]/[Optional] markers, and the sharing workflow does include verification (check GET_ITEM_PERMISSIONS first, get explicit confirmation for write roles). However, the destructive delete workflow has no explicit verify-before-delete checkpoint in its sequence, and per the judging guidelines missing validation steps for destructive/batch operations caps workflow clarity at 3. It is not score 2, since sequences are well defined and some checkpoints (connection status, drive access, permission checks) do exist.

3 / 5

Progressive Disclosure

The file is well-sectioned with a useful Quick Reference table, but at ~230 lines all per-workflow parameter and pitfall detail is inlined with no bundle files or one-level-deep references to offload it. This matches the score-3 anchor ('some structure but could be better organized; content that should be separate is inline'); the simple-skill exception (score 5 for short, well-organized skills) does not apply at this length, and the duplication between workflow pitfalls and 'Known Pitfalls' further signals reorganization would help.

3 / 5

Total

13

/

20

Passed

Description

75%Weight 40%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 is specific and distinctive, with a comprehensive list of concrete OneDrive operations and clear tooling context (Rube MCP/Composio). Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3, and the lack of synonym variation in trigger terms.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user asks to upload, download, search, share, or manage files in OneDrive.'

Include natural synonyms and variations such as 'Microsoft OneDrive', 'share links', or 'sync files' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'file management, search, uploads, downloads, sharing, permissions, and folder operations' — giving comprehensive coverage of the OneDrive domain. This matches the score-5 anchor ('Lists multiple specific concrete actions; comprehensive coverage') and exceeds the score-4 anchor, which allows for minor coverage gaps.

5 / 5

Completeness

The 'what' is clearly answered (automating OneDrive file operations via Rube MCP/Composio), but there is no 'Use when...' clause or equivalent trigger guidance — the second sentence ('Always search tools first for current schemas') is procedural, not a trigger. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3 ('clear what but when missing').

3 / 5

Trigger Term Quality

Good natural keyword coverage: 'OneDrive', 'search', 'uploads', 'downloads', 'sharing', 'permissions', 'folder operations' are phrases users would naturally say. It falls short of the score-5 anchor because it lacks synonyms and variations (e.g., 'Microsoft OneDrive', 'sync', 'share links'), while clearly exceeding score 3 ('some relevant keywords but missing common variations').

4 / 5

Distinctiveness Conflict Risk

'OneDrive' names a clear niche with distinct triggers, further distinguished by 'via Rube MCP (Composio)', so conflict risk with other skills is minimal — matching the score-5 anchor. It is not score 4 because it has no meaningful overlap with closely related skills (e.g., generic file-management or Google Drive skills would not match these triggers).

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/one-drive-automation/SKILL.md

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.