CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dropbox-automation

Automate Dropbox file management, sharing, search, uploads, downloads, 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/dropbox-automation/SKILL.md

The canonical home for this skill is dropbox-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.

A dense, well-organized operator's manual with concrete tool sequences, parameters, and pitfalls that assumes competence and avoids concept explanations. Its weaknesses are significant duplication between workflow pitfalls, the Known Pitfalls section, and the Quick Reference table; missing pre-delete validation on destructive operations; and no use of separate reference files to keep SKILL.md lean.

Suggestions

Add a validation checkpoint before destructive/batch operations, e.g., "Confirm the canonical path with DROPBOX_GET_METADATA and verify with the user before DROPBOX_DELETE_FILE_OR_FOLDER or DELETE_BATCH."

De-duplicate content: keep each pitfall in one place and either cut the Known Pitfalls section or the per-workflow Pitfalls blocks, and drop or move the Quick Reference table that re-lists every tool and parameter.

Move the per-tool parameter detail and Quick Reference table into a references/ file (e.g., TOOLS.md), leaving SKILL.md as a workflow-focused overview that points to it.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no concept padding) but repeats material: the 10,000-match search cap, base64 file_content_bytes, 409 Conflict on shared links, path-casing rules, and SAVE_URL timeout each appear in both per-workflow "Pitfalls" and again in "Known Pitfalls", and the Quick Reference table re-lists every tool and parameter. This matches "mostly efficient but could be tightened" rather than the padded verbosity of 2.

3 / 5

Actionability

Concrete tool slugs with exact parameters, example values ("/Documents", "2026-12-31T23:59:59Z", ["jpg", "png"]), error codes, and numeric limits give mostly executable guidance. It falls short of 5 only because no complete example call payloads are shown, so calls are not fully copy-paste ready.

4 / 5

Workflow Clarity

Sequences are clearly ordered with Required/Optional markers and some validation (GET_METADATA before link creation, LIST_SHARED_LINKS to avoid 409, batch-status polling), but the destructive delete and batch move operations have no verification step — no path confirmation via GET_METADATA or explicit check before delete. Per the rubric guideline, missing validation on destructive/batch operations caps workflow clarity at 3.

3 / 5

Progressive Disclosure

The ~225-line body is well-sectioned but entirely monolithic: per-tool parameter detail and the 22-row Quick Reference table are content that belongs in a separate reference file, and no bundle files exist. "Some structure but content that should be separate is inline" fits better than 4, while the clear section headers keep it above 2.

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.

A strong, specific description that names the domain and concrete capabilities with good natural keywords. Its main weakness is the missing explicit 'Use when...' trigger clause, which caps completeness and leaves activation guidance implicit.

Suggestions

Append an explicit trigger clause, e.g., "Use when the user mentions Dropbox, wants to upload/download or share files, or asks to organize Dropbox folders."

Add natural trigger synonyms and variants users say, such as "sync", "share links", or "Dropbox Paper", to broaden keyword coverage.

Drop the implementation directive "Always search tools first for current schemas" from the description; it belongs in the body, not the trigger text.

DimensionReasoningScore

Specificity

The description lists six concrete action areas — "file management, sharing, search, uploads, downloads, and folder operations" — giving comprehensive coverage comparable to the anchor-5 example. No single capability group is missing, so it does not fall to 4.

5 / 5

Completeness

The "what" is clearly stated (automating Dropbox operations), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline. It is not 4 because 'when' is entirely absent rather than merely under-specified.

3 / 5

Trigger Term Quality

Natural terms like "Dropbox", "sharing", "search", "uploads", and "downloads" match what users would say, but common synonyms and variants (e.g., "sync", "share links", "Dropbox Paper", file extensions) are absent. Good coverage without synonym breadth places it at 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

"Dropbox" plus "via Rube MCP (Composio)" carves out a clear niche with distinct triggers and minimal overlap with other file-related skills, matching the anchor-5 example. No neighboring anchor fits better.

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/dropbox-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.