Name: fivetran
Rating: 64.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

fivetran

Fivetran integration. Manage Connectors, Groups. Use when the user wants to interact with Fivetran data.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/fivetran/SKILL.md

Quality

Content

82%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 highly actionable CLI guide with well-sequenced connection workflows and explicit state checkpoints. The main gaps are minor: a little concept/marketing padding, no validation guidance for the destructive actions it surfaces, and a large inline actions table that could move to a reference file.

Suggestions

Add a brief validation/confirmation checkpoint before destructive actions (delete-connection, delete-group, delete-destination), e.g. listing the resource and confirming with the user before running delete, to close the workflow_clarity gap.

Move the 20-row "Popular actions" table into a REFERENCES/actions file and keep a short curated subset inline, improving progressive disclosure and token efficiency.

Trim the Fivetran definition paragraph and the "so you can focus on the integration logic" line, which restate concepts Claude already knows.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient operational commands and reference tables, with only minor over-explanation — the opening paragraph defining what Fivetran is and the marketing line "so you can focus on the integration logic rather than auth plumbing" could be trimmed. Not anchor 5 because those few unnecessary explanations remain; not anchor 3 because padding is minor relative to the high-value command content.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands throughout (install, login, connection ensure, --wait polling, action list/run, request) plus concrete action-key and proxy-flag tables that cover the common cases, matching the anchor for fully executable guidance.	5 / 5
Workflow Clarity	The "Connecting to Fivetran" flow is clearly sequenced with state-based checkpoints (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and a poll-retry feedback loop. It is not anchor 5 because destructive operations (delete-connection, delete-group, delete-destination) and batch sync are listed in the actions table without any pre-validation guidance, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Headers are well-organized and navigation is easy, and no nested references exist, but all content lives inline in SKILL.md with the 20-row "Popular actions" table inlined rather than split to a reference file; at ~160 lines the under-50-line simple-skill exception does not apply, so it falls short of anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

73%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 answers both what and when with an explicit trigger clause and a highly distinctive proper-noun niche, but its action vocabulary is generic. Expanding "Manage" into concrete verbs and adding a few natural synonyms would lift specificity and trigger-term coverage.

Suggestions

Replace the generic verb "Manage" with concrete operations, e.g. "Create, update, sync, and delete Connectors and Groups" to improve specificity.

Add natural synonyms users say alongside "Fivetran" — e.g. "data pipeline", "sync", "ETL", or "data warehouse" — to broaden trigger-term coverage.

Make the "when" clause more concrete with multiple trigger phrases, e.g. "Use when the user wants to list, sync, or manage Fivetran connectors and groups."

Dimension	Reasoning	Score
Specificity	"Manage Connectors, Groups" names the Fivetran domain and two target entities, but the single generic verb "Manage" is minimal rather than enumerating concrete operations (create, sync, delete, test). It sits above anchor 2 (one generic action) but below anchor 4 (several specific actions).	3 / 5
Completeness	It has an explicit "what" ("Fivetran integration. Manage Connectors, Groups.") and an explicit "Use when the user wants to interact with Fivetran data" trigger, satisfying both halves; the "when" clause is somewhat generic and lacks multiple concrete trigger phrases, so it is not anchor 5. The present "Use when" clause avoids the cap at 3.	4 / 5
Trigger Term Quality	Natural terms a user would say are present ("Fivetran", "Connectors", "Groups", "Fivetran data"), giving good keyword coverage; common variations like "sync", "ETL", "data pipeline", or "data warehouse" are missing, so it falls short of comprehensive (anchor 5).	4 / 5
Distinctiveness Conflict Risk	"Fivetran" is a unique proper noun naming a specific service, giving a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/fivetran/SKILL.md
Commit: f484c82

Reviewed: ~20 hours ago

Table of Contents

Discovery Implementation Validation

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.