airbyte
Airbyte integration. Manage data, records, and automate workflows. Use when the user wants to interact with Airbyte data.
68
61%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/airbyte/SKILL.mdQuality
Discovery
57%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 correctly identifies the tool (Airbyte) and includes an explicit 'Use when' clause, which is good for completeness. However, it is severely lacking in specificity—it doesn't describe any concrete Airbyte-specific actions like managing connections, syncing sources/destinations, or configuring pipelines. The generic phrasing around 'manage data' and 'automate workflows' creates overlap risk with other data integration skills.
Suggestions
Add specific Airbyte actions such as 'create and manage connections, configure sources and destinations, trigger syncs, monitor sync status'.
Include natural trigger terms users would say like 'data sync', 'ELT pipeline', 'connectors', 'sources', 'destinations', and 'data integration'.
Make the 'Use when' clause more detailed, e.g., 'Use when the user mentions Airbyte, data syncing, ELT pipelines, or configuring data connectors and destinations'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without listing any concrete actions specific to Airbyte. It doesn't describe what specific operations can be performed (e.g., create connections, sync sources, configure destinations). | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' (Use when the user wants to interact with Airbyte data), with an explicit 'Use when...' clause. However, both parts are quite thin in detail. | 3 / 3 |
Trigger Term Quality | It includes 'Airbyte' as a key trigger term and mentions 'data' and 'workflows', but misses natural variations users might say like 'sync', 'connectors', 'sources', 'destinations', 'ELT', 'data pipeline', or 'data integration'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Manage data, records, and automate workflows' is very generic and could overlap with many other data/integration tools. The mention of 'Airbyte' specifically helps distinguish it, but the rest of the description is not distinctive enough. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides solid, actionable CLI commands for interacting with Airbyte through Membrane, with good coverage of the key workflows. Its main weaknesses are unnecessary introductory context about Airbyte, a large table of actions with no descriptions that wastes tokens, and a workflow that could benefit from clearer end-to-end sequencing with explicit error handling steps.
Suggestions
Remove the opening paragraph explaining what Airbyte is and the bare 'Airbyte Overview' bullet list — Claude already knows what Airbyte is.
Either add meaningful descriptions to the popular actions table or remove it entirely and rely on the `action list --intent` discovery mechanism.
Add a numbered end-to-end workflow (e.g., 1. Connect → 2. Discover actions → 3. Run/Create → 4. Validate output) with explicit error handling guidance for failed action runs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explains what Airbyte is, which is unnecessary context for Claude. The 'Airbyte Overview' bullet list adds little value. The popular actions table has 'No description' for every entry, wasting tokens. However, the CLI commands themselves are reasonably concise. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands for every step: installing the CLI, authenticating, connecting, searching for actions, creating actions, polling, and running actions with input parameters. Commands are copy-paste ready with clear placeholder conventions. | 3 / 3 |
Workflow Clarity | The workflow for creating and running actions is reasonably sequenced (search → create if needed → poll → run), and the polling loop with state checks is a good validation checkpoint. However, there's no explicit error recovery guidance for failed action runs, and the overall flow from authentication through to running actions could be more clearly sequenced as a numbered workflow. | 2 / 3 |
Progressive Disclosure | The content is structured with clear headers and sections, but it's somewhat monolithic — the popular actions table and the action creation/polling details could be split into separate reference files. There are no references to external supplementary files for advanced usage patterns. | 2 / 3 |
Total | 9 / 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
- membranedev/application-skills
- Commit
56d7336
- 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.