airbyte
Airbyte integration. Manage data, records, and automate workflows. Use when the user wants to interact with Airbyte data.
54
61%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 names the tool (Airbyte) and includes an explicit 'Use when' clause, which are positives. However, the capabilities listed are extremely vague and could apply to almost any data tool. It fails to describe what Airbyte-specific actions the skill can perform, making it hard to distinguish from other data integration skills.
Suggestions
Replace vague actions with Airbyte-specific capabilities such as 'configure source/destination connectors, trigger syncs, monitor sync status, manage connections and workspaces'.
Add natural trigger terms users would say, such as 'connectors', 'sync', 'ELT pipeline', 'data replication', 'sources and destinations'.
Expand the 'Use when' clause with specific scenarios like 'Use when the user mentions Airbyte, data syncing, ELT pipelines, or configuring data connectors'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The actions listed ('manage data, records, and automate workflows') are extremely vague and generic. There are no concrete actions specific to Airbyte such as configuring connectors, syncing sources/destinations, managing connections, or checking sync status. | 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'). The explicit 'Use when...' clause is present, though both parts are quite shallow in detail. | 3 / 3 |
Trigger Term Quality | It includes 'Airbyte' which is a strong trigger term for the specific tool, but 'data', 'records', and 'workflows' are overly generic. Missing natural terms like 'connectors', 'sync', 'sources', 'destinations', 'ELT', 'data pipeline', or 'data integration'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Airbyte' as a named tool provides some distinctiveness, but 'manage data, records, and automate workflows' is so generic it could overlap with many other data integration or workflow automation skills. The description doesn't clearly carve out Airbyte's specific niche. | 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 Airbyte integration via Membrane with good coverage of connection states and error handling. However, it suffers from unnecessary introductory context about Airbyte, a bulky actions table with no descriptions, and could benefit from better end-to-end workflow sequencing and content splitting into supporting files.
Suggestions
Remove the introductory paragraph explaining what Airbyte is — Claude already knows this. Start directly with the Membrane CLI workflow.
Either add meaningful descriptions to the popular actions table or remove it entirely, as 'No description' entries waste tokens without adding value.
Add an explicit end-to-end numbered workflow (install → auth → connect → discover → run → verify) to make the overall sequence clearer.
Consider splitting the proxy request reference and popular actions table into separate bundle files to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explains what Airbyte is, which is unnecessary context for Claude. The popular actions table with 'No description' entries adds bulk without value. The Membrane explanation is somewhat verbose but mostly justified since it's non-obvious tooling. | 2 / 3 |
Actionability | Commands are concrete, copy-paste ready, and cover the full workflow: installation, authentication, connection setup, action discovery, action execution, and proxy requests. Flag tables and state-handling instructions are specific and executable. | 3 / 3 |
Workflow Clarity | The connection setup workflow has clear sequencing with state-based branching (READY, CLIENT_ACTION_REQUIRED, errors), but there are no explicit validation checkpoints after running actions or proxy requests. The overall flow from install → auth → connect → discover → run is implicit rather than explicitly sequenced as a numbered end-to-end workflow. | 2 / 3 |
Progressive Disclosure | Content is reasonably structured with headers and sections, but everything is in a single monolithic file. The popular actions table and proxy request details could be split into separate reference files. No bundle files exist to offload detailed content, and the external docs link is the only reference. | 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
f484c82
- 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.