airparser
Airparser integration. Manage data, records, and automate workflows. Use when the user wants to interact with Airparser data.
49
53%
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/airparser/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 is minimally functional—it names the integration and includes a 'Use when' clause, but the capabilities described are so generic ('manage data, records, and automate workflows') that they could apply to almost any data integration tool. It fails to explain what Airparser actually does (parsing emails/documents to extract structured data) and lacks the specific trigger terms that would help Claude correctly select this skill.
Suggestions
Replace vague actions with Airparser-specific capabilities, e.g., 'Parse emails and documents to extract structured data, manage inboxes and parsing templates, retrieve extracted records.'
Add natural trigger terms users would say, such as 'parse emails', 'extract data from emails', 'document parsing', 'email inbox', 'structured data extraction'.
Improve distinctiveness by clarifying Airparser's niche (email/document parsing and data extraction) to differentiate it from generic data management or workflow automation skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without listing any concrete actions specific to Airparser. It doesn't explain what Airparser does (e.g., parse emails, extract data from documents) or what specific operations are available. | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' (when the user wants to interact with Airparser data) with an explicit 'Use when' clause. However, both parts are quite shallow in detail. | 3 / 3 |
Trigger Term Quality | It includes 'Airparser' as a keyword and generic terms like 'data' and 'records', but misses natural terms users might say such as 'parse emails', 'extract data from documents', 'email parsing', 'document parsing', or 'inbox'. The trigger terms are too generic to be useful. | 2 / 3 |
Distinctiveness Conflict Risk | 'Manage data, records, and automate workflows' is extremely generic and could overlap with dozens of other integration skills. The mention of 'Airparser' provides some distinctiveness, but the generic action terms create conflict risk with any data management or workflow automation skill. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
50%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 and covers the full workflow from setup to execution, which is its main strength. However, it is verbose — explaining what Airparser is, what Membrane does, and detailing connection states at length when much of this could be condensed. The structure is reasonable but monolithic, with no progressive disclosure to supporting files.
Suggestions
Remove the introductory paragraph explaining what Airparser is and what document parsing means — Claude already knows this. Start directly with the integration overview.
Condense the connection state handling section (BUILDING, CLIENT_ACTION_REQUIRED, etc.) into a compact reference table or move it to a separate CONNECTIONS.md file.
Trim unnecessary filler phrases like 'so you can focus on the integration logic rather than auth plumbing' and 'Think of it as a way to programmatically pull information out of unstructured documents.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explains what Airparser is and what document parsing means — concepts Claude already knows. There's also unnecessary explanation of Membrane's auth handling, agent types, and verbose descriptions of connection states that could be significantly condensed. The skill is quite long for what it conveys. | 1 / 3 |
Actionability | The skill provides fully executable CLI commands for every step: installation, authentication, connection setup, action discovery, running actions, and proxy requests. Commands are copy-paste ready with clear parameter placeholders. | 3 / 3 |
Workflow Clarity | The connection setup workflow has a reasonable sequence with state-based branching (READY, CLIENT_ACTION_REQUIRED, errors), but there are no explicit validation checkpoints after running actions or uploading documents. The overall flow from install → auth → connect → discover → run is present but could be more clearly sequenced with numbered top-level steps. | 2 / 3 |
Progressive Disclosure | The content is structured with headers and a table of popular actions, but it's essentially a monolithic document with no references to external files. The connection state handling details and proxy request documentation could be split into separate reference files to keep the main skill leaner. | 2 / 3 |
Total | 8 / 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.