airtable-automation
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
63
45%
Does it follow best practices?
Impact
96%
1.37xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/airtable-automation/SKILL.mdQuality
Discovery
40%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 identifies a clear niche (Airtable via Rube MCP/Composio) which makes it distinctive, but it lacks specificity in what actions it performs and entirely omits explicit trigger guidance for when Claude should select this skill. The instruction to 'always search tools first' is operational guidance rather than a description of capabilities.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about Airtable records, bases, tables, or wants to automate Airtable workflows.'
Replace 'automate tasks' with specific concrete actions such as 'Create, read, update, and delete records; manage bases, tables, fields, and views in Airtable.'
Move the operational instruction ('Always search tools first for current schemas') out of the description or reframe it as a capability, e.g., 'Discovers current schemas dynamically before performing operations.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Airtable) and lists some entities (records, bases, tables, fields, views), but the actions are vague — 'automate tasks' doesn't specify concrete operations like create, update, delete, or query. | 2 / 3 |
Completeness | It partially answers 'what' (automate Airtable tasks) but there is no explicit 'Use when...' clause or equivalent trigger guidance, and the 'what' itself is vague. The absence of a 'when' clause caps this at 2 per the rubric, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Airtable', 'records', 'bases', 'tables', 'fields', 'views', and 'Rube MCP (Composio)', but misses common user phrases like 'create a record', 'update a table', 'list bases', or 'airtable API'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Airtable' and 'Rube MCP (Composio)' creates a very specific niche that is unlikely to conflict with other skills. The tool and platform are clearly identified. | 3 / 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.
This is a competent Airtable automation skill that covers the major operations with clear tool sequences and useful pitfall documentation. Its main weaknesses are the lack of executable invocation examples (actual tool call payloads), missing validation checkpoints for destructive operations, and some content redundancy across sections. The formula syntax guide and ID format references are genuinely useful additions.
Suggestions
Add at least one complete, executable MCP tool invocation example per core workflow showing the actual JSON parameters passed to the tool (e.g., a full RUBE_SEARCH_TOOLS call followed by AIRTABLE_CREATE_RECORD with realistic field values).
Add explicit validation/confirmation steps in workflows involving destructive operations — e.g., 'Before deleting, list the records matching your filter and confirm the count matches expectations.'
Consolidate the repeated pitfalls (ID formats, batch limits, case sensitivity) into the single 'Known Pitfalls' section and remove duplicates from individual workflow sections to reduce token usage.
Consider adding a brief error recovery pattern: 'If you get a 422, re-fetch the schema with AIRTABLE_GET_BASE_SCHEMA to verify field names before retrying.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy — pitfalls are repeated across sections (e.g., field name case sensitivity, 422 errors), the ID format table repeats information already mentioned inline, and the quick reference table largely duplicates the tool sequences already listed in each workflow. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | The skill provides concrete tool names, parameter names, and formula syntax examples, which is good. However, it lacks executable code/command examples showing actual MCP tool invocations with real parameter structures (e.g., JSON payloads). The guidance is specific but stops short of copy-paste ready examples of actual tool calls. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with labeled steps and prerequisite/optional annotations, which is helpful. However, for destructive operations (delete records, update records, batch operations), there are no explicit validation or confirmation checkpoints. The setup section has a good verification flow, but the core workflows lack feedback loops for error recovery beyond listing pitfalls. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a monolithic document with no references to supporting files. The formula syntax reference, pagination patterns, and quick reference table could be split into separate files. For a standalone skill with no bundle, the inline organization is decent but the document is long enough that splitting would improve navigation. | 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
- davepoon/buildwithclaude
- Commit
d065ead
- 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.