airtable

Airtable REST API via curl. Records CRUD, filters, upserts.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/productivity/airtable/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable curl recipes and a clear validated workflow, but it carries redundancy across its three notes-style sections and keeps a large reference catalog inline rather than splitting it into separate files. Consolidating the repeated gotchas and externalizing the reference material would improve both conciseness and progressive disclosure.

Suggestions

Merge 'Pitfalls' and 'Important Notes for Hermes' into a single deduplicated gotchas section to remove repeated restatements of filterByFormula encoding, rate limits, and pagination.

Move the stable field-type write-shape table and/or the full query/mutation catalog into a one-level-deep reference file (e.g. references/field-types.md) referenced from SKILL.md, so the main file stays an overview.

Dimension	Reasoning	Score
Conciseness	The core field-type table and curl patterns are lean and assume competence, but the same gotchas are restated across 'Common Queries', 'Pitfalls', and 'Important Notes for Hermes' (filterByFormula encoding ×3, rate limits ×2, pagination ×2). Not a 3 because this redundancy could be tightened into one canonical notes section.	2 / 3
Actionability	Every section provides fully executable curl commands with real endpoints, auth headers, and JSON bodies — copy-paste ready and complete. Not a 2 because there is no pseudocode or missing key detail.	3 / 3
Workflow Clarity	The 'Typical Hermes Workflow' lays out a 6-step sequence with explicit validation checkpoints (auth→expect 200, inspect schema before mutating, read-before-write, confirm before destructive ops). Not a 2 because validation and feedback for destructive/batch operations are present rather than missing.	3 / 3
Progressive Disclosure	The skill is well-organized into clear sections but is a monolithic ~213-line API reference with no bundle files, matching the '200 lines of API reference that could be in a separate file' anchor. Not a 3 because content such as the field-type table and full query/mutation catalog could be split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and clearly scoped to Airtable, but omits any 'Use when…' trigger guidance and leans on technical jargon (CRUD, upserts) over natural user phrasings. Adding an explicit trigger clause would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when…' clause naming natural user triggers, e.g. 'Use when the user asks to read, create, update, or delete Airtable records, filter a table, or sync data into an Airtable base.'

Soften jargon by adding lay synonyms alongside technical terms — e.g. 'create, read, update, and delete records (CRUD)' and 'insert-or-update (upsert)' — so natural phrasings are covered.

Dimension	Reasoning	Score
Specificity	"Records CRUD, filters, upserts" enumerates multiple concrete capabilities tied to a named API and tool, matching the 'lists multiple specific concrete actions' anchor. Not a 2 because the action coverage is comprehensive rather than partial.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when…' or equivalent trigger guidance for when to use it, so completeness is capped at 2 per the judging guidelines. Not a 1 because the 'what' half is explicit and concrete.	2 / 3
Trigger Term Quality	"Airtable", "records", and "filters" are natural user terms, but "CRUD", "upserts", "REST API", and "curl" lean technical and common phrasings like "Airtable base/table" are absent. Not a 3 because coverage of natural phrasings is narrow rather than broad.	2 / 3
Distinctiveness Conflict Risk	Naming the specific product "Airtable" with its REST API pins a clear niche unlikely to collide with other skills. Not a 2 because the brand-specific framing leaves little overlap risk.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/productivity/airtable/SKILL.md
Commit: d0d116b

Reviewed: about 13 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.