Name: nabla
Rating: 62.4 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

nabla

Nabla integration. Manage data, records, and automate workflows. Use when the user wants to interact with Nabla data.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/nabla/SKILL.md

Quality

Content

82%Weight 40%Scale 1-5

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

The content is a strong, command-driven CLI integration guide with concrete executable examples, a clear workflow, and built-in validation feedback loops for connection state. Its main gaps are minor: a few padded phrases and inconsistent step numbering (a "1b" block and a referenced-but-unlabeled "Step 2").

Suggestions

Fix the step numbering: either relabel "1b. Wait for the connection to be ready" as a clean numbered step or add an explicit "Step 2" header where "skip to Step 2" points, so the sequence is unambiguous.

Trim opinional filler such as "so you can focus on the integration logic rather than auth plumbing" to keep every token load-bearing.

Consider moving the detailed connection-state reference and the proxy options table into a REFERENCES.md file, keeping SKILL.md as a tighter overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with command-first blocks, but includes minor trimmable phrasing like "so you can focus on the integration logic rather than auth plumbing", fitting the efficient-with-minor-over-explanation anchor.	4 / 5
Actionability	It provides copy-paste-ready commands throughout (install, login, connection ensure, action list/run, request) plus concrete notes like "The result is in the `output` field of the response", matching the fully-executable anchor.	5 / 5
Workflow Clarity	There is a clear install→auth→connect→search→run sequence with validation via connection-state polling and a retry loop after user action, but step labels are inconsistent (a "1b" subsection and a dangling reference to an unlabeled "Step 2"), keeping it just below the top anchor.	4 / 5
Progressive Disclosure	The single-file skill is well-organized into clear headed sections (Overview, Install, Auth, Connecting, Searching, Running, Proxy, Best practices) with an external docs link and no nested references, though some inline material (detailed connection states, proxy options) could optionally live in a reference file.	4 / 5
	Total	17 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 clearly targets a specific platform (Nabla) and includes an explicit "Use when" trigger, which keeps it distinct and complete. Its main weakness is that the listed actions ("manage data, records, automate workflows") are generic rather than concrete, slightly limiting specificity and trigger richness.

Suggestions

Replace generic verbs with concrete Nabla-specific actions (e.g., "list conversations, send and read messages, manage patient and therapist records") to raise specificity.

Expand trigger terms with natural synonyms users might say, such as "Nabla conversations", "Nabla messages", or "Nabla patient records", beyond just "interact with Nabla data".

Tighten the "when" clause to name the concrete interactions (e.g., "Use when the user wants to read or send Nabla messages, manage conversations, or look up user records").

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" lists a few actions but they are generic rather than concrete API-level operations, fitting the anchor that names the domain with 1-2 actions that are not comprehensive.	3 / 5
Completeness	It states both a "what" ("Manage data, records, and automate workflows") and an explicit "Use when the user wants to interact with Nabla data" trigger, but the "when" is somewhat generic so it sits below the fully concrete anchor 5.	4 / 5
Trigger Term Quality	The trigger centers on the brand "Nabla" and the phrase "interact with Nabla data", which are relevant but lack synonyms or common variations users might say, matching the anchor for some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	"Nabla integration" names a specific branded platform with a distinct trigger ("Nabla"), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/nabla/SKILL.md
Commit: f484c82

Reviewed: 5 days 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.