Name: deliverect
Rating: 55.2 (1 reviews)
Author: membranedev

deliverect

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

Quality

62%

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/deliverect/SKILL.md

Quality

Content

67%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 body is a solid, command-heavy integration guide with good actionability and a real connection-readiness feedback loop. Its main weaknesses are some trimmable explanatory prose and a dangling "Step 2" cross-reference that slightly weakens workflow navigation.

Suggestions

Remove concept-explainer prose (e.g., the restaurant/POS sentence and "rather than auth plumbing") so every line earns its place for token efficiency.

Fix the dangling "Step 2" reference by labeling the post-connection section (e.g., "## Step 2: Discover and run actions") so the cross-reference resolves.

Add one concrete end-to-end example using a real Deliverect action (e.g., listing recent orders) so the actionability gap between placeholders and real usage closes.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, but includes unnecessary prose such as the Deliverect explainer ("This helps restaurants manage orders efficiently and reduce errors") and filler like "so you can focus on the integration logic rather than auth plumbing" that could be trimmed, matching the mostly-efficient-but-could-tighten level 3.	3 / 5
Actionability	It provides concrete, executable CLI commands for the common cases (login, connection ensure, action list/run, proxy requests) with a flags table, but uses placeholders like CONNECTION_ID and `--intent "QUERY"` and lacks a concrete end-to-end Deliverect example, fitting the mostly-executable level 4.	4 / 5
Workflow Clarity	The connection flow has a clear sequence with an explicit readiness feedback loop (poll until READY, handle CLIENT_ACTION_REQUIRED, surface error states), but the "skip to Step 2" reference has no matching Step 2 anchor, a minor navigation gap that keeps it at level 4.	4 / 5
Progressive Disclosure	With no bundle files, the single SKILL.md is organized into clear, well-labeled sections (Install, Authentication, Connecting, Searching, Actions, Proxy, Best practices); at ~150 lines it stays appropriately single-file, matching level 4 with only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

57%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 is correctly third-person and answers both what and when with an explicit trigger, but the capability actions are generic and the trigger-term coverage lacks Deliverect-specific synonyms. It is functional but could be sharper and more concrete.

Suggestions

Replace "Manage data, records, and automate workflows" with concrete Deliverect actions such as pulling orders, syncing menus/products, and handling location/order webhooks.

Expand trigger terms with specific phrases users would say (e.g., "Deliverect orders", "sync Deliverect menu", "Deliverect POS", "Uber Eats/DoorDash orders") instead of only "Deliverect data".

Tighten the when clause to name the triggering situations (e.g., "Use when the user wants to query or sync Deliverect orders, menus, or locations").

Dimension	Reasoning	Score
Specificity	The description names the domain ("Deliverect integration") but the actions it lists — "Manage data, records, and automate workflows" — are generic and abstract rather than concrete, matching the anchor where the domain is named but actions are minimal or generic.	2 / 5
Completeness	It provides both a (vague) "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Deliverect data"), but the when clause could be more specific, fitting level 4 rather than the fully concrete level 5.	4 / 5
Trigger Term Quality	"Deliverect" and "Deliverect data" are the relevant natural keywords, but no synonyms or specific Deliverect concepts (orders, menus, locations) are included, so coverage has the common-variation gaps described at level 3.	3 / 5
Distinctiveness Conflict Risk	"Deliverect integration" with a Deliverect-specific trigger carves a clear niche with low conflict risk, though the generic "manage data, records, automate workflows" phrasing leaves minor overlap with other integration skills, placing it at level 4.	4 / 5
	Total	13 / 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/deliverect/SKILL.md
Commit: f484c82

Reviewed: 4 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.