Name: prove
Rating: 56.00000000000001 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

prove

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

Quality

64%

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/prove/SKILL.md

Quality

Content

69%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 well-structured, actionable CLI workflow with explicit state validation and a polling feedback loop, held back mainly by light marketing prose and a couple of loosely-labeled sequencing references rather than by any structural problem.

Suggestions

Trim the marketing intro and phrases like "so you can focus on the integration logic rather than auth plumbing" to tighten token use.

Label the post-connection section explicitly as "Step 2" so the "skip to Step 2" references resolve cleanly.

Provide one fully-resolved end-to-end example (a concrete actionId and input) to complement the placeholder-based command templates.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight CLI commands, but includes padded prose such as the Prove marketing intro ("helps businesses verify customer identities and reduce fraud"), "so you can focus on the integration logic rather than auth plumbing", and "This is the fastest way to get a connection" that could be trimmed.	3 / 5
Actionability	Copy-paste-ready membrane commands with flags (--json, --wait, --input) cover install, auth, connection, action discovery/execution, and proxying, plus useful response-shape detail ("result is in the `output` field", schema fields); only minor gaps remain from unresolved placeholders like CONNECTION_ID and QUERY.	4.5 / 5
Workflow Clarity	There is a clear install→login→connection→search→run sequence with a state-based feedback loop (poll until READY, handle CLIENT_ACTION_REQUIRED, re-poll) and explicit state validation, but the "skip to Step 2" reference points to an unlabeled section, leaving a minor sequencing gap.	4 / 5
Progressive Disclosure	The single file is well-organized into clear sections (Overview, Install, Auth, Connecting, Searching, Running, Proxy, Best practices) with no bundle files needed, though at ~138 lines some inline material (the proxy flag table, action schema fields) could be split into a reference file.	4 / 5
	Total	15.5 / 20 Passed

Description

58%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 correctly pairs a what with an explicit when-to-use clause and is anchored to a distinct brand, but its capability list is generic and it omits the identity-verification/fraud vocabulary users would naturally invoke.

Suggestions

Replace generic verbs with Prove's concrete capabilities, e.g. "Verify customer identities, retrieve identity attributes, and run fraud-prevention checks".

Expand the trigger to include natural user phrasing: "Use when the user wants to verify identities, prevent fraud, or streamline onboarding with Prove."

Add the file-format or entity cues (e.g. phone numbers, identity tokens) that distinguish this from generic data-integration skills.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Prove domain and three actions, but the actions are generic ("manage data/records") rather than concrete capabilities like identity verification or fraud checks, falling between the domain-only anchor and the concrete-actions anchor.	2.5 / 5
Completeness	It states both a "what" ("Prove integration. Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Prove data"), matching the anchor where both are present but the when could be more specific.	4 / 5
Trigger Term Quality	The description surfaces the brand term "Prove" and the trigger phrase "interact with Prove data", but misses the natural terms a user would actually say (identity verification, fraud prevention, onboarding, identity proofing).	3 / 5
Distinctiveness Conflict Risk	The repeated brand name "Prove" and the Prove-specific trigger make it largely distinct from other skills, though the generic "manage data/records/workflows" phrasing leaves minor overlap risk with general data-integration skills.	4 / 5
	Total	13.5 / 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/prove/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.