Name: finicity
Rating: 56.8 (1 reviews)
Author: membranedev

finicity

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

Quality

65%

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/finicity/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, mostly executable guide to driving Finicity through the Membrane CLI, with a clear connection state-machine and useful command examples. Its main weaknesses are modest padding and a couple of broken/inconsistent step labels.

Suggestions

Cut the background intro paragraph and the empty 'Finicity Overview' list, and merge the duplicated `action list` example in 'Searching for actions' and 'Popular actions' into one place.

Fix the step labeling: add an explicit 'Step 2' heading (or relabel 'skip to Step 2' to the actual target) and rename '1b' to align with a '1a' step.

Consider moving the detailed clientAction field breakdown and the full proxy flag table into a references file so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient CLI command blocks, but the opening Finicity background paragraph, the near-empty 'Finicity Overview' list, and the duplicated `action list --intent` example between 'Searching for actions' and 'Popular actions' add padding that could be trimmed.	3 / 5
Actionability	It provides concrete, runnable commands throughout (install, login, connection ensure, action run, request) with a clear proxy flag table, fitting 'mostly executable guidance with minor gaps' rather than the fully copy-paste-ready level 5 because of placeholders like CONNECTION_ID and <actionId>.	4 / 5
Workflow Clarity	The connection flow is clearly sequenced with a state-based feedback loop (poll until READY, re-poll after CLIENT_ACTION_REQUIRED), but the 'skip to Step 2' reference points to an unlabeled target and the '1b' heading has no '1a', leaving minor gaps short of level 5.	4 / 5
Progressive Disclosure	The body is a single well-sectioned document with clear headers and no nested references, which is appropriate for a CLI-wrapper skill with no bundle files; it sits at 'good structure with minor organization gaps' rather than 5 because some inline detail (clientAction breakdown, proxy table) could live in references.	4 / 5
	Total	15 / 20 Passed

Description

62%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 uses third person and includes an explicit 'Use when' trigger, but its capability verbs are generic and it offers only a single thin trigger phrase. It is competent but leaves room for more concrete actions and richer trigger terms.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Finicity-specific actions such as 'pull customer transaction history, verify accounts, and generate financial reports'.

Broaden the trigger with natural variations, e.g. 'Use when the user wants to access Finicity financial data, verify accounts, pull transactions, or run Finicity reports'.

Add the file-format or endpoint cues users actually mention (e.g. 'Finicity API', 'customer-permissioned data') to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the Finicity domain plus a couple of actions ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete, matching the 'names domain and 1-2 actions but not comprehensive' anchor rather than the more specific level 4.	3 / 5
Completeness	It states both what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with Finicity data'), but the 'what' is generic so it does not reach the fully concrete level 5.	4 / 5
Trigger Term Quality	The only natural trigger is 'Use when the user wants to interact with Finicity data' — it surfaces the product name but misses common variations or synonyms, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Naming the specific Finicity platform gives it a clear niche with low conflict risk, but the generic 'interact with data' phrasing leaves minor overlap with general data-integration skills rather than the minimal risk of level 5.	4 / 5
	Total	14 / 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/finicity/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.