Name: finch
Rating: 61.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

finch

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

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/finch/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 body is highly actionable with executable commands and a clear connection workflow including polling and state-based checkpoints. Minor gains come from trimming the introductory context paragraph and adding validation guidance for destructive proxy calls.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable commands and minimal padding, though the opening "Finch is a unified API for employment systems..." paragraph and a couple of explanatory sentences restate context Claude can infer, placing it just below the fully lean level 5.	4 / 5
Actionability	Commands are copy-paste ready throughout ("npm install -g @membranehq/cli@latest", "membrane connection ensure", "membrane action run", "membrane request") with concrete flags and JSON examples covering the common cases, matching the fully executable anchor.	5 / 5
Workflow Clarity	The connect-then-use sequence is clearly laid out with explicit state checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a poll-after-user-action feedback loop, but the "Step 2" / "1b" numbering is inconsistent and no validation guards destructive proxy methods (DELETE/PUT), keeping it just below level 5.	4 / 5
Progressive Disclosure	The single file is well organized into clearly labeled sections with no nested references, but at ~140 lines with all content inlined (proxy options, action discovery) it could split some reference material into separate files, fitting the good-structure-with-minor-gaps anchor rather than the ideal split level 5.	4 / 5
	Total	17 / 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 answers both what and when with a clear Finch-specific trigger, but the capability actions are generic and lack concrete Finch operations. Tightening the action list to specific API verbs would raise specificity and trigger coverage.

Suggestions

Replace generic verbs ("Manage data, records") with concrete Finch operations such as "query employment, payroll, and benefits data" to lift specificity.

Add natural trigger synonyms users actually say, e.g. "employee data," "payroll records," or "HR data," to improve trigger term coverage.

Keep the explicit "Use when..." clause but pair it with a sharper capability list so both what and when are concrete.

Dimension	Reasoning	Score
Specificity	Names the Finch domain and a few actions ("Manage data, records, and automate workflows") but the actions are generic rather than concrete API operations, fitting the "1-2 concrete actions but not comprehensive" anchor and falling short of the multi-specific-action level above.	3 / 5
Completeness	Both a "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Finch data") are present, but the "what" could be more specific, matching the "both present, when could be more explicit" anchor rather than the fully concrete level 5.	4 / 5
Trigger Term Quality	"Use when the user wants to interact with Finch data" is a natural trigger phrase, but the supporting keywords ("data, records, workflows") are generic with Finch as the only domain-specific term, missing common synonyms and variations.	3 / 5
Distinctiveness Conflict Risk	"Finch integration" tied to "interact with Finch data" targets a named product niche with a distinct trigger, leaving only minor overlap risk with other HR/employment-data skills rather than the minimal-risk 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/finch/SKILL.md
Commit: f484c82

Reviewed: ~19 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.