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

procountor

Procountor integration. Manage data, records, and automate workflows. Use when the user wants to interact with Procountor 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/procountor/SKILL.md

Quality

Content

63%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 delivers strong actionable CLI guidance with a well-sequenced connection workflow and real validation checkpoints. Its weaknesses are the padded inline entity enumeration and the absence of any progressive-disclosure structure to offload bulk reference material.

Suggestions

Move the long Procountor entity-type list into a separate references file and link to it, keeping only the key concepts inline.

Add a validation/verification step before destructive proxy or action-run operations (e.g. confirm connection state is READY and review the outputSchema before mutating calls).

Standardize command invocations to either `membrane` or `npx @membranehq/cli@latest` consistently to avoid confusing the reader.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands and tight prose, but the ~85-item bullet enumeration of Procountor entity types is padding that Claude does not need and could be trimmed or externalized.	3 / 5
Actionability	It provides concrete, copy-paste-ready CLI commands for install, auth, connection, action discovery, action execution, and proxying, with flag tables and JSON examples; minor gaps include inconsistent `membrane` vs `npx @membranehq/cli` invocation and unsubstituted placeholders.	4 / 5
Workflow Clarity	There is a clear sequenced workflow (install, auth with a headless branch, connection ensure, poll until READY, then search/run actions) with explicit state-checkpoint validation and a feedback loop, though destructive action-run and proxy paths lack their own validation steps.	4 / 5
Progressive Disclosure	Content is organized into clear sections but everything is inline in a single ~230-line file with no external references, and the large entity-type list is bulk material that would be better split into a separate reference file.	3 / 5
	Total	14 / 20 Passed

Description

61%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 names a clear niche (Procountor) and includes an explicit 'Use when' trigger, so it answers both what and when. Its main weakness is generic verbs ('manage', 'automate workflows') that under-specify the concrete financial capabilities the skill exposes.

Suggestions

Replace generic verbs with concrete Procountor capabilities, e.g. 'Create and manage invoices, vouchers, payments, and accounting records in Procountor.'

Add natural trigger variations users might say, such as 'bookkeeping', 'invoicing', or 'Procountor API'.

Tighten the 'when' clause with specific triggers, e.g. 'Use when the user wants to query or update Procountor financial data, invoices, or payments.'

Dimension	Reasoning	Score
Specificity	Names the Procountor domain and a couple verbs ('Manage data, records, and automate workflows') but the actions are generic rather than concrete Procountor operations like invoicing, vouchers, or payments.	2 / 5
Completeness	It states both what it does ('Procountor integration. Manage data, records, and automate workflows') and when to use it ('Use when the user wants to interact with Procountor data'), though the 'when' clause is fairly generic.	4 / 5
Trigger Term Quality	'Procountor' and 'Procountor data' are natural terms a user would say, but there is little synonym or variation coverage beyond the product name.	3 / 5
Distinctiveness Conflict Risk	Procountor is a distinct niche financial product with clear, specific triggers, so there is minimal risk of this skill firing for an unrelated skill.	5 / 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/procountor/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.