Name: pro-ledger
Rating: 58.4 (1 reviews)
Author: membranedev

pro-ledger

Pro Ledger integration. Manage Accounts, Contacts, Invoices, Reports. Use when the user wants to interact with Pro Ledger data.

Quality

68%

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/pro-ledger/SKILL.md

Quality

Content

68%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 well-organized and largely executable, guiding connection setup with a real poll-and-branch loop. It is held back by missing validation around destructive action/proxy operations and a broken step reference, plus minor verbosity and no external reference structure.

Suggestions

Add an explicit validation/verification checkpoint before running destructive or batch actions and proxy mutating requests (verify the connection is READY and confirm the action's effect), and fix the dangling "skip to Step 2" reference.

Provide at least one fully filled example (concrete agentType, actionId, CONNECTION_ID, and a sample --input JSON) so the action/proxy commands are end-to-end runnable.

Trim the conversational padding ("so you can focus on...", "This is the fastest way...") and move the proxy flag table or action reference into a separate reference file if the skill grows.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable commands and tight tables, but it keeps a few padded lines ("so you can focus on the integration logic rather than auth plumbing", "This is the fastest way to get a connection") and a bare overview bullet list, fitting anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Commands are concrete and copy-pasteable (npm install, membrane login, connection ensure, the proxy flag table), but placeholders like <agentType>, <actionId>, and CONNECTION_ID are templated without a filled example, leaving minor gaps consistent with anchor 4.	4 / 5
Workflow Clarity	The connection flow has an explicit poll/branch sequence, but running actions and proxy requests (DELETE/PATCH) are destructive/batch-capable operations with no validation or verify step, which per the rubric caps workflow_clarity at 3; a dangling "skip to Step 2" with no Step 2 also breaks the sequence.	3 / 5
Progressive Disclosure	There are no bundle files (references/scripts/assets absent) and the ~120-line body has no one-level-deep references, but section headers and the docs link provide good structure with only minor organization gaps, matching anchor 4 rather than the well-split reference structure of anchor 5.	4 / 5
	Total	15 / 20 Passed

Description

67%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 cleanly states what it does and when to use it with named domain objects and an explicit trigger clause. Its main weakness is generic wording (one "Manage" verb, no synonyms) that leaves the trigger phrases broad and somewhat overlapping with general accounting skills.

Suggestions

Replace the single verb "Manage" with distinct concrete actions per object (e.g., "Create and send invoices, reconcile accounts, manage contacts, generate reports") to lift specificity and trigger-term quality.

Expand the when-clause with natural user phrases and synonyms (e.g., "Use when the user mentions invoices, billing, accounts, contacts, or Pro Ledger data").

Add the file/data extensions or noun variants a user would actually say to broaden trigger-term coverage and reduce overlap with generic accounting skills.

Dimension	Reasoning	Score
Specificity	"Manage Accounts, Contacts, Invoices, Reports" names four concrete domain objects, above the 1-2 action threshold of anchor 3 but short of the multiple distinct concrete actions of anchor 5 because a single generic verb "Manage" governs all of them.	4 / 5
Completeness	It has both a clear "what" ("Manage Accounts, Contacts, Invoices, Reports") and an explicit "when" ("Use when the user wants to interact with Pro Ledger data"), but the when-clause is broad rather than packed with concrete trigger phrases, matching anchor 4 not 5.	4 / 5
Trigger Term Quality	It lists relevant nouns (Accounts, Contacts, Invoices, Reports, Pro Ledger) but offers no synonyms or variations users might say, and "interact with Pro Ledger data" is generic, fitting anchor 3's "some relevant keywords but missing common variations".	3 / 5
Distinctiveness Conflict Risk	"Pro Ledger integration" plus named accounting objects carves a clear niche with only minor overlap risk against generic accounting/CRM skills; it is not the fully-distinct-minimal-risk anchor 5 because the triggers stay generic.	4 / 5
	Total	15 / 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/pro-ledger/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.