CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

budget-insight

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

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/budget-insight/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 practical, command-first guide with a genuinely good connection state-machine workflow and executable examples throughout. Main gaps: the 'Popular actions' section is an empty shell repeating a discovery command with no actual Budget Insight actions, the workflow references a 'Step 2' that is never defined, and there is light marketing padding in the intro.

Suggestions

Populate the 'Popular actions' section with real Budget Insight action names and runnable examples (e.g. list transactions, manage budgets and categories, manage users/connections) instead of repeating the discovery command.

Fix the dangling navigation: replace 'skip to Step 2' (referenced twice, never defined) with the actual section name, and reconcile the '1b' heading with a proper step numbering scheme.

Trim the marketing-style opening sentence about who uses Budget Insight, and deduplicate the action-list command between 'Searching for actions' and 'Popular actions'.

DimensionReasoningScore

Conciseness

The body is dominated by tight, executable commands with short justifications, with only minor trimmable material: the marketing-style intro sentence ('It's primarily used by individuals and families looking to gain better control over their finances and achieve their financial goals') and the 'Popular actions' section repeating the action-list command already shown under 'Searching for actions'. Anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed') fits; not 3 since nothing explains concepts Claude already knows, and not 5 since the padding exists.

4 / 5

Actionability

Concrete copy-paste commands cover install, login (incl. headless completion), connection creation with a real URL, --wait polling, action discovery/run with JSON input, and a proxy flags table. Not anchor 5: the 'Popular actions' heading contains no actual action names (no example for transactions, budgets, or categories) and proxy paths are placeholders like '/path/to/endpoint'.

4 / 5

Workflow Clarity

The sequence (install, login, connection ensure, state-machine handling with explicit poll-again feedback loop, discover actions, run, proxy fallback) is clear with real checkpoints for READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR. Anchor 4 rather than 5 because 'skip to Step 2' is referenced twice and a '1b' section exists with no numbered steps or Step 2 defined in the document; not 3 because validation checkpoints are explicit.

4 / 5

Progressive Disclosure

A single-file skill with no bundle files and well-organized section headers; no nested or buried references. Anchor 4 ('Good structure; most content is appropriately placed; minor organization gaps') fits: the proxy flags table and the clientAction state-machine detail are candidates to offload into a reference file given the ~140-line body; not 5 since the simple-skill exception applies to skills under 50 lines.

4 / 5

Total

16

/

20

Passed

Description

57%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, names the target product, and includes an explicit 'Use when' clause, so it is functional. Its weakness is genericness: 'Manage data, records, and automate workflows' conveys no concrete capability and omits the natural finance vocabulary (transactions, budgets, bank accounts) users would actually say.

Suggestions

Replace the generic 'Manage data, records, and automate workflows' with concrete capabilities drawn from the skill's own entity list, e.g. 'Retrieve bank account transactions, manage categories and budgets (incl. budget lines), and manage users and connections via the Budget Insight API'.

Add natural trigger terms to the 'Use when' clause: 'Use when the user mentions Budget Insight, bank transactions, spending categories, budgets, or personal finance data.'

Mention the Membrane connection mechanism briefly so the description distinguishes this integration skill from raw-API alternatives.

DimensionReasoningScore

Specificity

"Manage data, records, and automate workflows" names the domain (Budget Insight) but the actions are generic with no concrete capabilities (no mention of transactions, budgets, categories, or connections). This matches the anchor 'Names the domain but actions are minimal or generic' rather than 3, which requires 1-2 concrete actions.

2 / 5

Completeness

Both clauses are present: what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Budget Insight data"). Anchor 4 fits because the 'when' could be more specific; it is not 3 since the trigger is explicitly stated, and not 5 since neither clause uses concrete trigger phrases.

4 / 5

Trigger Term Quality

"Budget Insight" is the natural keyword users would say, but the finance-domain terms and synonyms (transactions, bank accounts, budgets, spending, personal finance) are all missing. Anchor 3 ('Some relevant keywords but missing common variations or synonyms') fits; it is not 4 because keyword coverage is not good beyond the product name.

3 / 5

Distinctiveness Conflict Risk

The named product "Budget Insight" establishes a clear niche, but "Manage data, records, and automate workflows" is generic phrasing with overlap risk against other data/automation skills. Mostly distinct with minor overlap risk (anchor 4), not 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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/budget-insight/SKILL.md

Reviewed

Table of Contents

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.