CtrlK
BlogDocsLog inGet started
Tessl Logo

unbox

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

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/unbox/SKILL.md
SKILL.md
Quality
Evals
Security

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 is rich with executable Membrane CLI commands and a well-handled connection state machine, but it is dragged down by padding, a broken "Step 2" reference, placeholder-heavy examples, and a monolithic structure with no supporting reference files. It is a competent integration guide that needs tightening and structural refinement.

Suggestions

Remove marketing/padding phrasing (e.g. "so you can focus on the integration logic rather than auth plumbing") and consolidate the duplicated action-discovery commands into one canonical example.

Fix the broken workflow numbering: label an explicit Step 1 and add the missing Step 2 section referenced by "skip to Step 2", or replace the step references with descriptive section links.

Add a validation/verification checkpoint after `action run` (e.g. check the `output` field and handle error states) so destructive or batch operations have a feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands, but padded with marketing phrasing ("so you can focus on the integration logic rather than auth plumbing") and repeated discovery commands, matching anchor 3 "Mostly efficient but includes some unnecessary explanation or could be tightened." Not 4 because the over-explanation is more than minor; not 2 because it is not severely padded.

3 / 5

Actionability

Provides many concrete, executable commands (connection ensure, action list/run, proxy table) with minor gaps (placeholder CONNECTION_ID/<actionId> and the vague "Use action names and parameters as needed"), matching anchor 4 "Mostly executable guidance; concrete code or commands with minor gaps." Not 5 because placeholders prevent copy-paste readiness for common cases; not 3 because the guidance is largely executable rather than pseudocode.

4 / 5

Workflow Clarity

The connection flow is clearly sequenced with polling and state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a retry loop, matching anchor 4 "Clear sequence with most checkpoints present; minor validation gaps." Not 5 because it references a non-existent "Step 2" and omits validation for action runs; not 3 because explicit checkpoints and a feedback loop are present.

4 / 5

Progressive Disclosure

No bundle files exist; the ~154-line single SKILL.md uses section headers but keeps content that could be split (proxy options table, action discovery) inline, matching anchor 3 "Some structure but could be better organized." Not 4 because there are no well-signaled one-level-deep references and inline bulk could be externalized; not 2 because clear section structure is present rather than minimal/buried organization.

3 / 5

Total

14

/

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 distinct brand trigger, but its action vocabulary is generic and its trigger coverage is narrow. It sits solidly above average but lacks the concrete, comprehensive wording of a top-tier description.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with concrete Unbox actions a user would actually request, e.g. query subscription records, retrieve tracking details, or run billing workflows.

Broaden the when-clause with the natural phrases users would say, such as "subscription data", "Unbox records", or "recurring billing" rather than only "interact with Unbox data".

Keep third-person voice consistent and ensure the trigger phrases cover the Overview entities (Package, Tracking Details, Account) so the description matches the body.

DimensionReasoningScore

Specificity

Names the domain (Unbox) and a couple of actions ("Manage data, records, and automate workflows") but the actions are generic rather than concrete, matching anchor 3 "Names domain and 1-2 concrete actions, but not comprehensive." Not 4 because there are not several specific actions; not 2 because it goes beyond minimal naming.

3 / 5

Completeness

States both what ("Unbox integration. Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Unbox data"), matching anchor 4 "Has both 'what' and 'when'; 'when' could be more explicit or specific." Not 5 because the when-clause is a single narrow trigger; not 3 because both what and an explicit when are present.

4 / 5

Trigger Term Quality

Includes the brand term and a natural phrase ("when the user wants to interact with Unbox data") but lacks synonyms or variations, matching anchor 3 "Some relevant keywords but missing common variations or synonyms." Not 4 because keyword coverage is narrow; not 2 because it has more than one-or-two generic keywords.

3 / 5

Distinctiveness Conflict Risk

The Unbox brand is a distinct SaaS niche with a specific trigger ("interact with Unbox data"), but the generic "Manage data, records" portion creates minor overlap risk, matching anchor 4 "Mostly distinct; minor overlap risk." Not 5 because the non-branded portion is generic; not 3 because the branded trigger is clearly distinct.

4 / 5

Total

14

/

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.

Validation15 / 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
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.