CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clerkio

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

Quality

62%

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/clerkio/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 provides a clear, executable workflow for connecting to Clerk.io and discovering/running actions via the Membrane CLI, with good state-handling branches for connection readiness. Weaknesses are modest: a padded overview paragraph, a duplicated command, and thin guidance on parsing outputs and handling configuration errors.

Suggestions

Trim the opening marketing paragraph ('It helps online stores increase sales... It is used by ecommerce businesses looking to improve conversion rates') to one factual sentence about what Clerk.io is.

Show how to extract the connection id from the 'membrane connection ensure --json' output (e.g., a jq snippet) since every subsequent command needs it.

Standardize CLI invocation ('membrane' vs 'npx @membranehq/cli') and merge the duplicated action-list command in 'Popular actions' into the earlier 'Searching for actions' section.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but the opening marketing paragraph ('Clerk.io is an ecommerce personalization platform. It helps online stores increase sales...') is padding, and the action-list command is duplicated across 'Searching for actions' and 'Popular actions'. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened', not level 4 which requires only minor trims.

3 / 5

Actionability

Concrete executable commands throughout (install, login with headless fallback, connection ensure, action run with --input JSON, proxy flags table) cover the common cases. Minor gaps: no example of extracting the connection id from the JSON output, and inconsistent CLI invocation ('membrane' vs 'npx @membranehq/cli') — matches 'mostly executable guidance with minor gaps', just below copy-paste-ready level 5.

4 / 5

Workflow Clarity

Clear sequence (install → login → connect → wait → search → run → proxy fallback) with state-based decision branches (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and a re-poll feedback loop after the user completes an action. Not 5 because recovery guidance for CONFIGURATION_ERROR is thin ('check the error field for details') and no validation is described for the run results themselves.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ all absent), and the single ~150-line file is well-sectioned (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices). Minor organization gaps — the proxy flag table and client-action state details are inline content that could live in a reference file — match anchor 4 rather than the cleanly split structure of anchor 5.

4 / 5

Total

15

/

20

Passed

Description

41%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 has an explicit and appropriately scoped 'Use when' clause anchored to a distinct niche (Clerk.io), but the 'what' is generic. 'Manage data, records, and automate workflows' could describe almost any integration skill, and the only real trigger term is the product name itself.

Suggestions

Replace the generic 'Manage data, records, and automate workflows' with concrete Clerk.io capabilities, e.g., 'Sync products, orders, customers, and categories; manage search terms, banners, and recommendations'.

Add natural trigger keywords users would actually say, such as 'ecommerce personalization', 'product recommendations', 'Clerk search', or 'Clerk.io data sync'.

State the mechanism briefly (e.g., 'via the Membrane CLI') so the 'what' answers what the skill does, not just which domain it targets.

DimensionReasoningScore

Specificity

The description names the domain ('Clerk.io integration') but its actions are generic — 'Manage data, records, and automate workflows' gives no concrete Clerk.io capabilities (e.g., syncing products, fetching orders, managing search terms). This matches the anchor for naming the domain with minimal or generic actions, not the level above which requires 1-2 concrete actions.

2 / 5

Completeness

The 'when' is explicit ('Use when the user wants to interact with Clerk.io data') but the 'what' is vague ('Manage data, records, and automate workflows' does not say what the skill actually does). It falls between a clear 'what' with weak 'when' (3) and both present with 'when' improvable (4) — the 'when' is fine but the 'what' is not clear, so it cannot score 4.

3 / 5

Trigger Term Quality

The only keywords are 'Clerk.io' (repeated) and the generic 'data'; natural phrases users would say (products, orders, recommendations, search, ecommerce personalization) are absent. This is one or two generic keywords missing the natural phrases users actually say.

2 / 5

Distinctiveness Conflict Risk

'Clerk.io' is a clear niche trigger tied to an explicit 'Use when' clause, giving minimal conflict risk; however the generic opening ('Manage data, records, and automate workflows') creates minor overlap risk with other data-management skills, keeping it just below the clear-niche anchor 5.

4 / 5

Total

11

/

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/clerkio/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.