CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

accountscore

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

Quality

66%

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/accountscore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 a practical, command-first integration guide with strong polling/error-state handling for connections. Its main weaknesses are an empty 'Overview' section, a duplicated action-list section, and broken step references ('Step 2', '1b.') that make the intended sequence harder to follow than it should be.

Suggestions

Fix the workflow numbering: label the sections as Step 1 (connect), Step 1b (wait), and Step 2 (search/run actions) so the two 'skip to Step 2' references resolve.

Delete or fill in the empty 'AccountScore Overview' bullet section ('Account / Score / Configuration') and merge 'Popular actions' into 'Searching for actions' to remove the duplicated `action list` command.

Make `membrane login` copy-paste ready with a concrete example (e.g. `--tenant=example --clientName=claude`) and standardize on one CLI invocation form.

DimensionReasoningScore

Conciseness

The body is largely command-dense and efficient, but the 'AccountScore Overview' section ('**Account** / **Score** / **Configuration**') is content-free padding, and 'Popular actions' repeats the `action list` command already shown — 'mostly efficient but includes some unnecessary explanation or could be tightened', short of anchor 4.

3 / 5

Actionability

Nearly every section gives executable commands (install, login, connection ensure, polling, action list/run, proxy flag table), but `membrane login --tenant --clientName=<agentType>` is not copy-paste ready without a concrete value, and the CLI is invoked inconsistently (`membrane` vs `npx @membranehq/cli`) — 'mostly executable guidance ... with minor gaps'.

4 / 5

Workflow Clarity

The connect-then-poll-then-act sequence exists with a good state-driven checkpoint (BUILDING/READY/CLIENT_ACTION_ERROR handling and re-poll loop), but the text twice says 'skip to **Step 2**' when no step is numbered or labeled, and the orphan '1b.' heading has no '1.' or '2.' siblings — 'sequence present but checkpoints missing or implicit' in navigation terms, matching anchor 3 rather than 4.

3 / 5

Progressive Disclosure

A single ~150-line file with clear section headers and no external references; nothing is deeply nested or buried, and the size does not demand splitting — 'good structure; most content appropriately placed ... minor organization gaps', short of anchor 5 which expects well-signaled separate reference files.

4 / 5

Total

14

/

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 has an explicit 'Use when' trigger and a distinctive app name, but its capability statement is vague padding that never reveals what AccountScore actually does (churn prediction). It is serviceable but reads like a template filled in for any SaaS integration.

Suggestions

State the core capability concretely, e.g. 'Retrieve churn scores and at-risk account data from AccountScore' instead of 'Manage data, records, and automate workflows'.

Add natural trigger synonyms users would actually say — 'churn', 'churn score', 'customer retention', 'at-risk accounts' — to the 'Use when' clause.

Mention key record types (accounts, scores, configurations) in the description so the 'what' answers more than just 'integration'.

DimensionReasoningScore

Specificity

Only 'AccountScore integration' names the domain; the stated actions — 'Manage data, records, and automate workflows' — are generic and could describe almost any SaaS integration, matching the anchor 'names the domain but actions are minimal or generic' rather than anchor 3's concrete 1-2 actions.

2 / 5

Completeness

Both parts are present: the 'what' ('AccountScore integration. Manage data, records, and automate workflows') and an explicit 'Use when the user wants to interact with AccountScore data' trigger. Not 5 because the 'what' is thin (never states AccountScore predicts churn) and the trigger could be more specific; not 3 because the 'when' is explicit rather than weakly implied.

4 / 5

Trigger Term Quality

'AccountScore' is the natural keyword a user would say, but surrounding terms ('data', 'records', 'workflows') are generic and common variations like 'churn', 'churn score', or 'customer retention' are missing — 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The AccountScore app name gives a clear, distinct trigger with minimal conflict risk, but the generic 'manage data, records, and automate workflows' phrasing overlaps with other app-integration skills — 'mostly distinct; minor overlap risk with closely related skills'.

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/accountscore/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.