CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apptus

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

Quality

70%

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/apptus/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 is a largely executable, command-first guide with good error-state handling for the connection lifecycle and a sensible action-before-proxy strategy. Its main weaknesses are a padded, generic entity list in the Overview, incoherent step numbering (dangling 'Step 2' references, an orphan '1b' section), and one malformed bullet ('- **Data Deduplication' is missing its closing '**').

Suggestions

Delete or drastically trim the 'Apptus Overview' bullet list of generic data-terms (Data Mapping, Data Cleansing, Data Governance, etc.) — none of it is used or Apptus-specific; keep only the one-paragraph platform description and the docs link.

Fix the broken flow references: either label the sections as Steps 1/2 or replace 'skip to **Step 2**' with the actual section name ('Searching for actions'), and rename '#### 1b' to fit a consistent numbering scheme.

Fix the malformed markdown on the 'Data Deduplication' bullet (missing closing '**'), and show one concrete end-to-end action example (a real actionId with its input) to bridge the discovery-to-execution gap.

DimensionReasoningScore

Conciseness

The CLI instructions are tight and command-first, but the 'Apptus Overview' section is ~20 bullets of generic data-terms ("Data Source", "Data Cleansing", "Data Governance", "Data Quality") with no Apptus-specific meaning attached — padding that teaches nothing actionable. This fits 'Mostly efficient but includes some unnecessary explanation or could be tightened'; it stays below 4 because that list is a substantial padded block, not a minor trim.

3 / 5

Actionability

Nearly every section gives a copy-paste-ready command with realistic arguments ('membrane connection ensure "https://www.apptus.com" --json', action run with --input JSON, a full proxy flag table), plus headless-auth fallback. It fits 'Mostly executable guidance; concrete code or commands with minor gaps' — below 5 because no concrete action names/examples are shown and CONNECTION_ID placeholders are never instantiated end-to-end.

4 / 5

Workflow Clarity

The sequence (install → login → connection ensure → poll states → handle clientAction → search actions → run → proxy fallback) is clear with state-based checkpoints and error recovery for CLIENT_ACTION_REQUIRED and CONFIGURATION_ERROR. It fits 'Clear sequence with most checkpoints present; minor validation gaps' — below 5 because the text twice says 'skip to Step 2' though no Step 2 is labeled, and '#### 1b' has no matching '1a' or numbered steps, leaving the numbered flow incoherent.

4 / 5

Progressive Disclosure

As a single-file skill with no bundle files, the body is organized into well-labeled sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) and stays a reasonable length for on-demand loading. This fits 'Good structure; most content is appropriately placed; references mostly clear; minor organization gaps' — the disorganized Overview entity-list and the dangling step references keep it from 5.

4 / 5

Total

15

/

20

Passed

Description

61%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 a clear, explicit trigger structure and is highly distinctive thanks to naming Apptus, but the capability statement is generic ('Manage data, records, and automate workflows') and trigger coverage is limited to the product name. It reads like a template description applied to any app rather than one tailored to Apptus's merchandising/recommendations domain.

Suggestions

Replace 'Manage data, records, and automate workflows' with Apptus-specific capabilities, e.g. 'Search and run Apptus merchandising actions: product recommendations, product placement, category and attribute data, imports/exports'.

Broaden trigger terms beyond the product name to include natural phrases like 'e-commerce merchandising', 'product recommendations', or 'optimize product placement'.

State what Apptus is (an AI-powered e-commerce merchandising platform) so the skill triggers correctly even when the user hasn't named the tool.

DimensionReasoningScore

Specificity

The description names the domain ("Apptus integration") but the actions are generic: "Manage data, records, and automate workflows" could describe almost any data tool and names no Apptus-specific capability (merchandising, recommendations, product placement). This matches the anchor 'Names the domain but actions are minimal or generic'; it is below anchor 3 because no concrete action like 'extract' or 'fill forms' is stated.

2 / 5

Completeness

Both parts are present: what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Apptus data"). This fits 'Has both what and when; when could be more explicit or specific' — it is above anchor 3 because the when-clause is explicit rather than implied, but below 5 because the what is vague and the when lacks concrete trigger phrases.

4 / 5

Trigger Term Quality

"Use when the user wants to interact with Apptus data" provides the natural trigger "Apptus", but coverage stops there — common variations a user would plausibly say (e-commerce, merchandising, product recommendations, search optimization) are absent even though the body establishes them. This matches 'Some relevant keywords but missing common variations or synonyms'; it does not reach 4 because the only real trigger term is the product name itself.

3 / 5

Distinctiveness Conflict Risk

The "Apptus" qualifier gives a clear niche with a distinct trigger (the product name), so conflict risk with other skills is minimal — matching anchor 5. The generic 'manage data' phrasing alone would overlap broadly, but the explicit Apptus binding keeps it distinct.

5 / 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.

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/apptus/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.