CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

airship

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/airship/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 content delivers strong, copy-paste-ready CLI guidance with a well-sequenced connection workflow and good error-state handling. Its main weaknesses are the padded intro and unexplained entity-list section, plus a dangling 'Step 2' reference that suggests the doc was extracted from a larger structure.

Suggestions

Delete or drastically trim the marketing intro paragraph and the 'Airship Overview' bullet list, or replace the bullet list with a one-line note on what those entities mean for action discovery.

Fix the dangling 'skip to Step 2' references — either number the workflow sections explicitly (Step 1: connect, Step 2: discover actions, Step 3: run) or reword to point at the actual section names like 'Searching for actions'.

Add a brief error-checking note after `action run` (e.g. inspect the response for error fields before reporting success) to close the validation gap in the run workflow.

DimensionReasoningScore

Conciseness

The body is mostly efficient command-focused guidance, but the marketing-style intro ('Airship is a customer engagement platform that helps businesses connect with their audience...') and the unexplained 'Airship Overview' bullet list (Crew, Roster, Schedule, Training, etc.) add padding without actionable value. It fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than level 4, where only minor instances could be trimmed.

3 / 5

Actionability

Guidance is fully executable throughout: exact install/login commands including headless completion, `connection ensure` with polling via `--wait`, action list/run with JSON input examples, and proxy requests with a complete flags table. Commands are copy-paste ready and cover the common cases (auth, connection setup, discovery, execution, fallback proxy).

5 / 5

Workflow Clarity

The install → authenticate → connect → poll → discover → run sequence is clear, with explicit state-based checkpoints (READY / CLIENT_ACTION_REQUIRED with its sub-fields / CONFIGURATION_ERROR) and poll-again recovery loops. It falls short of level 5 because 'skip to Step 2' is referenced twice but no Step 2 exists in the document — a dangling reference — and action-run results have no error-checking guidance.

4 / 5

Progressive Disclosure

The body has good structure with well-labeled sections, no nested references, and no monolithic wall of text; at ~145 lines most content is appropriately inline for a CLI-based skill. It misses level 5 because the purposeless 'Airship Overview' entity list and the proxy flags table could live in a separate reference file, and the skill exceeds the under-50-line simple-skill exception.

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 has an explicit 'Use when...' trigger and names a distinct platform, but it undersells the skill with vague action language ('manage data, records') and thin trigger-term coverage. Adding concrete Airship capabilities (push notifications, in-app messages, campaigns) would improve both specificity and trigger quality.

Suggestions

Replace the vague 'Manage data, records, and automate workflows' with concrete Airship operations, e.g. 'Send push notifications and in-app messages, manage audiences and campaigns, and automate engagement workflows in Airship.'

Expand trigger terms to include natural user phrases such as 'push notification', 'in-app message', 'mobile engagement', or 'Airship campaign' so the skill triggers when users describe Airship capabilities without naming the platform.

Make the 'when' clause less circular — instead of 'interact with Airship data', specify 'Use when the user wants to send Airship push notifications, query Airship records, or automate Airship workflows.'

DimensionReasoningScore

Specificity

The description names the domain ("Airship integration") but the actions — "Manage data, records, and automate workflows" — are generic with no concrete operations listed. It matches the anchor 'names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 concrete actions.

2 / 5

Completeness

Both 'what' ("Manage data, records, and automate workflows") and 'when' ("Use when the user wants to interact with Airship data") are explicitly present, satisfying the 'Use when...' requirement. It falls short of level 5 because the 'what' is vague rather than concrete, and the trigger is circular ('interact with Airship data') rather than listing concrete trigger phrases.

4 / 5

Trigger Term Quality

"Airship" and "Airship data" are relevant keywords a user would say, but common natural variations are missing entirely — no mention of push notifications, in-app messages, email campaigns, or engagement, which are the phrases Airship users actually use. This fits 'some relevant keywords but missing common variations or synonyms' rather than level 4, where only a few natural terms are missing.

3 / 5

Distinctiveness Conflict Risk

The named platform "Airship" gives it a clear niche with mostly distinct triggers, but the generic phrases "Manage data, records, and automate workflows" create minor overlap risk with generic data-management or workflow-automation skills when Airship is not explicitly named. This matches 'mostly distinct; minor overlap risk' rather than level 5's minimal conflict risk.

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/airship/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.