CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autobound

Autobound integration. Manage data, records, and automate workflows. Use when the user wants to interact with Autobound 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/autobound/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 body is a lean, command-first integration guide with a clear setup sequence and genuinely useful state-handling guidance. Its main flaws are cosmetic-but-real: an empty Description column in the actions table, a dangling 'Step 2' reference, and a stub overview section.

Suggestions

Fill in the Description column of the 'Popular actions' table (or drop the table in favor of `membrane action list --intent` guidance) so the reader knows what each action does.

Fix the broken navigation: the text says 'skip to **Step 2**' and uses '#### 1b' numbering, but no 'Step 1'/'Step 2' headings exist — either add numbered step headings or reword to plain section names.

Either describe the data-model entities (Account, Contact, Sequence, Steps, Task) in one line each or remove the empty 'Autobound Overview' bullet stubs.

DimensionReasoningScore

Conciseness

The body is command-driven with little explanation of concepts Claude already knows, e.g. install ("npm install -g @membranehq/cli@latest"), auth, and proxy usage are all given as bare commands. Minor trimmable padding exists — the stub data-model bullets under 'Autobound Overview' ('**Account** / **Contacts**' with no descriptions) and the filler line 'Use action names and parameters as needed' — which keeps it below a 5.

4 / 5

Actionability

Guidance is mostly executable: concrete commands for login, connection ensure with a real URL, action list/run with JSON input examples, and a proxy flags table. The main gap is the 'Popular actions' table having an entirely empty Description column, so the reader cannot tell what each action does without running a search; that incompleteness prevents a 5.

4 / 5

Workflow Clarity

The setup flow is clearly sequenced (install → login → connection ensure → poll state → search → run) with state-based checkpoints and recovery guidance for 'CLIENT_ACTION_REQUIRED' and error states. Minor gaps: 'skip to **Step 2**' references a heading that does not exist, and the '#### 1b' numbering implies a step structure that was never defined — noticeable but not disqualifying, so a 4 rather than 5.

4 / 5

Progressive Disclosure

The ~150-line body is a single well-sectioned file (Install, Authentication, Connecting, Searching, Popular actions, Running, Proxy, Best practices) with no bundle files and no buried references. Structure is good and content is mostly appropriately placed for an overview of this size; it is not a 5 because the connection-state handling and proxy options could arguably live in a separate reference file, and the sparse Overview bullets add little navigational value.

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 the right structural shape — domain plus an explicit 'Use when' clause — but its capability statement is generic filler. Replacing 'Manage data, records, and automate workflows' with Autobound's concrete capabilities would raise specificity and trigger quality substantially.

Suggestions

Replace the generic 'Manage data, records, and automate workflows' with concrete capabilities the skill actually supports, e.g. 'Generate personalized email openers, sequences, insights, SMS messages, and call scripts; manage contacts and sequences'.

Add natural trigger terms users would actually say, such as 'sales outreach', 'personalized emails', 'email sequences', 'prospecting', or 'sales engagement', alongside the brand name.

Make the 'when' clause task-specific rather than tautological, e.g. 'Use when the user wants to generate or automate personalized sales outreach in Autobound' instead of 'interact with Autobound data'.

DimensionReasoningScore

Specificity

The description names the domain ("Autobound integration") but its actions — "Manage data, records, and automate workflows" — are generic with no concrete capabilities (no mention of email openers, sequences, insights, or contacts). This matches the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because no specific action like 'generate personalized emails' is stated.

2 / 5

Completeness

Both clauses are explicitly present: 'what' ("Autobound integration. Manage data, records, and automate workflows") and 'when' ("Use when the user wants to interact with Autobound data"). The 'when' could be more specific and the 'what' is vague, fitting anchor 4 rather than 5; it is not a 3 because the 'when' clause is explicit, not merely implied.

4 / 5

Trigger Term Quality

The only substantive natural keyword is "Autobound" (appearing twice); "data", "records", and "workflows" are generic and users seeking sales outreach help would not say them. Common variations like 'sales outreach', 'email personalization', 'prospecting', or 'sequences' are missing, matching 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The brand name "Autobound" in both the what and when clauses makes this skill mostly distinct with minimal conflict risk against other app-integration skills. It is not a 5 because the generic phrases "Manage data, records, and automate workflows" could overlap with other data-management or workflow-automation 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/autobound/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.