CtrlK
BlogDocsLog inGet started
Tessl Logo

google-recaptcha

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

55

Quality

62%

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/google-recaptcha/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 content is a well-structured, mostly executable guide to the Membrane CLI workflow for reCAPTCHA, with a genuine state-based feedback loop for connection readiness. Its main weakness is a padded conceptual intro and minor numbering inconsistencies in the workflow steps.

Suggestions

Cut the opening paragraph explaining what reCAPTCHA is and why web developers use it; Claude already knows this and it consumes context without adding actionability.

Fix the step numbering: add a matching "Step 2" header (or relabel) and pair "1b" with an explicit "1a" so the cross-references resolve.

Add a short validation note after `membrane action run` showing how to confirm success from the `output` field for batch/multiple-action cases.

DimensionReasoningScore

Conciseness

The body is mostly efficient concrete commands, but the opening paragraph explains what reCAPTCHA is (which Claude already knows) and a few padded sentences add no actionable value.

3 / 5

Actionability

Copy-paste-ready commands cover install, login, connection setup, action discovery, action runs, and proxy requests with a clear flags table; only obvious placeholders need substitution.

4 / 5

Workflow Clarity

A clear install→auth→connect→search→run sequence is present with a state-machine feedback loop (BUILDING/READY/CLIENT_ACTION_REQUIRED with --wait polling), though "Step 2" is referenced without a matching header and "1b" has no "1a".

4 / 5

Progressive Disclosure

No bundle files exist, but the single-file body is well sectioned with headers, a flags table, and code blocks at one level of depth, giving easy navigation despite being over 50 lines.

4 / 5

Total

15

/

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 correctly names a distinct domain and includes an explicit Use-when trigger, but it leans on generic Membrane boilerplate ("Manage data, records, and automate workflows") rather than reCAPTCHA-specific capabilities. Trigger phrasing is functional but circular and lacks natural synonyms.

Suggestions

Replace the generic actions with reCAPTCHA-specific verbs, e.g. "Verify reCAPTCHA tokens, create score-based assessments, and inspect site keys" to lift specificity.

Rewrite the trigger to mention natural user phrases: "Use when the user wants to add reCAPTCHA to a site, verify a reCAPTCHA token, or check a bot-detection score."

Drop the filler clause "Manage data, records, and automate workflows" since it does not describe anything specific to reCAPTCHA.

DimensionReasoningScore

Specificity

The domain is named ("Google reCAPTCHA integration") but the only actions are generic boilerplate ("Manage data, records, and automate workflows") with no reCAPTCHA-specific concrete actions such as verifying tokens or creating assessments.

2 / 5

Completeness

Both a "what" (integration plus actions) and an explicit "Use when..." trigger are present, but the "when" clause is circular and could be more specific.

4 / 5

Trigger Term Quality

The natural term "reCAPTCHA" is present, but "interact with Google reCAPTCHA data" is an awkward trigger and common synonyms (bot detection, verify token, site key) are missing.

3 / 5

Distinctiveness Conflict Risk

"Google reCAPTCHA" is a clear, distinct niche with low conflict risk, though the boilerplate action phrasing overlaps with sibling Membrane integration 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.

Validation15 / 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
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.