Tessl • The management layer for AI agent skills

SkillPublic

authbridge

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/authbridge/SKILL.md

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.

A reasonably strong CLI-integration skill: nearly all guidance is executable commands with a clear connection-state feedback loop. Its main weaknesses are a content-free overview section, a 'Popular actions' section that promises but never lists actions, and broken internal step references.

Suggestions

Delete or populate the 'Authbridge Overview' filler section — a bare bullet tree ('Identity / Verification / Template / Field' plus 'Use action names and parameters as needed.') spends tokens without guidance.

Fix the step navigation: 'skip to Step 2' references a step that is never labeled, and '1b' appears without a 'Step 1'; either number the workflow consistently or drop the numbers.

Either list actual popular Authbridge actions (e.g. identity verification, background check) in that section or remove the heading, since it currently only repeats the action-list command.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean CLI commands, but the 'Authbridge Overview' section is pure filler ('Identity / Verification / Template / Field' with no content, 'Use action names and parameters as needed.'), plus marketing padding like 'so you can focus on the integration logic rather than auth plumbing' and duplicated action-list instructions.	3 / 5
Actionability	Concrete, copy-paste-ready commands with placeholders appear throughout (install, login, connection ensure, polling, action run, proxy flags table), but there are minor gaps: 'skip to Step 2' points at a step that is never labeled, and the 'Popular actions' section lists no actual actions.	4 / 5
Workflow Clarity	The install → login → connection ensure → poll until READY → search actions → run → proxy fallback sequence is clear, with state-based checkpoints (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and re-poll instructions. However, the step numbering is broken — a '1b' subsection with no 'Step 1' or 'Step 2' heading makes the referenced navigation confusing.	4 / 5
Progressive Disclosure	No bundle files exist, and the ~140-line body uses well-organized section headers with content appropriately kept in a single file for a CLI-wrapper skill. Minor gaps: the empty overview and 'Popular actions' sections add navigation noise without content.	4 / 5
	Total	15 / 20 Passed

Description

37%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 names the product but fails to convey what Authbridge actually does (identity verification, background screening, KYC) or when a user would need it beyond naming the brand. Its trigger clause is circular and its capability language is generic SaaS filler.

Suggestions

State the actual capabilities concretely, e.g. 'Verify identities, run background checks, and retrieve KYC screening results through the Authbridge API' instead of 'Manage data, records, and automate workflows'.

Add natural trigger terms users would say — 'identity verification', 'background check', 'KYC', 'candidate screening' — rather than only the brand name.

Make the 'Use when...' clause non-circular, e.g. 'Use when the user mentions Authbridge or asks to verify someone's identity or run a background check'.

Dimension	Reasoning	Score
Specificity	'Manage data, records, and automate workflows' names the domain (Authbridge) but the actions are entirely generic — no concrete capability like identity verification, background checks, or KYC is stated. This matches anchor 2, not 3, which requires 1-2 concrete actions.	2 / 5
Completeness	A 'Use when...' clause is present ('Use when the user wants to interact with Authbridge data') but it is circular — it restates the product name rather than giving a trigger — and the 'what' ('Manage data, records, and automate workflows') is vague. It falls between anchors 3 and 4, below the midpoint, because neither half carries concrete information.	3 / 5
Trigger Term Quality	The only substantive keyword is the brand name 'Authbridge'; the natural phrases a user would actually say ('identity verification', 'background check', 'KYC', 'screening') are entirely missing, leaving one or two generic terms ('data', 'records').	2 / 5
Distinctiveness Conflict Risk	The brand name 'Authbridge' anchors it to a niche, but the generic action language ('manage data, records, and automate workflows') would overlap with virtually any data or integration skill, so it is only somewhat specific.	3 / 5
	Total	10 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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/authbridge/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

Discovery Implementation Validation

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.

authbridge

Table of Contents

Is this your skill?