Name: lighthouse
Rating: 60.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

lighthouse

Lighthouse integration. Manage Organizations. Use when the user wants to interact with Lighthouse data.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

81%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 highly actionable with executable commands and an excellent state-polling workflow including error handling and feedback loops. Its main weakness is token efficiency: an unnecessary intro paragraph and a large inline action catalog that could be externalized.

Suggestions

Cut or shorten the introductory paragraph explaining what Lighthouse is, since Claude already knows this; lead directly with how to use the integration.

Move the full popular-actions table and the proxy flag reference into a separate reference file (e.g. references/actions.md) and keep only a few representative examples inline.

The 'Step 2' referenced in the READY branch is never labeled as a numbered section; label the workflow steps explicitly so 'skip to Step 2' resolves.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable commands, but the introductory paragraph ('Lighthouse is a website auditing tool used to improve the quality of web pages...') and the large inline 20-row popular-actions catalog add tokens that could be trimmed or moved to a reference file, matching 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	Commands are concrete and copy-paste ready throughout (install, login, connection ensure, polling, action list/run with JSON input, request proxy with flag table) and cover the common cases, matching 'fully executable; copy-paste ready; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The connection workflow has a clear state-based sequence with explicit checkpoints ('state: READY', 'CLIENT_ACTION_REQUIRED', 'CONFIGURATION_ERROR/SETUP_FAILED') and a feedback loop (poll -> act -> poll again), matching 'clear sequence with explicit validation steps; feedback loops for error recovery'; validation is present so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	The content is organized into clear, well-labeled sections with no nested references, but the full action catalog and proxy flag table are inlined as reference material that could be split into a separate file, matching 'good structure; most content appropriately placed; minor organization gaps'.	4 / 5
	Total	17 / 20 Passed

Description

62%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 includes both a 'what' and a 'when' clause anchored to a specific named product, which is solid but not exceptional. Its weaknesses are generic action wording ('Manage Organizations', 'integration') and a thin set of trigger terms beyond the product name.

Suggestions

Replace the generic 'Lighthouse integration' and 'Manage Organizations' with concrete action verbs that Lighthouse supports (e.g., 'Manage Lighthouse projects, tickets, milestones, and messages').

Expand the 'Use when' trigger with concrete natural phrases users would say (e.g., 'when the user mentions Lighthouse tickets, projects, or milestone tracking').

Add domain synonyms and entity keywords (tickets, discussions, to-dos) so the description matches how users actually refer to Lighthouse data.

Dimension	Reasoning	Score
Specificity	It names the domain (Lighthouse) and one concrete action ('Manage Organizations'), matching the '1-2 concrete actions but not comprehensive' anchor; 'integration' is generic and only one action verb is given, so it does not reach 'several specific actions' (4).	3 / 5
Completeness	Both 'what' ('Lighthouse integration. Manage Organizations.') and an explicit 'when' ('Use when the user wants to interact with Lighthouse data.') are present, but the when-clause is generic rather than listing concrete trigger phrases, keeping it at 4 instead of 5.	4 / 5
Trigger Term Quality	'Lighthouse' and 'interact with Lighthouse data' provide some relevant keywords, but beyond the product name there are no synonyms or common variations, so coverage is partial rather than good (4) or comprehensive (5).	3 / 5
Distinctiveness Conflict Risk	The named product 'Lighthouse' gives it a clear, mostly-distinct niche with minimal conflict risk, but the surrounding language ('integration', 'interact with data') is generic enough to risk minor overlap, placing it at 4 rather than a fully distinct 5.	4 / 5
	Total	14 / 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/lighthouse/SKILL.md
Commit: f484c82

Reviewed: 6 days ago

Table of Contents

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.