Name: bridge
Rating: 52 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

bridge

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

Quality

57%

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/bridge/SKILL.md

Quality

Content

57%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 reasonably actionable CLI guide with concrete commands and a well-sequenced connection flow. Its weaknesses are padded/redundant prose, a lack of validation/verification steps around action execution (capping workflow clarity), and loose cross-reference labeling that hurts navigation.

Suggestions

Add a validation/verification step to the action-running workflow (e.g. inspect the response 'output' field and confirm expected fields before reporting success), to lift workflow clarity above the destructive/batch cap.

Fix the dangling references: either label 'Step 1'/'Step 2' explicitly or remove 'skip to Step 2' and the orphaned '1b' heading.

Trim fluff such as 'so you can focus on the integration logic rather than auth plumbing' and deduplicate the pre-built-actions/auth/pagination point made in both 'Best practices' bullets.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with copy-paste command blocks, but includes padded phrasing like 'so you can focus on the integration logic rather than auth plumbing' and repeats the pre-built-actions/auth/pagination point across the 'Best practices' section, fitting the mostly-efficient-but-could-be-tightened anchor.	3 / 5
Actionability	It provides concrete executable commands with real flags (e.g. 'membrane action run <actionId> --connectionId=CONNECTION_ID --input ... --json' and the proxy flag table), with only minor placeholders like CONNECTION_ID and QUERY, matching the mostly-executable-with-minor-gaps anchor rather than fully copy-paste-ready 5.	4 / 5
Workflow Clarity	The connection workflow is well-sequenced with polling and state checkpoints (READY / CLIENT_ACTION_REQUIRED / poll again), but running actions and proxy requests on external data has no validation or verification of results, so the destructive/batch cap holds it at 3 rather than 4.	3 / 5
Progressive Disclosure	It is a single well-sectioned file with no bundle references (none exist), but navigation is undermined by dangling labels ('skip to Step 2' with no Step 2, a '1b' with no 1a/2) and an undifferentiated 18-item entity bullet list, fitting the some-structure-but-could-be-better-organized anchor.	3 / 5
	Total	13 / 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' clause and names a specific product, giving it reasonable completeness and distinctiveness. Its main weakness is specificity: the listed actions are generic verbs rather than concrete operations, and trigger-term coverage lacks synonyms.

Suggestions

Replace generic verbs with concrete actions, e.g. 'List meetings, manage transcriptions, search records, and run action items' instead of 'Manage data, records, and automate workflows'.

Add natural trigger terms and synonyms users would actually say, e.g. 'Use when the user mentions Bridge meetings, transcriptions, summaries, or wants to query Bridge records.'

Tie the 'when' clause to the concrete Bridge objects (meetings, transcriptions, action items) surfaced in the skill body to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Bridge integration') but the actions 'Manage data, records, and automate workflows' are generic verbs with no concrete operations, matching the anchor for minimal/generic actions rather than the 1-2 concrete actions of a 3.	2 / 5
Completeness	It explicitly answers both 'what' ('Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with Bridge data'), with the 'when' present but somewhat generic, matching the both-present-but-could-be-more-specific anchor rather than the 3 (which requires a missing/weak 'when').	4 / 5
Trigger Term Quality	It includes a relevant keyword/phrase ('interact with Bridge data', 'Bridge') but offers no synonyms or common variations users might say, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The named product 'Bridge' and 'interact with Bridge data' trigger give it a clear niche with minimal conflict risk, but the generic 'Manage data, records' phrasing leaves minor overlap risk with other data-management skills, fitting the mostly-distinct anchor.	4 / 5
	Total	13 / 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/bridge/SKILL.md
Commit: f484c82

Reviewed: 3 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.