Name: truss
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

truss

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

Quality

65%

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/truss/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.

The body is a strong, actionable CLI guide with a genuine validation loop for connection readiness and clean sectioning. Its weaknesses are a padded intro explaining Truss, placeholder-laden examples, and a broken 'Step 2' reference that slightly muddies the workflow.

Suggestions

Trim the opening paragraph that defines what Truss is; Claude does not need the platform overview, and removing it would lift conciseness.

Resolve the dangling 'Step 2' reference by labeling the searching/running section as Step 2, or rephrase to 'skip to Searching for actions'.

Provide one fully-resolved example with a concrete action id and connection id so the actionability examples are copy-paste ready without placeholders.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands and examples, but the opening paragraph explaining what Truss is and asides like 'so you can focus on the integration logic rather than auth plumbing' are unnecessary explanation Claude does not need, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	Concrete, copy-paste-ready commands dominate (npm install, membrane login, connection ensure, action run) with a useful proxy flag table, but placeholders like CONNECTION_ID and <actionId> leave minor gaps versus the fully-specified common-cases anchor at 5.	4 / 5
Workflow Clarity	There is a clear install → authenticate → connect → poll-until-ready → search → run sequence with an explicit validation/feedback loop on connection state (READY/BUILDING/CLIENT_ACTION_REQUIRED), though the undefined 'Step 2' reference is a minor navigation gap keeping it below 5.	4 / 5
Progressive Disclosure	Content is well organized into clearly headed sections with no nested references and no bundle files that need splitting, but at ~140 lines it exceeds the under-50-line simple-skill threshold for a 5, so it sits at 'good structure, minor organization gaps'.	4 / 5
	Total	15 / 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 is concise and correctly pairs a 'what' with an explicit 'when' trigger, anchored on the distinct Truss product name. Its main weakness is generic action verbs and limited keyword variation, which cap specificity and trigger quality.

Suggestions

Replace generic verbs with concrete Truss actions (e.g., 'deploy and serve ML models, manage model versions and datasets') to lift specificity.

Add natural trigger synonyms users might say (e.g., 'Truss models', 'Truss deployment', 'Basetwo Truss') to broaden trigger term coverage.

Tighten the 'when' clause with concrete trigger phrases (e.g., 'Use when the user mentions Truss models, deployments, or model versions') to push completeness toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain (Truss) and a few actions ('Manage data, records, and automate workflows') but the verbs are generic and coverage is not comprehensive, matching the 'names domain and 1-2 concrete actions' anchor rather than the multi-action anchor at 4.	3 / 5
Completeness	Both 'what' (Truss integration, manage data/records, automate workflows) and an explicit 'when' ('Use when the user wants to interact with Truss data') are present, but the 'what' is somewhat generic so it stops short of the concrete-trigger anchor at 5.	4 / 5
Trigger Term Quality	Relevant keywords are present ('Truss', 'data', 'records', 'workflows', 'interact with Truss data') but common synonyms and variations are missing, fitting the 'some relevant keywords but missing common variations' anchor rather than the strong coverage at 4.	3 / 5
Distinctiveness Conflict Risk	The repeated 'Truss' naming gives a clear niche with minimal conflict risk, though the generic 'manage data, records, workflows' phrasing leaves minor overlap risk with adjacent data skills, so it does not reach the fully distinct anchor at 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/truss/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.