Tessl • The management layer for AI agent skills

SkillPublic

cnvrgio

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

Quality

70%

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/cnvrgio/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 delivers strong executable guidance with a well-handled connection state machine and a sensible proxy fallback. Its main weaknesses are redundancy (repeated action-list command, vague intro) and broken internal cross-references that slightly undermine navigation.

Suggestions

Fix internal navigation: define the "Step 2" section the text points to (or drop the reference) and renumber the "1b" heading into a coherent step sequence.

Trim the intro paragraph explaining what Cnvrg.io is and the filler line "Use action names and parameters as needed", and merge the duplicated `action list` discovery command from "Popular actions" into "Searching for actions".

Either populate "Popular actions" with a few named common actions (e.g. running an experiment, deploying an endpoint) or remove the section so readers aren't directed to an empty list.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and command-first, but includes unnecessary padding: an intro paragraph explaining what Cnvrg.io is, a duplicated action-discovery command ("Popular actions" repeats "Searching for actions"), and filler like "Use action names and parameters as needed.".	3 / 5
Actionability	Commands are concrete and copy-paste ready (install, login, connection ensure, polling, action run with --input, proxy flags), but there are minor gaps: "skip to Step 2" references a heading that doesn't exist, and the "Popular actions" section lists no actual actions.	4 / 5
Workflow Clarity	The install → authenticate → connect → poll → search → run → proxy sequence is clear and includes a real feedback loop (state-machine polling, CLIENT_ACTION_REQUIRED handling, re-poll after user action), but the broken "Step 2" cross-reference and orphan "1b" numbering leave minor sequence gaps.	4 / 5
Progressive Disclosure	The single file is well-sectioned with clear headers and appropriate inline content, but the effectively empty "Popular actions" section and the duplicated discovery command leave minor organization gaps for a ~150-line skill.	4 / 5
	Total	15 / 20 Passed

Description

61%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 a distinctive platform anchor, but the capability statement is generic. Naming the actual Cnvrg.io objects and operations (experiments, datasets, deployments) would sharpen both specificity and trigger coverage.

Suggestions

Replace the generic "Manage data, records, and automate workflows" with concrete Cnvrg.io operations, e.g. "Run experiments, manage datasets and models, deploy endpoints, and automate ML pipelines in Cnvrg.io".

Broaden the trigger clause beyond "interact with Cnvrg.io data" to include natural phrasings users would say, such as "Use when the user mentions Cnvrg.io, wants to run ML experiments, manage datasets, or deploy models".

Mirror the platform vocabulary from the body's Overview (Project, Experiment, Flow, Dataset, Deployment, Endpoint) so the description triggers on those terms.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Cnvrg.io integration") but the actions are generic — "Manage data, records, and automate workflows" could describe almost any integration, with no Cnvrg-specific verbs like "run experiments", "deploy models", or "manage datasets".	2 / 5
Completeness	Both a "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Cnvrg.io data") are present; the "when" is somewhat narrow (only "data") and the "what" is vague, so it falls short of the anchor-5 example.	4 / 5
Trigger Term Quality	"Cnvrg.io" is a strong natural trigger term, but common user phrasings for this platform (experiments, datasets, MLOps, deploy models, clusters) are missing, leaving keyword coverage partial.	3 / 5
Distinctiveness Conflict Risk	"Cnvrg.io" names a clear niche and both the trigger and scope are tied explicitly to it, giving minimal overlap risk with other skills.	5 / 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/cnvrgio/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.

cnvrgio

Table of Contents

Is this your skill?