Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

bigml

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

Quality

76%

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/bigml/SKILL.md

Quality

Content

82%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 strong, action-dense guide: every workflow phase ships executable CLI commands, and connection-state handling includes genuine validation and retry loops. The main defects are a dangling "Step 2" reference (numbered headings don't exist), light padding in the intro/overview, and the popular-actions table being inline reference material in an otherwise bundle-free skill.

Suggestions

Fix the dangling "skip to **Step 2**" references by numbering the workflow sections explicitly (1. Connect, 2. Search actions, 3. Run) so the navigation targets exist.

Trim the introductory paragraph and the bare resource-name bullet list ("**Dataset**... Use action names and parameters as needed.") — they restate what BigML is without adding actionable guidance.

Move the 20-row Popular actions table to a references/ file (e.g. references/actions.md) and keep a handful of representative examples inline, keeping the main file lean.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands and tables with little padding, but the opening "BigML is a Machine Learning platform as a service. It provides a cloud-based infrastructure..." paragraph and the bare resource-name bullet list ("Dataset... Use action names and parameters as needed.") could be trimmed, matching anchor 4 rather than the fully lean level 5.	4 / 5
Actionability	Every phase has copy-paste-ready commands: "npm install -g @membranehq/cli@latest", "membrane connection ensure \"https://bigml.com/\" --json", "membrane action run <actionId> ... --input '{\"key\": \"value\"}'", and a proxy flag table, covering the common cases comprehensively.	5 / 5
Workflow Clarity	The install → login → connect → poll → search → run sequence is clear with strong feedback loops (CLIENT_ACTION_REQUIRED handling, re-polling until READY, error-state guidance), but the body tells the reader to "skip to Step 2" twice while no Step 1/Step 2 headings exist — only "1b" is numbered — a minor coherence gap that keeps it below level 5.	4 / 5
Progressive Disclosure	With no bundle files present, the single-file body is well-organized with clear section headers, and the 20-row Popular actions table is the only bulk reference material that arguably belongs in a separate references file — a minor organization gap matching anchor 4.	4 / 5
	Total	17 / 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 is distinct and has an explicit use-when clause, but the capability statement is generic — "manage data, records, and automate workflows" could describe almost any data platform, and users would benefit from concrete BigML vocabulary (datasets, models, predictions, evaluations). It reads as a template-generated description with minimal platform-specific tailoring.

Suggestions

Replace the generic "Manage data, records, and automate workflows" with concrete BigML capabilities, e.g. "Create datasets and models, run predictions, evaluate ensembles, and manage BigML ML resources."

Broaden trigger terms to include natural variations users would say: machine learning, ML models, training datasets, predictions, anomaly detection.

Tighten the when-clause to name concrete scenarios, e.g. "Use when the user mentions BigML, or wants to create/train/deploy machine learning models in the cloud."

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the domain but the actions are generic ("manage", "automate workflows") with no concrete capabilities like listing datasets or training models, matching the anchor for domain named with minimal/generic actions rather than the concrete 1-2 actions of level 3.	2 / 5
Completeness	It has both a what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with BigML data"), but the when is a single phrase without concrete trigger variations, matching level 4 rather than the comprehensive triggers of level 5.	4 / 5
Trigger Term Quality	"BigML" is the key natural term, but common variations users would say — machine learning, ML, datasets, models, predictions — are absent, matching "some relevant keywords but missing common variations or synonyms".	3 / 5
Distinctiveness Conflict Risk	The description is anchored entirely to a named niche platform ("BigML integration"... "interact with BigML data") with distinct triggers, so it is clearly distinguishable from other skills and unlikely to fire for the wrong one.	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/bigml/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.

bigml

Table of Contents

Is this your skill?