Name: mode
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

mode

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

Quality

62%

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/mode/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 well-structured, actionable CLI guide with a sensible connection-state workflow and feedback loops, weakened mainly by a padded intro, redundant action-list sections, and a broken 'Step 2' cross-reference.

Suggestions

Fix the 'skip to Step 2' reference by labeling the action-discovery section as Step 2, or reword to 'skip to Searching for actions'.

Merge 'Searching for actions' and 'Popular actions' into one section to remove the duplicated `action list --intent=QUERY` example.

Trim the opening paragraph that explains what Mode is; assume Claude's knowledge and keep only what is needed to orient the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command-driven prose, but the opening paragraph explaining what Mode is ('a data science platform that combines SQL querying...') and the redundant action-list examples in 'Searching for actions' and 'Popular actions' could be trimmed.	3 / 5
Actionability	Concrete, copy-paste-ready CLI commands cover install, auth, connection, action discovery, running, and proxying with flag tables, though examples rely on placeholders (CONNECTION_ID, actionId) and lack a fully-realized Mode-specific endpoint call.	4 / 5
Workflow Clarity	There is a clear install -> authenticate -> connect -> poll-for-ready -> search -> run/proxy sequence with state-based checkpoints (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and a re-poll feedback loop, but the 'skip to Step 2' reference points to no labeled Step 2.	4 / 5
Progressive Disclosure	Content is organized into well-labeled sections with no nested external references (no bundle files exist and none are needed), but the action-discovery material is split across two overlapping sections and inline proxy-flag detail could be tighter.	4 / 5
	Total	15 / 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 correctly includes an explicit 'Use when' trigger and names the Mode platform, but it is thin on concrete capabilities and misleads scope by emphasizing 'Manage Organizations' over the report/query/collection features the body actually exposes.

Suggestions

Replace the generic 'Manage Organizations' with the concrete capabilities the skill exposes, e.g. 'Run Mode reports and queries, manage Collections and Spaces, and list users.'

Broaden the trigger phrase to natural terms users say: 'Use when the user wants to run or schedule Mode reports, query Mode data, or manage Mode collections, spaces, and users.'

Drop the bare 'Mode integration.' opener or fold it into the action list so every token earns its place.

Dimension	Reasoning	Score
Specificity	The description names the Mode domain and a single concrete action ('Manage Organizations') plus the generic phrase 'interact with Mode data', leaving the actual capabilities (reports, queries, collections, spaces) unstated.	2 / 5
Completeness	Both a 'what' (Mode integration, Manage Organizations) and an explicit 'when' ('Use when the user wants to interact with Mode data') are present, though the 'when' could name concrete triggers and the 'what' is thin.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with Mode data' surfaces the natural keyword 'Mode'/'Mode data', but omits common synonyms users would say like reports, queries, SQL, dashboards, or charts.	3 / 5
Distinctiveness Conflict Risk	'Mode' names a specific BI platform giving it a clear niche with minimal conflict risk, though the generic 'interact with Mode data' leaves minor overlap with adjacent data/BI skills.	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/mode/SKILL.md
Commit: f484c82

Reviewed: 5 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.