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

Blog Docs Log in Get started

median

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/median/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 content is a well-structured, largely executable guide to driving Median via the Membrane CLI, with a clear workflow and real polling-based feedback loops. Its main weaknesses are filler at the top, a duplicated/thin 'Popular actions' section, and an entity overview that does not connect to actionable steps.

Suggestions

Remove the placeholder opener ('I don't have enough information to describe this app...') and the vague 'Use action names and parameters as needed.' line; they add tokens without guidance.

Merge 'Popular actions' into 'Searching for actions' to eliminate the duplicated discovery command, or populate it with named example actions tied to the entities in the overview.

Connect the Median Overview entity list (Company, Metric, User, Alert) to concrete example intents or action names so the overview is actionable rather than a bare taxonomy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands, but it opens with filler ('I don't have enough information to describe this app...'), includes a vague directive ('Use action names and parameters as needed.'), and repeats action-discovery guidance in 'Popular actions', fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection ensure, action list/run, and proxy requests with concrete flags, matching 'mostly executable guidance with minor gaps'; the thin 'Popular actions' section and unsubstituted placeholders keep it below 5.	4 / 5
Workflow Clarity	The install → authenticate → connect → search → run → proxy sequence is clear and includes a genuine feedback loop via connection-state polling (READY/BUILDING/CLIENT_ACTION_REQUIRED with 'poll again' instructions), matching 'clear sequence with most checkpoints present'; it is not a 5 because some recovery paths (action-run errors) are left implicit.	4 / 5
Progressive Disclosure	As a single-file skill with no bundle directories, it is well organized into clearly labeled sections; the dense clientAction state breakdown and proxy-flag table could plausibly live in a reference file, so it sits at 'good structure, minor organization gaps' rather than 5.	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 successfully pairs a 'what' with an explicit 'Use when...' trigger and names a distinct app, but its capability verbs are generic and its keyword coverage is thin. Tightening the actions to concrete operations and adding natural trigger variations would raise specificity and trigger_term_quality.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Median operations such as 'pull metric snapshots', 'manage users', or 'configure alerts'.

Expand trigger terms with natural variations users might say, e.g. 'Use when the user wants to query Median metrics, manage records, or automate Median workflows.'

Add a couple of file-format or entity keywords (e.g. 'Metric Snapshot', 'Metric Board', 'alerts') to improve distinctiveness and keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the Median domain but its actions ('Manage data, records, and automate workflows') are generic verbs rather than concrete operations, matching the 'names the domain but actions are minimal or generic' anchor rather than the concrete-action anchor above.	2 / 5
Completeness	It states both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Median data'), matching the anchor where both are present but the 'what' could be more concrete; it does not reach 5 because the actions and trigger phrases are not comprehensive.	4 / 5
Trigger Term Quality	Phrases like 'Median integration', 'Median data', and 'interact with Median data' provide some relevant keywords but lack common variations or synonyms, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Naming the specific Median app gives a mostly distinct niche with minimal conflict risk, but the generic 'manage data, records, automate workflows' framing creates minor overlap with other data-management skills, so it sits at 4 rather than 5.	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/median/SKILL.md
Commit: f484c82

Reviewed: 6 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.