Name: mend
Rating: 48.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

mend

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

Quality

53%

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/mend/SKILL.md

Quality

Content

56%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 CLI guidance with a well-sequenced, state-aware connection workflow, but it is weighed down by a large redundant entity enumeration that should live in a separate reference file. Operational sections are the strength; the overview list is the main token sink.

Suggestions

Move the 70+ line entity/Risk Report enumeration out of SKILL.md into a separate reference file (e.g. references/entities.md) and link to it, keeping the overview lean.

Trim the redundant "X Risk Report" bullet variants, which roughly double the list length without adding actionable guidance.

Populate the "Popular actions" section with concrete Mend action IDs and examples instead of restating the discovery command.

Dimension	Reasoning	Score
Conciseness	The ~74-line "Mend Overview" entity list — including a redundant "X Risk Report" variant for nearly every entity — is heavily padded, and the intro paragraph restates what Mend is. It matches anchor 2 ("noticeably verbose; several padded sections") rather than 3 because the padding is more than "some," though the operational CLI sections are leaner, keeping it above 1.	2 / 5
Actionability	Concrete, copy-paste-ready bash commands cover install, auth, connect, search, run, and proxy, plus a flag table. It fits anchor 4 ("mostly executable guidance; concrete code or commands with minor gaps") rather than 5 because examples use abstract placeholders (QUERY, CONNECTION_ID, <actionId>) and "Popular actions" restates the discovery command instead of listing real Mend actions.	4 / 5
Workflow Clarity	There is a clear sequence (install -> auth -> connect -> search -> run) with state-based validation and a feedback loop in the connection phase (poll until READY, handle CLIENT_ACTION_REQUIRED, then re-poll). It is anchor 4 ("clear sequence with most checkpoints present; minor validation gaps") rather than 5 because there are no validation checkpoints after running actions or issuing proxy requests.	4 / 5
Progressive Disclosure	Clear section headers and logical flow exist, but at ~210 lines the 74-line reference-style entity enumeration is inlined and there are no external reference files at all. This matches anchor 3 ("content that should be separate is inline") rather than 4 (which would require references) and rather than 2 (which would need minimal structure).	3 / 5
	Total	13 / 20 Passed

Description

50%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 because it names the Mend product and includes an explicit "Use when" clause, but its capability language is generic and it omits the concrete Mend concepts (vulnerabilities, dependencies, licenses, SCA) users would actually mention. It is adequate but padded with abstract verbs that could apply to almost any integration.

Suggestions

Replace the generic actions ("Manage data, records, and automate workflows") with concrete Mend capabilities, e.g. "scan open-source dependencies for vulnerabilities, check license compliance, and prioritize remediation."

Add natural trigger terms users would actually say, e.g. "Use when the user wants to scan dependencies, check CVEs/vulnerabilities, review open-source licenses, or manage Mend findings."

Dimension	Reasoning	Score
Specificity	The description names actions ("Manage data, records, and automate workflows") but they are generic abstractions rather than concrete Mend capabilities like vulnerability scanning, dependency analysis, or license compliance. It sits at anchor 2 ("actions are minimal or generic") rather than 3 because no Mend-specific concrete action is given.	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 Mend data"), and the "Use when" clause is present so it is not capped at 3. It is not 5 because the "what" is vague and the "when" lacks concrete trigger phrases.	4 / 5
Trigger Term Quality	Only "Mend" is a genuinely natural trigger; "data", "records", and "workflows" are generic, and the phrases users actually say (scan dependencies, CVEs, open-source licenses, SCA) are absent. This matches anchor 2 ("one or two generic keywords; missing the natural phrases users say") rather than 3 because common synonyms and variations are missing.	2 / 5
Distinctiveness Conflict Risk	Scoping to the "Mend" brand gives a clear niche with low conflict risk, but the generic action language ("Manage data, records, and automate workflows") creates minor overlap with other data-integration skills. It fits anchor 4 ("mostly distinct; minor overlap risk") rather than 5 due to that generic phrasing.	4 / 5
	Total	12 / 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/mend/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.