Name: cobalt
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

cobalt

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

Quality

69%

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/cobalt/SKILL.md

Quality

Content

72%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 highly actionable with executable commands and good connection-state feedback loops, but it lacks validation guidance for its destructive operations and keeps all reference material inline with no external files. The introductory Cobalt summary also contradicts the actual actions (customer-support framing vs. findings/pentests/assets).

Suggestions

Add a verify-before-destructive step, e.g. run get/list actions to confirm the target before delete-asset or a DELETE proxy request, to lift the workflow clarity cap.

Move the Popular actions table and proxy flags table into a separate references file (e.g. ACTIONS.md) referenced one level deep from SKILL.md.

Fix or remove the misleading intro paragraph: the skill's actions are about findings, pentests, and assets, not customer-support tickets.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean commands and tables, with only minor over-explanation such as the introductory Cobalt paragraph and phrases like 'so you can focus on the integration logic rather than auth plumbing', matching 'efficient; minor instances of over-explanation that could be trimmed'.	4 / 5
Actionability	It provides copy-paste-ready commands for every common case (install, login, connection ensure, action list/run, request proxy) plus a concrete actions table and a proxy flags table, matching 'fully executable; copy-paste ready; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The connection flow has explicit state checkpoints and feedback loops (poll until READY, handle CLIENT_ACTION_REQUIRED then re-poll), but the skill exposes destructive operations (delete-asset, DELETE via proxy) with no verify-before-delete guidance, so the destructive-operations cap of 3 applies.	3 / 5
Progressive Disclosure	Sections are clearly organized, but at ~155 lines everything is inline with no one-level-deep reference files, and the Popular actions / proxy flags reference tables are inlined rather than split out, fitting 'some structure but content that should be separate is inline'.	3 / 5
	Total	15 / 20 Passed

Description

66%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 app-specific and includes both a capability statement and a 'Use when' trigger, but its action verbs are generic and its trigger phrasing is narrow. It is clearly distinct but could be more concrete about Cobalt's actual capabilities (findings, pentests, assets).

Suggestions

Replace generic verbs ('Manage data, records, automate workflows') with concrete Cobalt capabilities such as 'list and update findings, browse pentests, and manage assets'.

Broaden the trigger clause to mirror natural user requests, e.g. 'Use when the user wants to query Cobalt findings, pentests, assets, or organizations.'

Mention the concrete entities (findings, pentests, assets, organizations) so the trigger terms match what users will actually say.

Dimension	Reasoning	Score
Specificity	The phrase 'Manage data, records, and automate workflows' names the Cobalt domain plus a few actions, but the verbs are generic ('manage', 'automate') rather than concrete capabilities, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	It states both a 'what' ('Manage data, records, and automate workflows') and a 'when' ('Use when the user wants to interact with Cobalt data'), but the 'when' could be more explicit/specific, matching the 'has both what and when; when could be more explicit' anchor rather than the concrete-trigger anchor of 5.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with Cobalt data' offers a trigger around 'Cobalt data', but natural user phrasings (e.g. 'list findings', 'look up assets in Cobalt') and synonyms are absent, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Tying triggers explicitly to the named 'Cobalt' SaaS app gives it a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 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/cobalt/SKILL.md
Commit: f484c82

Reviewed: ~12 hours 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.