cx-observability-setup
Use this skill when the user asks to "set up monitoring", "configure observability", "onboard new service", "create saved view", "set up notifications", "configure webhook", "set up Slack integration", "outgoing webhook", "automation action", "webhook for alerts", "create view", "saved view", "view folder", "organize dashboards", "install integration", "configure extension", "contextual data", "connect external service", "create notification connector", "set up email alerts", "configure PagerDuty", "notification routing", "deploy extension", "test webhook", "notification preset", "test notification", "webhook actions", or wants to set up, configure, or manage the observability stack for a service or team.
52
57%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/cx-observability-setup/SKILL.mdQuality
Discovery
64%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 essentially a long list of trigger phrases wrapped in a 'Use this skill when...' clause. While it excels at providing natural keywords users might say, it completely lacks a 'what does this do' statement describing the skill's concrete capabilities. The extremely broad scope covering monitoring, webhooks, notifications, integrations, views, and dashboards risks overlap with more specialized skills.
Suggestions
Add a clear opening statement describing what the skill does before the trigger terms, e.g., 'Configures observability tooling including monitoring setup, saved views, notification connectors, webhooks, and integrations for services and teams.'
Consider narrowing the scope or organizing the trigger terms into logical groups to reduce conflict risk with more specialized skills (e.g., separate webhook management from notification routing from dashboard organization).
Rewrite in third person voice (e.g., 'Sets up monitoring and configures observability...') rather than the current 'Use this skill when the user asks...' format which, while functional, doesn't describe capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists many trigger phrases but doesn't clearly describe concrete actions the skill performs. It mentions things like 'set up monitoring', 'configure observability', 'create saved view' etc., which hint at capabilities but are presented as trigger terms rather than as a structured list of what the skill actually does. | 2 / 3 |
Completeness | The 'when' is extensively covered with the 'Use this skill when...' clause and numerous trigger phrases. However, the 'what does this do' part is essentially missing — there is no clear statement of what the skill actually does or what capabilities it provides. The trigger terms imply capabilities but don't explicitly describe them. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say, including variations like 'set up monitoring', 'configure observability', 'create saved view', 'set up Slack integration', 'configure PagerDuty', 'set up email alerts', 'webhook for alerts', and many more. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The description covers a very broad range of observability-related tasks (monitoring, webhooks, notifications, integrations, saved views, dashboards) which could overlap with more specialized skills for individual tools like PagerDuty, Slack, or webhook management. The scope is so wide it risks conflicting with narrower skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive CLI reference and reasonable workflow structure for observability setup, but suffers from two key gaps: the JSON payload files referenced throughout are never defined (making the guidance not truly copy-paste ready), and the CLI command tables are excessively long for patterns Claude could infer. The workflows are well-sequenced but lack explicit validation checkpoints between steps.
Suggestions
Add at least one concrete JSON example for each major resource type (connector, router, webhook, view) so that `--from-file` references are actionable rather than opaque.
Add explicit validation steps after creation commands (e.g., `cx webhooks get <id> -o json` to verify creation succeeded before proceeding to test).
Condense the CLI reference tables by documenting the common CRUD pattern once and only listing commands that deviate from it (e.g., `test`, `types`, `reorder`).
Move the full CLI command reference to a separate REFERENCE.md and keep SKILL.md focused on workflows with inline command examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The extensive CLI command tables are useful as a reference but are quite verbose — many commands follow obvious CRUD patterns that Claude could infer. The tables consume significant tokens for predictable patterns (list/get/create/update/delete). However, the specific command syntax (e.g., `cx notifications connectors entity-subtypes --type <type>`) does add value since these are tool-specific. | 2 / 3 |
Actionability | Commands are concrete and executable, but all `--from-file` references point to files like `connector.json`, `router.json`, etc. without ever showing the JSON schema or content of those files. A user following this skill would not know what to put in `slack-connector.json` or `router.json`, making the guidance incomplete for actual execution. | 2 / 3 |
Workflow Clarity | Multiple workflows are clearly sequenced with numbered steps, and the Notification Setup Workflow includes a test step at the end. However, there are no explicit validation checkpoints or error-recovery feedback loops between steps — for instance, after creating a connector, there's no 'verify it was created successfully before proceeding' step. The batch actions command also lacks validation guidance. | 2 / 3 |
Progressive Disclosure | The skill references related skills (cx-dashboards, cx-incident-management, etc.) which is good progressive disclosure. However, the massive CLI reference tables could be split into a separate REFERENCE.md file, keeping the SKILL.md focused on workflows. No bundle files exist to offload this content to. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- coralogix/cx-cli
- Commit
34d6303
- Reviewed
Table of Contents
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.