CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cx-observability-setup/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A well-structured, command-dense setup guide with concrete executable steps and explicit test checkpoints, but it is a monolith: a full CLI command catalog inlined in the body, redundant command repetition across three overlapping workflow sections, and no example JSON payloads or reference files to carry the detail. The guidance is reliable but pays a real token cost on every invocation.

Suggestions

Move the ~90-command CLI catalog to a references/cli-reference.md file and keep only the 10-15 commands actually used in the workflows in the SKILL.md body, with a clearly signaled link to the full reference.

Merge the New Service Setup, Notification Setup, and Webhook Setup sections into a single workflow — the latter two largely restate steps 2-4 of the first — eliminating the repeated `cx notifications connectors types`, `cx webhooks types`/`create`/`test` blocks.

Add one minimal example payload (e.g. a router.json or slack-connector.json with the required fields) or an explicit pointer to where field schemas can be discovered, since `--from-file` commands are currently unaccompanied by any description of file contents.

DimensionReasoningScore

Conciseness

The body contains no explanations of concepts Claude already knows and the tables are dense, but the three workflow sections (New Service Setup, Notification Setup, Webhook Setup) repeat commands already catalogued verbatim in the ~90-row CLI tables (e.g. `cx notifications connectors types`, `cx webhooks types`/`create`/`test` appear in multiple sections). It matches anchor 3 — mostly efficient but could be meaningfully tightened by deduplication.

3 / 5

Actionability

Concrete, copy-paste-ready `cx` commands throughout (e.g. `cx views create --from-file folder.json`, `cx notifications routers create --from-file router.json`), plus a genuinely useful "template from existing" technique (`cx <command> get <id> -o json > template.json`). Below anchor 5 because the JSON payload files (view.json, webhook.json, router.json) — the actual hard content of the task — are never shown or described, leaving a minor-to-moderate gap.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced (New Service Setup 1-7, Notification Setup 1-5 with a "Test End-to-End" step, Webhook Setup 1-4 with a test step), reinforced by the Key Principles section ("Always test after setup"). Below anchor 5 because there are no explicit feedback loops — no guidance on diagnosing a failed `cx webhooks test` or `cx notifications test` result and retrying.

4 / 5

Progressive Disclosure

Sections are well-organized with clear headers and useful cross-skill links (cx-dashboards, cx-slos), but there are no bundle files at all: the entire ~90-command CLI catalog — reference material that clearly belongs in a separate file — is inlined in SKILL.md. This matches anchor 3 (structure present, content that should be separate is inline) rather than 2, since navigation is not buried.

3 / 5

Total

14

/

20

Passed

Description

82%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.

A trigger-optimized description with exceptional natural-language keyword coverage and an explicit, well-scoped "when" clause. Its main weakness is that the capability statement (the "what") is implicit — scattered across quoted trigger phrases rather than stated directly. Third-person voice and observability-stack framing keep conflict risk low.

DimensionReasoningScore

Specificity

Many concrete actions are named ("create saved view", "configure webhook", "set up Slack integration", "configure PagerDuty", "deploy extension"), giving minor gaps in coverage rather than a comprehensive capability statement. It is above anchor 3 because far more than 1-2 actions are listed, but below anchor 5 because the actions appear as quoted trigger phrases rather than an explicit statement of what the skill does.

4 / 5

Completeness

The "when" is emphatically explicit ("Use this skill when the user asks to..." plus "or wants to set up, configure, or manage the observability stack for a service or team"), and the "what" is conveyed through the enumerated operations. It falls short of anchor 5 because there is no standalone, explicit capability statement — the "what" must be assembled from the trigger list — while exceeding anchor 3 since the "when" is anything but weakly implied.

4 / 5

Trigger Term Quality

Comprehensive natural-language coverage with synonyms and product-specific terms: "set up monitoring", "configure observability", "onboard new service", "saved view", "view folder", "webhook for alerts", "set up email alerts", "notification routing", "test webhook", "connect external service". These are exactly the phrases a user would naturally say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

Most triggers (saved view, notification connector, PagerDuty, notification routing, outgoing webhook) point clearly at observability setup, but a few terms overlap sibling skills: "organize dashboards" and "create view" could match a dashboards skill, and "webhook for alerts" could match an alerts skill. This is minor overlap with closely related skills, matching anchor 4.

4 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
coralogix/cx-cli
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.