datadog-cli

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

1.43x

Quality

89%

Does it follow best practices?

Impact

96%

1.43x

Average score across 6 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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.

An efficient, highly actionable command reference with a clear triage workflow and well-structured one-level-deep references. Minor redundancy between the command table, quick examples, and workflow is the only weakness.

Suggestions

Consolidate overlapping commands between the Commands Overview table, Quick Examples, and Incident Triage Workflow to reduce redundancy and save tokens.

Add a brief validation/decision checkpoint in the triage workflow (e.g., 'if errors are new vs. baseline, proceed to step N') to make the investigative sequence more self-correcting.

Dimension	Reasoning	Score
Conciseness	Lean and command-table-driven with no concept over-explanation, though the Quick Examples and Incident Triage Workflow repeat commands already shown in the Commands Overview, which could be trimmed.	4 / 5
Actionability	Copy-paste-ready npx commands with concrete flags cover the common cases (logs search, tail, trace, metrics query, compare, error summary).	5 / 5
Workflow Clarity	The Incident Triage Workflow is a clear, numbered, commented 6-step sequence; it lacks explicit validation checkpoints, but as a read-only investigative flow the destructive/batch cap does not apply and the gap is minor.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with five one-level-deep reference links (all real files: logs-commands.md, metrics.md, query-syntax.md, workflows.md, dashboards.md), clearly signaled in Required Reading and inline.	5 / 5
	Total	18 / 20 Passed

Description

92%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 strong, third-person description that names concrete capabilities and gives explicit trigger guidance. Only minor keyword-synonym gaps prevent a perfect trigger_term_quality score.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — 'searching logs, querying metrics, tracing requests, and managing dashboards' — giving comprehensive coverage of the CLI's capabilities with no vague filler.	5 / 5
Completeness	Explicitly answers both what ('searching logs, querying metrics, tracing requests, managing dashboards') and when ('Use this when debugging production issues or working with Datadog observability') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'debugging production issues' and 'Datadog observability' plus log/metric/trace/dashboard terms are present, but a few common synonyms (e.g. 'alerts', 'APM') are missing.	4 / 5
Distinctiveness Conflict Risk	'Datadog CLI' names a clear niche with distinct triggers; minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: softaworks/agent-toolkit
Path: skills/datadog-cli/SKILL.md
Commit: 3027f20

Reviewed: 4 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.