CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

datadog-automation

Automate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas.

60

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/datadog-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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-organized, actionable reference that names exact tools, parameters, and query syntax for six workflows without padding. The main gaps are the duplicated pitfalls content, a missing pre-delete validation checkpoint for the irreversible dashboard deletion, and no bundle files splitting the per-tool API detail out of the main skill.

Suggestions

Add an explicit verification step before DATADOG_DELETE_DASHBOARD (e.g., 'Run DATADOG_GET_DASHBOARD first and confirm the ID and title match the intended dashboard before deleting'), plus a post-action confirmation checkpoint.

Deduplicate the 'Known Pitfalls' section — timestamp units, query syntax, and pagination guidance are already stated in the per-workflow Pitfalls blocks; keep only net-new content there.

Move the per-tool parameter details and the Quick Reference table into a references/ file (e.g., TOOLS.md), keeping SKILL.md as a workflow-level overview with well-signaled one-level-deep links.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence (tool slugs, parameter tables, pitfalls) with almost no explanation of concepts Claude already knows. However, the 'Known Pitfalls' section repeats material already stated per-workflow (timestamp units, query syntax, pagination), which is minor duplication that could be trimmed — fitting 'Efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean 5.

4 / 5

Actionability

Concrete guidance throughout: exact tool names, [Required]/[Optional] sequences, named parameters with example values (`avg:system.cpu.user{host:web01}`), and copy-pasteable monitor query syntax blocks. It is not 5 because no full tool-invocation example is shown (it delegates schemas to RUBE_SEARCH_TOOLS), leaving a minor gap for the most common single call.

4 / 5

Workflow Clarity

Setup steps are sequenced with checkpoints (verify RUBE responds, confirm connection ACTIVE before workflows), but the skill includes a destructive, irreversible operation (DATADOG_DELETE_DASHBOARD — 'DELETE is permanent; there is no undo') with no explicit verify-before-delete validation step. Per the guidelines, missing validation for destructive/batch operations caps workflow clarity at 3; it is not 2 because sequences and checkpoints for setup are otherwise well defined.

3 / 5

Progressive Disclosure

A single self-contained file with clear sectioning (per-workflow headers, Common Patterns, Quick Reference table) and one external link to the toolkit docs — no nested references. It is not 5 because at ~240 lines the per-tool parameter detail and the 19-row quick-reference table could arguably live in a reference file, which is a minor organization gap rather than a clear split.

4 / 5

Total

15

/

20

Passed

Description

75%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, specific description that names the domain and enumerates concrete capabilities in third person. Its single notable weakness is the absence of an explicit 'when to use' trigger clause, which limits discoverability and caps completeness.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user mentions Datadog, monitoring, observability, metrics, monitors, dashboards, downtimes, or log searches.'

Include a couple of common synonyms such as 'observability' or 'alerting' to broaden natural-language matching.

DimensionReasoningScore

Specificity

Lists five concrete actions ("query metrics, search logs, manage monitors/dashboards, create events and downtimes") that comprehensively cover the Datadog automation domain. This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage', and there is no vague filler that would pull it toward 4.

5 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or any trigger guidance for when to invoke the skill, which the guidelines cap at 3 ('Has a clear what but when is missing or only weakly implied'). It is not 2 because the what is specific, not vague.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'Datadog', 'metrics', 'logs', 'monitors', 'dashboards', 'events', 'downtimes'. A few natural variations are missing (e.g., 'observability', 'alerting', 'trace'), so it fits 'Good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

The description names a clear niche ('Datadog tasks via Rube MCP (Composio)') whose triggers (metrics, monitors, downtimes) are unambiguous and would not collide with other skills. Matches 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

davepoon/buildwithclaude

Path

plugins/all-skills/skills/datadog-automation/SKILL.md

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.