CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

49

Quality

54%

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 ./skills/datadog-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill covers a broad set of Datadog operations but suffers from significant verbosity and repetition, with timestamps, tag syntax, and query formats explained multiple times. The actionability is moderate—tool names and parameters are listed but lack complete invocation examples. The monolithic structure with no supporting bundle files makes it harder to navigate and wastes context window tokens.

Suggestions

Deduplicate repeated information (timestamps, tag syntax, query formats) into a single 'Common Patterns' section and remove from individual workflow pitfalls

Add concrete, copy-paste-ready tool invocation examples for at least the 2-3 most common workflows (e.g., querying metrics, creating a monitor)

Add explicit validation/confirmation steps after destructive operations like DELETE dashboard and after creating downtimes

Split the Quick Reference table and detailed per-workflow parameter docs into a separate REFERENCE.md file, keeping SKILL.md as a concise overview

DimensionReasoningScore

Conciseness

The skill is significantly verbose with substantial repetition. The 'Pitfalls' sections repeat information across workflows (timestamps mentioned multiple times), the Quick Reference table duplicates information already covered in each workflow section, and the 'Known Pitfalls' section rehashes points already made. Much of the parameter documentation (tag syntax, query formats) is information Claude could derive from tool schemas that the skill itself says to always fetch first.

2 / 5

Actionability

The skill provides tool names and parameter lists, which is somewhat concrete, but lacks executable examples showing actual tool invocations with realistic parameter values. The monitor query syntax examples are helpful, but most workflows describe what to do abstractly ('Call DATADOG_QUERY_METRICS') without showing a complete invocation with all required parameters filled in. The instruction to 'always call RUBE_SEARCH_TOOLS first' partially undermines the value of the detailed parameter docs.

3 / 5

Workflow Clarity

Workflows are sequenced with numbered steps and labeled as Required/Optional, which is good. However, the DELETE dashboard operation is listed without any validation or confirmation step, and there are no feedback loops for error recovery. The 'create downtime' workflow lacks a verification step to confirm the downtime was applied. For destructive operations like DELETE dashboard, the missing validation caps this at 3.

3 / 5

Progressive Disclosure

The content is a monolithic ~200-line document with no references to external files. The detailed parameter documentation for 6 different workflow categories, the quick reference table, and the common patterns section could all benefit from being split into separate reference files. Everything is inlined in a single wall of content with no bundle files to support it.

2 / 5

Total

10

/

20

Passed

Description

70%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 strong in specificity and distinctiveness, clearly identifying Datadog-specific automation capabilities via a named integration (Rube MCP/Composio). Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Adding a few more natural trigger terms and synonyms would also improve discoverability.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Datadog monitoring, log queries, alerting, or dashboard management.'

Include additional natural trigger terms and synonyms such as 'observability', 'alerting', 'APM', 'log search', or 'incident management' to improve matching.

DimensionReasoningScore

Specificity

Lists several specific actions: query metrics, search logs, manage monitors/dashboards, create events and downtimes. These are concrete capabilities, though 'manage monitors/dashboards' is slightly vague compared to more granular actions like 'create, update, delete monitors.'

4 / 5

Completeness

Clearly answers 'what' with specific Datadog automation tasks, but lacks an explicit 'when' clause (no 'Use when...' guidance). The operational note 'Always search tools first for current schemas' is useful but doesn't substitute for trigger guidance. Per rubric rules, missing 'Use when' caps completeness at 3.

3 / 5

Trigger Term Quality

Includes strong natural keywords like 'Datadog', 'metrics', 'logs', 'monitors', 'dashboards', 'events', 'downtimes', and 'Composio'/'Rube MCP'. Missing some synonyms or variations users might say (e.g., 'alerting', 'observability', 'APM', 'log search').

4 / 5

Distinctiveness Conflict Risk

Highly distinctive due to the specific mention of 'Datadog', 'Rube MCP (Composio)', and domain-specific terms like monitors, downtimes, and metrics. Very unlikely to conflict with other skills.

5 / 5

Total

16

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.