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.
75
66%
Does it follow best practices?
Impact
89%
1.28xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/datadog-automation/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly enumerates specific Datadog capabilities and includes excellent natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The procedural note about searching tools first is a nice operational detail but doesn't substitute for trigger guidance.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Datadog monitoring, log searches, metric queries, or managing Datadog resources.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'query metrics, search logs, manage monitors/dashboards, create events and downtimes.' Also includes a procedural instruction to 'search tools first for current schemas.' | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific Datadog actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied by the domain context. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Datadog', 'metrics', 'logs', 'monitors', 'dashboards', 'events', 'downtimes', 'Rube MCP', 'Composio'. These cover the main terms a user working with Datadog would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of 'Datadog', 'Rube MCP (Composio)', and the enumerated Datadog-specific operations. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 catalog of Datadog operations via Rube MCP with good structural organization and useful pitfall warnings. However, it suffers from verbosity through repeated information across sections, lacks fully executable examples showing complete tool call sequences, and misses validation checkpoints for destructive operations. The content would benefit from being more concise and splitting reference material into separate files.
Suggestions
Add complete, executable tool call examples for at least 2-3 core workflows showing actual parameter values and expected response structures, rather than just listing parameter names.
Add explicit confirmation/validation checkpoints before destructive operations (DELETE dashboard, creating downtimes) — e.g., 'GET the dashboard first to confirm identity, then confirm with user before DELETE'.
Consolidate duplicate information: timestamp format warnings, tag syntax, and query patterns each appear in multiple places. Keep them in one authoritative section and reference it.
Extract the quick reference table and common patterns into a separate reference file to reduce the main skill's token footprint and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but quite verbose for what it covers. There's significant repetition (e.g., pitfalls about timestamps appear in multiple sections AND in a dedicated 'Known Pitfalls' section). The quick reference table duplicates information already covered in each workflow section. Much of this (tag syntax, pagination patterns) is information Claude could derive from tool schemas after calling RUBE_SEARCH_TOOLS. | 2 / 3 |
Actionability | The skill provides tool names, parameter lists, and some query syntax examples, which is helpful. However, there are no complete executable workflows showing actual tool calls with concrete parameter values. The monitor query syntax examples are useful but most guidance remains at the 'list of parameters' level rather than showing copy-paste-ready tool invocations with realistic inputs and expected outputs. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps and labeled as Required/Optional, which is good. However, for destructive operations like DELETE dashboard ('irreversible') and creating indefinite downtimes, there are no explicit validation or confirmation checkpoints — just warnings in pitfalls. The setup section has a good verification flow, but core workflows lack feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | The content is structured with clear sections and headers, but it's monolithic — all content is in a single file with no references to supporting files. The quick reference table, common patterns, and known pitfalls sections could be split into separate reference files. For a skill this long (~200+ lines), better progressive disclosure with linked reference materials would improve navigability. | 2 / 3 |
Total | 8 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
74c7031
- 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.