create-runtime-setting
Create a new RuntimeSetting that can be changed at runtime via `agent config set/get` and the config API
72
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/create-runtime-setting/SKILL.mdQuality
Discovery
57%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 reasonably specific about what it does—creating a RuntimeSetting—and references concrete interfaces, giving it a clear niche. However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms and broader action coverage.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to add a new runtime configuration option, setting, or flag that can be changed via `agent config set/get`.'
Include more natural trigger terms such as 'configuration option', 'new setting', 'add config', 'runtime flag' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a specific domain (RuntimeSetting) and a concrete action (create), and mentions the mechanism (`agent config set/get` and config API), but it only describes one action rather than listing multiple concrete capabilities. | 2 / 3 |
Completeness | It answers 'what' (create a new RuntimeSetting changeable at runtime via specific interfaces) but lacks an explicit 'Use when...' clause or equivalent trigger guidance, capping this at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'RuntimeSetting', 'agent config set/get', 'config API', and 'runtime', which are useful but fairly technical. Missing more natural user phrasings like 'add a configuration option', 'new setting', or 'runtime configuration'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is quite specific to RuntimeSetting creation with particular APIs (`agent config set/get`), making it a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill that provides a clear multi-step workflow for creating RuntimeSettings in the Datadog Agent codebase. Its greatest strengths are the precise file paths, concrete implementation guidance, and well-sequenced workflow with verification steps. Minor weaknesses include some redundancy between sections and the lack of progressive disclosure through supporting files for what is a moderately complex skill.
Suggestions
Remove the redundancy between the step descriptions and the Important Notes section — several points (RuntimeSetting interface location, helper functions, HTTP/CLI exposure) are stated twice.
Consider creating bundle reference files for type-specific implementation templates (e.g., a boolean vs integer example) to reduce the main skill's length and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and well-structured, but includes some information Claude would already know (e.g., explaining what CLI and HTTP API are, some redundancy between the instructions and the Important Notes section). The step-by-step format is appropriate for the complexity, but some details are repeated across sections. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific file paths, exact glob patterns to discover references, precise method signatures to implement, specific bash commands for testing, and clear naming conventions. It tells Claude exactly which files to read, what to create, and where to register the setting. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with logical dependencies (gather info → read references → implement → test → register → verify). Step 6 includes explicit validation via tests and linting with a feedback loop ('If tests or linting fail, fix the issues'). The workflow handles the complexity of multi-service registration well. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but it's a monolithic file with no references to supporting bundle files. Given the complexity (multiple value types, multiple registration sites, test patterns), some content like type-specific implementation examples or registration patterns could be split into referenced files. However, no bundle files exist to support this. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- DataDog/datadog-agent
- Commit
0f36ad4
- 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.