apm-integrations
This skill should be used when the user asks to "add a new integration", "instrument a library", "add instrumentation for", "create instrumentation", "new dd-trace integration", "add tracing for", "TracingPlugin", "DatabasePlugin", "CachePlugin", "ClientPlugin", "ServerPlugin", "CompositePlugin", "ConsumerPlugin", "ProducerPlugin", "addHook", "shimmer.wrap", "orchestrion", "bindStart", "bindFinish", "startSpan", "diagnostic channel", "runStores", "reference plugin", "example plugin", "similar integration", or needs to build, modify, or debug the instrumentation and plugin layers for a third-party library in dd-trace-js.
70
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
72%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 excels at trigger term coverage and distinctiveness, providing an extensive list of specific phrases and technical terms that would help Claude select this skill accurately. However, it is weak on describing what the skill actually does — the concrete capabilities and outputs are barely mentioned, buried under the long list of trigger keywords. The description reads more like a keyword index than a balanced skill description.
Suggestions
Add a clear 'what it does' section before the trigger terms, e.g., 'Creates new dd-trace-js integrations with proper plugin structure, configures tracing hooks, wraps library methods with shimmer, and sets up diagnostic channel instrumentation.'
Restructure to separate capabilities from triggers — lead with 2-3 sentences describing concrete actions, then follow with 'Use when...' trigger guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions the domain (dd-trace-js instrumentation/plugin layers) and some actions (build, modify, debug), but it doesn't list specific concrete actions comprehensively — it's mostly a long list of trigger terms rather than describing what the skill actually does step by step. | 2 / 3 |
Completeness | The 'when' is very well covered with explicit trigger phrases and a 'Use when' equivalent at the start. However, the 'what does this do' is weak — it only vaguely says 'build, modify, or debug the instrumentation and plugin layers' without describing the concrete outputs or steps the skill performs. The heavy trigger-term focus leaves the capability description underdeveloped. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say, including both high-level phrases ('add a new integration', 'add tracing for') and specific technical terms ('shimmer.wrap', 'diagnostic channel', 'addHook', 'TracingPlugin'). These are terms a developer working with dd-trace-js would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the description is clearly scoped to dd-trace-js instrumentation and plugin layers for third-party libraries, with very specific technical terms (shimmer.wrap, orchestrion, bindStart, bindFinish) that are unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that efficiently communicates a complex integration architecture. It provides the right level of detail in the overview — architecture diagram, base class hierarchy, key concepts, decision criteria, debugging tips, and a clear workflow — while deferring deep details to well-organized reference files. The content is highly actionable with specific file paths, commands, and a reference integration table that makes it easy to find examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is dense and efficient. Every section earns its place — architecture diagrams, base class hierarchies, channel patterns, and debugging tips all convey non-obvious, project-specific knowledge. There's no explanation of basic concepts Claude would already know. | 3 / 3 |
Actionability | Provides concrete file paths, exact bash commands for testing, specific channel naming patterns, a decision framework for orchestrion vs shimmer, and a reference table mapping library types to specific plugins and base classes. The implementation workflow has copy-paste-ready commands. | 3 / 3 |
Workflow Clarity | The 7-step implementation workflow is clearly sequenced with investigation first, implementation second, registration third, and explicit test/verify steps at the end. The debugging section provides a troubleshooting feedback loop (symptoms → causes → fixes). The orchestrion-vs-shimmer decision tree provides clear validation criteria. | 3 / 3 |
Progressive Disclosure | The SKILL.md serves as a well-structured overview with clear one-level-deep references to 5 detailed reference files (new-integration-guide, orchestrion, plugin-patterns, testing, reference-plugins). Each reference is clearly labeled with its purpose. The main file contains enough context to orient without overwhelming. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- DataDog/dd-trace-js
- Commit
50aa025
- 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.