CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apm-integrations

Use when adding, debugging, fixing, or modifying instrumentation and plugins for third-party libraries in dd-trace-js. Triggers: "add a new integration", "instrument a library", any *Plugin base class (Tracing/Database/Cache/ Client/Server/Consumer/Producer/Composite), "addHook", "shimmer.wrap", "orchestrion", "bindStart"/"bindFinish", "diagnostic channel", "runStores", "subscriber cardinality", "channel.publish gate", "read upstream source", "reference plugin".

Quality

95%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An excellent instruction-oriented skill body: concrete commands and decision rules throughout, a fully sequenced workflow with explicit validation and debugging feedback loops, and clean one-level-deep progressive disclosure backed by verified reference files. The only deduction is minor rhetorical padding in a couple of prose passages that could be tightened without losing information.

DimensionReasoningScore

Conciseness

Dense and information-rich, teaching only non-obvious domain knowledge (channel prefix patterns, subscriber cardinality, orchestrion decision rules) with no basic-concept padding. Minor instances of rhetorical framing that could be trimmed, e.g. 'Memory of an SDK's contract drifts faster than the SDK; comments in the wrap go stale every minor version' and the two-camp cardinality exposition, so it sits at 'efficient; minor instances of over-explanation' rather than fully lean.

4 / 5

Actionability

Provides copy-paste-ready commands (git clone --depth 1 --branch, npm pack + tar extraction, PLUGINS="<name>" npm run test:plugins:ci, docker compose up -d, DD_TRACE_DEBUG=true), exact file paths for every artifact, a concrete decision rule for orchestrion vs. shimmer, and a reference table keyed by library type. The referenced bundle files contain the full executable templates (testing spec template, orchestrion config format), covering the common cases end to end.

5 / 5

Workflow Clarity

The 7-step Implementation Workflow is clearly sequenced with an explicit validation step ('Confirm all tests pass before marking work as complete') and concrete test commands including the external-services variant. The Debugging section supplies symptom-to-fix feedback loops (spans missing → verify hasSubscribers; context lost → use runStores not publish; ESM fails → esmFirst: true), matching the top anchor.

5 / 5

Progressive Disclosure

The body is a well-organized overview that links five reference files inline where each is relevant and catalogs all of them in a 'Reference Files' section with one-line descriptions. All five referenced files exist in references/, are substantive, and are exactly one level deep — no nested pointer chains.

5 / 5

Total

19

/

20

Passed

Description

95%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 description with an explicit 'Use when' clause, a clearly stated scope, and an unusually thorough trigger list spanning both natural phrases and repo-specific technical terms. The only minor gap is that the skill's full capability surface is implied through triggers rather than explicitly enumerated actions.

DimensionReasoningScore

Specificity

Lists concrete actions ('adding, debugging, fixing, or modifying instrumentation and plugins') against a precisely named domain ('third-party libraries in dd-trace-js'), matching the 'several specific actions; minor gaps' anchor. Not 5 because the capability surface (orchestrion config, plugin base classes, registration, testing) is conveyed through triggers rather than enumerated actions.

4 / 5

Completeness

Explicitly answers 'what' (instrumentation and plugins for third-party libraries in dd-trace-js) and 'when' via a leading 'Use when...' clause followed by a concrete trigger list. Clearly matches the top anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases users would say ('add a new integration', 'instrument a library', 'reference plugin') alongside verbatim technical synonyms ('addHook', 'shimmer.wrap', 'bindStart'/'bindFinish', 'runStores', 'diagnostic channel'). Comprehensive coverage including both casual and expert-level variations.

5 / 5

Distinctiveness Conflict Risk

Anchored to a single repository (dd-trace-js) with repo-specific trigger terms (shimmer.wrap, orchestrion, subscriber cardinality). Clear niche with distinct triggers; minimal conflict risk with any other skill.

5 / 5

Total

19

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

DataDog/dd-trace-js

Path

.agents/skills/apm-integrations/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.