feat: improve 3 skill definitions

[rohan-tessl]

Hey @DataDog 👋

I ran your skills through tessl skill review at work and found targeted improvements in your skills. Here's the before/after:

Skill	Before	After	Change
add-apm-integrations	17%	94%	+77%
migrate-junit-source-to-tabletest	84%	90%	+6%
techdebt	17%	83%	+66%

These were easy changes to bring the skill's structure and activation in line with what performs well against Anthropic's best practices.

What changed in add-apm-integrations

Removed unknown frontmatter key context and converted allowed-tools from YAML array to omitted (not a recognized key format). Rewrote description with concrete action verbs (scaffolds Gradle module, writes Instrumentation and Decorator classes, creates JUnit 5 tests). Score jumped from 17% to 94% because the frontmatter issues were blocking the LLM judge entirely.

What changed in techdebt

Removed unknown frontmatter keys user-invocable, context and allowed-tools array. Rewrote description with "Use when" clause and concrete capabilities (diffs against merge-base, identifies dead code, over-abstraction, copy-paste logic). All workflow steps preserved.

What changed in migrate-junit-source-to-tabletest

Added "Use when" clause to the description with concrete trigger terms. All conversion rules, table formatting rules, and JDK8 constraints preserved.

In addition, I stress-tested your add-apm-integrations skill against a few real-world scenarios, and it held up really well. This means that your skill meaningfully improves agent steering and contributes to stronger output quality. Kudos for that!

Honest disclosure, I work at @tesslio where we build tooling around skills like these. Not a pitch, just saw room for improvement and wanted to contribute.

If you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @rohan-tessl, if you hit any snags.