Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Diagnose and fix failed e2e tests in tektoncd/catalog. Use when a CI run fails, a local test hangs, or a TaskRun/PipelineRun reaches an error state. Covers triage from GitHub Actions output to root cause, common failure patterns, and local reproduction.
Performance-overhead review of a code diff / branch / PR for the dd-trace-java tracer. Flags hot-path allocation, unbounded memory, repeated work, escaping objects, native-boundary crossings, and JVM-specific pitfalls (escape analysis, JNI / virtual-thread pinning, backtracking-regex ReDoS, varargs/boxing hashing, String.format, ByteBuddy-Advice anti-patterns) using the tracer performance rubric. Use whenever the user wants a performance / overhead / hot-path review, asks to check a diff or PR for allocation / GC / memory / latency / startup cost, or mentions the "perf rubric" or the "do no harm / assume hot" tracer posture — even if they just say "review this for perf" without naming the rubric. Advisory and READ-ONLY: it reports ranked, verify-first findings; it never edits code.
Post-migration quality review. Checks Java test files produced by migrate-groovy-to-java against the shared quality rules. Use after migration, or on any branch with recently migrated .java test files. Produces structured FINDING blocks grouped by severity, then offers to auto-fix BLOCKERs and WARNINGs.
Use when user says "validate the task", "ensure everything is passing", "is everything ok?", "valide a entrega" (PT-BR), "garanta que tudo está funcionando" (PT-BR), "certifique-se de que está tudo ok" (PT-BR), or anything associated with the idea of validating a task.
Debug or inspect the Cucumber HTML reporter output in the playwright-bdd project. Use when: investigating DOM structure changes in the Cucumber HTML reporter, updating test selectors or POMs after reporter upgrades, verifying what attachments/hooks/steps look like in the generated HTML report.
Additional iTwin.js PR review heuristics focused on consumer impact, compatibility, invariants, UI evidence, and docs accuracy.
Use when adding or modifying offline judge tests for bench_env tasks — specifically entries in `OFFLINE_JUDGE_POSITIVE_CASES` / `OFFLINE_JUDGE_NEGATIVE_CASES` in `bench_env/tests/<suite>/test_tasks.py`, or writing live tests. Triggers after a new task is added, or when tightening judge coverage.
Use when writing or modifying `check_goals()` / `get_answer()` / App `check_*` methods in `bench_env/task/`, or when reviewing a draft task's judge correctness. Triggers include adding a new task, editing a judge method, or diagnosing a judge false-positive/negative.
Write Solidity integration tests for EigenLayer contracts. Use when the user asks to write integration tests, test user flows, test cross-contract interactions, or test upgrade scenarios. Follows project conventions with User/AVS actors and numbered action steps.
Write Solidity unit tests for EigenLayer contracts. Use when the user asks to write tests, add test coverage, create unit tests, or test a function. Follows project conventions with per-function test contracts and mock dependencies.