القائمة
Designs the test pyramid, writes unit, integration, and end-to-end tests, establishes CI gates, and sets coverage policy for a software project.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | go-eagle |
| version | 1.1.1 |
| description | Designs the test pyramid, writes unit, integration, and end-to-end tests, establishes CI gates, and sets coverage policy for a software project. |
| when_to_use | Use when establishing a testing strategy for a new project, adding missing test coverage, auditing test quality, or planning a QA phase before release. Invoke after go-wolf and/or go-lynx have produced a working implementation. |
go-eagle sees everything from above. It identifies what matters to test, at what level, and makes sure the safety net is real — not just numbers on a coverage report.
Prerequisites: Working implementation from go-wolf and/or go-lynx
→ invoke go-eagle
→ test pyramid design → unit tests → integration tests → E2E tests → CI gate
Decide the distribution and justify each choice:
/\
/E2E\ ← few, slow, catch integration failures
/------\
/Integr. \ ← moderate, catch contract and DB issues
/----------\
/ Unit \ ← many, fast, catch logic bugs
/--------------\
Anti-pattern to avoid: the ice cream cone (too many E2E, no unit tests).
For the full breakdown of what belongs at each level, read:
${CLAUDE_SKILL_DIR}/references/test-levels.md
Every PR must pass before merge:
E2E tests: merge to main or nightly — not every PR unless cycle time allows it.
Set a floor (e.g., 80%) but:
Flaky tests must be fixed or deleted — never skipped indefinitely. A test that cannot fail is not a test.
.test.ts co-located), not in a separate tests/ tree.docs/TESTING.md — test strategy (pyramid decisions, tooling, CI policy)Conducts structured technical conversations — code walkthroughs, architectural debates, decision support, rubber-duck debugging, and Q&A — using mode-aware dialogue, one-question-per-turn discipline, explicit assumption labeling, and escalation signals that hand off to the right beast when a conversation has produced enough to warrant a formal artifact.
Conducts a multi-pass code review with structured scoring across seven dimensions (correctness, security, maintainability, testability, performance, design, observability), applies a calibrated 0–4 rubric per dimension, produces OIR-structured findings with BLOCKER/WARNING/SUGGESTION/NIT severity classification, and emits a SCORE_REPORT.md with a dimensional scorecard and a merge verdict.
Translates approved requirements into an architecture decision record (ADR), technology stack selection, Mermaid component diagram, and interface contracts.
Audits an existing system's architecture across five dimensions — structure, observability, reliability, scalability, and security posture — and produces a prioritized HTML report with findings, capability gaps, and concrete improvement proposals. Uses repomix to pack the codebase, reads ADRs and CONTEXT.md when present, and opens the report in the browser.
Designs entity-relationship models, defines schemas with conventions, writes safe migrations with rollback, plans indexing strategy, and reviews queries for N+1 and sequential scans.
Translates interface contracts and functional requirements into BDD scenario files (Given/When/Then), an acceptance test skeleton, and a SPEC.md that go-wolf and go-lynx must satisfy before implementation begins.