Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Agistra/agistra.dev52026년 10월 19일 업데이트
무료GitHub에 공개
scan-tst
Use when: analysing a project's test health — coverage, robustness, and CI integration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기포함된 파일(1)
- SKILL.md2.3 KB
SKILL.md(원문)
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Test Perspective (TST)
Evaluates whether the project has a functioning, proportionate test suite. Assigns a score from 0.0 to 1.0 across two dimensions.
Dimensions
Coverage ratio — Are enough source files tested?
- Score = min((testFileCount / sourceFileCount) * 2, 1.0) — 50%+ coverage = full score
- 0 test files = 0.0 immediately (no further analysis needed)
Test script — Can the suite be run?
- package.json must define scripts.test
- Missing test script = 0.0 on this axis regardless of file count
Scoring
tst_score = (coverage_ratio + test_script) / 2
Edge case: if no test files exist at all, score is 0.0 and only one critical task is generated.
When test suite execution fails: If the test suite cannot be executed (missing dependencies, syntax errors, unavailable runtime), record this as a data gap rather than failure; note it in output and do not penalize the coverage score until the execution blocker is resolved.
Score interpretation:
- 0.9–1.0 Test suite is healthy and runnable
- 0.7–0.9 Good coverage but minor gaps
- 0.5–0.7 Coverage is below target — significant untested surface
- 0.0–0.5 Test suite is absent or severely inadequate — highest risk area
Tasks Generated
| Finding | Priority |
|---|---|
| No test files at all | critical |
| Test file ratio < 50% | high |
| No scripts.test in package.json | high |
Agent Analysis Guide
When performing a manual TST analysis:
- Count source files (excluding test files) and test files separately
- Calculate the ratio and identify which source modules have zero test coverage
- Run the test suite if possible — note any failing tests, not just missing ones
- Check test speed: tests that take >30 seconds block CI feedback loops
- Look for edge cases that are clearly missing: empty inputs, null values, concurrent access, error paths
- Identify tests that only assert the happy path — these create false confidence
- Flag any test that mocks the database or external service when an integration test is possible
Output: ratio score, list of untested modules ordered by risk, and specific edge cases missing from existing tests.
리뷰
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
댓글
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
같은 저장소의 스킬
Use when: architecture mode, architect this, ADR, C4, PlantUML, system boundary, design decision, PRD gap, high ambiguity, multiple technical approaches, security architecture, data architecture, integration risk, implementability gap, story ticket, or epic ticket.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Agistra/agistra.dev52026년 10월 19일 업데이트
Use when: assumptions audit, audit assumptions, check for hidden assumptions, plan/ticket has ambiguous scope edges, pre-flight before finalizing a ticket, unstated assumptions, or 'what am I assuming'. Surfaces unstated assumptions, ambiguous scope edges, and untested preconditions in a finished plan/ticket/ADR before it is handed to Builder. Optional pass — Architect judges when to apply it; not a mandatory gate on every ticket.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Agistra/agistra.dev52026년 10월 19일 업데이트
Use when: Tester needs UI state evidence for VBR, or Builder needs to verify an integration wire is observable end-to-end. Powered by agent-browser MCP — token-efficient browser automation (200–400 tokens/page).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Agistra/agistra.dev52026년 10월 19일 업데이트
Use when drafting a bug or defect ticket, reviewing one someone else wrote, or deciding whether a reported problem is ready to file. Keeps what the reporter actually saw separate from what the agent later found out, so a reader can tell which lines are testimony and which are collected proof. Trigger phrases: 'file a bug', 'write up this defect', 'triage this report', 'is this ticket ready to file', 'what did the reporter actually see'.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Agistra/agistra.dev52026년 10월 19일 업데이트
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Agistra/agistra.dev52026년 10월 19일 업데이트