Agent-Skills.md

Agent Skills: Regression Checker

Runs existing test suite to catch regressions after implementation changes. Use when Story needs regression verification. No status changes.

UncategorizedID: levnikolaevich/claude-code-skills/ln-513-regression-checker

Repository

levnikolaevich/claude-code-skills
levnikolaevichLicense: MIT
29647

Install this agent skill to your local

pnpm dlx add-skill https://github.com/levnikolaevich/claude-code-skills/tree/HEAD/skills-catalog/ln-513-regression-checker

Skill Files

Browse the full folder contents for ln-513-regression-checker.

Download Skill

Loading file tree…

skills-catalog/ln-513-regression-checker/SKILL.md

Skill Metadata

Name
ln-513-regression-checker
Description
"Runs existing test suite to catch regressions after implementation changes. Use when Story needs regression verification. No status changes."

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If shared/ is missing, fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.

Regression Checker

Type: L3 Worker Category: 5XX Quality

Runs the existing test suite to ensure no regressions after implementation changes.

Inputs

| Input | Required | Source | Description | |-------|----------|--------|-------------| | storyId | Yes | args, git branch, kanban, user | Story to process |

Resolution: Story Resolution Chain. Status filter: To Review

Purpose & Scope

  • Detect test framework (pytest/jest/vitest/go test/etc.) and test dirs.
  • Execute full suite; capture stdout/stderr for Story quality gate.
  • Return PASS/FAIL with counts/log excerpts; never modifies Linear or kanban.
  • Preserve full stdout/stderr output for downstream log analysis.

When to Use

  • After code quality checks pass
  • Code quality check passed

Workflow

Phase 0: Resolve Inputs

MANDATORY READ: Load shared/references/input_resolution_pattern.md, shared/references/ci_tool_detection.md

  1. Resolve storyId: Run Story Resolution Chain per guide (status filter: [To Review]).

Phase 1: Execute Tests

MANDATORY READ: Load shared/references/output_normalization.md

Read target project files if they exist: docs/project/infrastructure.md, docs/project/runbook.md

  1. Auto-discover test framework per ci_tool_detection.md Command Registry (Test Frameworks section).
  2. Get service endpoints, port allocation from infrastructure.md. Get exact test commands, Docker setup, environment variables from runbook.md. Runbook commands take priority over auto-detection (per ci_tool_detection.md Discovery Hierarchy).
  3. Build appropriate test command; run with timeout (5min per ci_tool_detection.md); capture stdout/stderr.
  4. Parse results: passed/failed counts; key failing tests.
  5. Normalize + group failures: Apply shared/references/output_normalization.md §1-§3 to test output. Group failing tests by error category (Import/Module, Assertion, Timeout, Type, Connection, Runtime). Report grouped: e.g., "3 Import errors in auth/, 2 Assertion mismatches in payment/".
  6. Output verdict JSON (PASS or FAIL + grouped failures list) and add Linear comment.

Critical Rules

  • No selective test runs; run full suite.
  • Do not fix tests or change status; only report.
  • Language preservation in comment (EN/RU).

Runtime Summary Artifact

MANDATORY READ: Load shared/references/quality_summary_contract.md

Accept optional summaryArtifactPath.

Summary kind:

  • quality-worker

Required payload semantics:

  • worker = "ln-513"
  • status
  • verdict
  • issues
  • warnings
  • artifact_path

Write the summary to the provided artifact path or return the same envelope in structured output.

Definition of Done

  • [ ] Framework detected; command executed
  • [ ] Results parsed; verdict produced with failing tests (if any)
  • [ ] Linear comment posted with summary

Reference Files

  • Risk-based limits used downstream: shared/references/risk_based_testing_guide.md
  • CI tool detection: shared/references/ci_tool_detection.md
  • Output normalization: shared/references/output_normalization.md
  • Pytest patterns: references/pytest_configuration.md

Version: 3.1.0 Last Updated: 2026-01-09