Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Integration Test Validator

ASecurity

Audits PABX backend integration tests (apps/backend/__tests__/integration/) against the integration-test-writer rules, producing a compliance report with a PASS/FAIL/PASS WITH WARNINGS verdict, per-violation severity, and fix suggestions. Read-only — never writes or fixes tests. Dispatched by the evaluator to confirm a corrected integration test conforms before resuming evaluation, or run directly by a user.

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentssqlapidatabasebackendsecurity

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add dayvisonassis/sdd-skills --skill integration-test-validator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Integration Test Validator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Integration Test Validator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dayvisonassis-integration-test-validator/badge)](https://www.skillsdirectory.com/skills/dayvisonassis-integration-test-validator)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: integration-test-validator
description: Audits PABX backend integration tests (apps/backend/__tests__/integration/) against the integration-test-writer rules, producing a compliance report with a PASS/FAIL/PASS WITH WARNINGS verdict, per-violation severity, and fix suggestions. Read-only — never writes or fixes tests. Dispatched by the evaluator to confirm a corrected integration test conforms before resuming evaluation, or run directly by a user.
---

# Integration Test Validator (PABX)

Audit **integration test files** to ensure they comply with every rule the
`integration-test-writer` enforces. **Read-only:** produce a compliance report; never modify
test/production files, never execute tests (static analysis only).

> **Project scope:** PABX backend. The full rule set is in
> **`../integration-test-writer/references/pabx-rules.md`** — validate against it.

**Scope:** `apps/backend/__tests__/integration/`.

## INPUT

- `test_file_path` (required) — test file or directory.
- `checklist_file_path` (optional) — the `.test.md` for coverage cross-reference.
- `target_file_or_endpoint` (optional) — the controller/endpoint under test.
- `severity_filter` (optional) — `critical` | `major` | `minor` (default: all).

## OUTPUT

A **compliance report** (English): summary counts, overall verdict (`PASS` = 0 critical + 0
major; `PASS WITH WARNINGS` = 0 critical, some major/minor; `FAIL` = ≥1 critical), each violation
(`[SEVERITY] Rule-ID`, location, description, expected, found, fix), coverage analysis, and
positive findings. When dispatched by the evaluator, the **verdict** is the signal it consumes.

---

## EXECUTION STEPS (3 Phases)

### Phase 1 — Structural Analysis
Inventory `describe`/`it`/hooks/helpers. Map checklist ↔ tests and endpoint ↔ tests (if provided).
Identify every data-creation point and every cleanup point (`try-finally`, `afterEach`,
`afterAll`, direct deletes). Note imports.

### Phase 2 — Rule-by-Rule Validation
Check EVERY rule from `../integration-test-writer/references/pabx-rules.md`:
- **Language & Naming** [CRITICAL] — English only; descriptive names; no double blank lines.
- **Test Structure** [MAJOR] — AAA; independence; deterministic; `setupTestDatabase`/`cleanupTestDatabase`/`supertest`/`app` file pattern; no prod modification.
- **Data Cleanup** [CRITICAL] — `try-finally` per data-creating test; `try-catch` inside `finally`; FK order (`audit_logs` → `users_permissions`/`user_permissions_group` → `group_permissions` → `permissions` → `users` → `dr_agent` → `dr_domain`); only test-created data; no data left behind; ≥2 cleanup levels.
- **Execution Setup** [MAJOR] — `setupTestDatabase()` in `beforeAll` (destructure `token`); `cleanupTestDatabase()` in `afterAll`; correct imports.
- **Coverage** [MAJOR] — CRUD, auth/authorization, validation errors, not-found, edge cases, security (SQLi/XSS), checklist alignment.
- **Forbidden Practices** [CRITICAL] — no prod modification; no external data scripts; no pre-existing-data removal; no afterEach-only cleanup for created data; no Portuguese.
- **API Behavior** [MINOR] — status assertions; response-body assertions; correct HTTP methods; `Authorization` header on authenticated requests.

Do not skip rules after finding criticals. State which were skipped and why.

### Phase 3 — Compliance Report
Emit the full report per OUTPUT. Verdict is derived strictly from the counts.

---

## RULES

**Always:**
- Validate against `../integration-test-writer/references/pabx-rules.md`; check every rule.
- Give exact line/block locations and a concrete fix per violation; report positives. Output in English.
- Derive the verdict strictly from severity counts.

**Never:**
- Modify any test or production file (read-only). Execute the tests. Mark PASS with any CRITICAL. Produce partial reports.

---

## Edge Cases

- **Empty test file:** CRITICAL. **Missing `setupTestDatabase`/imports:** report each individually.
- **Data created without `try-finally`:** CRITICAL (F4). **Wrong FK cleanup order:** CRITICAL (C3).
- **Directory input:** one report per file + a summary.

Attribution

dayvisonassisdayvisonassis
View sourceSee grades on GitHubMore from dayvisonassis →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

696561 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes
View all in ai-agents →