القائمة
Use when the user requests integration testing, feature validation, or test plan execution
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
Perform Harbor release procedures — version bumping, codegen, committing, pushing, and drafting GitHub releases. Use this skill when the user wants to release a new version of Harbor, bump the version number, create a release on GitHub, run the release codegen pipeline, or anything related to shipping a new Harbor version. Triggers on phrases like "release Harbor", "bump version", "new release", "ship a new version", or "prepare a release".
Live-test a Harbor Boost module by sending a real prompt through llamacpp via pi and validating the output. Use when asked to test a boost module, verify a module works, check module behavior, QA a boost module, or confirm a module's effect on LLM output.
CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services", "check what's running", "harbor launch", Boost custom workflows, or any Docker-based AI service management task.
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all fixes against repo constraints and target platforms. Runs end-to-end without user interaction.
Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration
| name | agent-integration-testing |
| description | Use when the user requests integration testing, feature validation, or test plan execution |
This skill guides the creation and autonomous execution of verifiable integration test specifications. It ensures that tests are actionable by agents, properly documented, and systematically executed by subagents to validate features or fix failures.
Investigate Codebase Area
glob and grep to narrow the investigation.Write Test Specification
./tests/<name>.md.<name> = "integration" unless the user specifies a particular feature area.Define Verifiable Tests
Execute Tests via Subagents
Task tool or @mention subagent system) to run each individual test.Fix Failures (Optional)
SWE or BUILDER agent) to investigate and fix any noted failures.| Action | Pattern / Command |
|---|---|
| Test File Location | ./tests/<name>.md (default: integration.md) |
| Prerequisites | Must be documented at the top of the test file |
| Test Format | Plain English, Repro Steps, Verifiable Expectations |
| Execution | Spawn one subagent per test or test suite |
| Fixing | Spawn SWE/BUILDER subagent if requested by user |
./tests/auth-integration.md)# Auth Integration Tests
## Prerequisites
- Start the test database: `docker compose up -d db`
- Run migrations: `npm run migrate`
- Start the server in background: `npm run start:test &`
## Test 1: User Registration
**Steps:**
1. Send a POST request to `/api/register` with payload `{"email": "test@example.com", "password": "pass"}`.
**Expectations:**
1. The HTTP response status must be `201 Created`.
2. A subsequent query to the database using `sqlite3 test.db "SELECT email FROM users WHERE email='test@example.com';"` must return the email.