菜单
Use when generating boilerplate code, __init__.py files, or test scaffolds. Provides scripts that generate consistent, convention-following code.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Reference for the Nomarr Docker development environment. Use when working with Docker containers, running e2e tests, querying ArangoDB directly, debugging prod-like issues, testing DB migrations, or interacting with the containerized Nomarr API. Contains credentials, ports, PowerShell snippets, AQL queries, and collection schema.
Generates a structured prompt for spawning Support-Librarian to gather relevant ADRs, logs, and design docs before a design, planning, or execution task. Use before starting any significant work — designing a feature, creating a plan, executing a plan, or reviewing code — to ensure prior decisions and dead ends are known. Trigger automatically in agents that have this skill, or manually when entering an unfamiliar area.
Fetch authoritative, up-to-date external documentation using Context7 MCP tools. Use proactively — without being asked — whenever writing or reviewing code that involves a third-party library or framework API (method signatures, config keys, behavior); a named library version (e.g., "Next.js 15", "React 19", "AWS SDK v3"); non-trivial configuration such as auth flows, crypto, or security-critical patterns; unfamiliar error messages from external tools; or any situation where guessing an API would be risky. Skip for purely local refactors and language fundamentals with no external dependencies.
Guide for building Python applications using the GitHub Copilot SDK. Use when integrating GitHub Copilot into Python apps: creating CopilotClient sessions, defining custom tools, handling streaming responses, managing session lifecycle, Pydantic parameter validation, BYOK (Bring Your Own Key) provider configuration, or any GitHub Copilot SDK API pattern. Requires Python 3.9+, asyncio, and GitHub Copilot CLI in PATH.
Use when executing implementation plans produced by the feature-planning skill. Orchestrates execution subagents (one plan phase at a time), dispatches review subagents for thorough quality enforcement after each plan, and manages fix cycles when review finds issues. Trigger when user says "execute the plans", "implement the feature", "work through the plans", or when validated plans exist in artifacts/plans/pending/TASK-*-{A..Z}-*.md and need implementation. Not for single-plan execution — use plan_complete_step directly for those.
Use when decomposing a major feature design into dependency-ordered implementation plans. Handles the full pipeline from design document to validated, cross-referenced plan files with minimal drift. Trigger when user mentions planning a large feature, breaking down a design doc into parts, creating implementation plans for multi-part work, or coordinating plans that span multiple sessions. Not for single plans or simple tasks — use the Plan subagent directly for those.
| name | code-generation |
| description | Use when generating boilerplate code, __init__.py files, or test scaffolds. Provides scripts that generate consistent, convention-following code. |
When to use: When creating new modules, updating exports, or scaffolding tests.
Purpose: Auto-generate __init__.py files with proper __all__ exports.
Use when:
Usage:
python scripts/generate_inits.py
How it works:
__init__.py with __all__ listing public exportsscripts/configs/generate_inits_config.ymlWhat it exports:
_*)Decision rule: After adding public functions to a module, run this to update exports.
Purpose: Generate test scaffolds with smart assertions and proper fixtures.
Use when:
Usage:
# Generate tests for a module
python scripts/generate_tests.py nomarr.services.domain.tagging_svc --output tests/unit/services/test_tagging_svc.py
# Preview without writing
python scripts/generate_tests.py nomarr.components.ml.ml_embed_comp --preview
# Specify layer for auto-fixture selection
python scripts/generate_tests.py nomarr.workflows.processing.process_file_wf --layer workflows
Generated tests include:
Create the module with your functions/classes
Update exports:
python scripts/generate_inits.py
Generate test scaffold:
python scripts/generate_tests.py nomarr.components.new_comp --output tests/unit/components/test_new_comp.py --preview
# If preview looks good:
python scripts/generate_tests.py nomarr.components.new_comp --output tests/unit/components/test_new_comp.py
Fill in test implementations
# After adding/removing public functions:
python scripts/generate_inits.py
# Review changes:
git diff nomarr/*/__init__.py
Located at scripts/configs/generate_inits_config.yml:
# Packages to scan
packages:
- nomarr.services
- nomarr.workflows
- nomarr.components
- nomarr.persistence
- nomarr.helpers
# Names to never export
banned_exports:
- TYPE_CHECKING
- annotations
generate_inits.py after adding public symbols — keeps exports consistent--preview before writing test files — verify structure is correct