By gao-hongnan
Python conventions: NumPy/Sphinx docstrings + strict typing + performance rules
Use when writing or reviewing Python docstrings for public modules, classes, functions, methods, properties, generators, overloads, doctest examples, or generated Sphinx API documentation, especially when choosing NumPy vs Sphinx style or deciding which Parameters, Returns, Yields, Raises, Warns, Attributes, Notes, See Also, and Examples sections belong.
Use when Python code may fail at scale: profiling hot paths, memory pressure, unbounded async fan-out, backpressure, queue design, hidden materialization, cache growth, expensive logging, timeouts, cancellation, cProfile, tracemalloc, or performance reviews that need measurement before refactoring.
Use when writing or reviewing modern Pydantic v2 or pydantic-settings code: BaseModel boundaries, SettingsConfigDict, BaseSettings, nested environment configuration, Annotated Field constraints, validators, computed fields, TypeAdapter, RootModel, discriminated unions, SecretStr, serialization, or production validation patterns.
Use when writing or reviewing Python 3.14+ with strict type-safety enforced: generics with PEP 695 syntax, annotationlib / deferred annotations, Protocol vs ABC, ParamSpec decorators, TypeIs / TypeGuard narrowing, TypedDict / ReadOnly, Literal vs StrEnum, NewType vs aliases, or any time mypy / pyright / pyrefly / ty is configured, run, or failing.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin suite — coding conventions, design patterns, and MCP server integrations packaged as installable skills.
| Plugin | Type | Skills | Requires |
|---|---|---|---|
omniagents-python | Skills | omniagents-python:typings, omniagents-python:docstrings, omniagents-python:performance | — |
omniagents-typescript | Skills | omniagents-typescript:typings, omniagents-typescript:docstrings | — |
omniagents-design-patterns | Skills | omniagents-design-patterns:software, omniagents-design-patterns:system | — |
omniagents-writing | Skills | omniagents-writing:measured-persuasion, omniagents-writing:markdown-conventions | — |
code-review-graph | MCP (stdio) | Tree-sitter knowledge graph tools | uv on PATH |
context7 | MCP (HTTP) | Library documentation lookup | CONTEXT7_API_KEY |
claude --versioncode-review-graph: uv installed — uvx --versioncontext7: a Context7 API key from https://context7.com/dashboardclaude plugin marketplace add gao-hongnan/omniagents
Or from inside Claude Code:
/plugin marketplace add gao-hongnan/omniagents
Install individually:
claude plugin install omniagents-python@omniagents
claude plugin install omniagents-typescript@omniagents
claude plugin install omniagents-design-patterns@omniagents
claude plugin install omniagents-writing@omniagents
claude plugin install code-review-graph@omniagents
claude plugin install context7@omniagents
| Flag | Effect |
|---|---|
| (none) | User scope — available across all projects |
--scope project | Project scope — committed to .claude/, shared |
--scope local | Local scope — gitignored, machine-local only |
Example — install omniagents-python for the whole team:
claude plugin install omniagents-python@omniagents --scope project
If a plugin is already installed, running claude plugin install ... again is
expected to report that it is already installed. Install is not the update
path.
Marketplace update only refreshes the catalogue; it does not install plugins that are not already installed.
Refresh the marketplace, then update the installed plugin:
claude plugin marketplace update omniagents
claude plugin update omniagents-python@omniagents
claude plugin update omniagents-typescript@omniagents
claude plugin update omniagents-design-patterns@omniagents
claude plugin update omniagents-writing@omniagents
claude plugin update code-review-graph@omniagents
claude plugin update context7@omniagents
Inside Claude Code, the equivalent commands are:
/plugin marketplace update omniagents
/plugin update omniagents-python@omniagents
/plugin update omniagents-typescript@omniagents
/reload-plugins
Claude Code uses the plugin version as the cache key. Because these plugins set
version in each .claude-plugin/plugin.json, maintainers must bump that
version whenever published skill contents change. Pushing new commits without a
version bump will make updates look current to already-installed users. For
fast-moving internal plugins, omit version from both plugin.json and the
marketplace entry so Claude Code uses the git commit SHA as the version.
The default scope is user. A bare uninstall command removes from user scope
without needing a flag. Add --prune to also drop any orphaned auto-installed
dependencies left behind:
claude plugin uninstall omniagents-python@omniagents --prune
claude plugin uninstall omniagents-typescript@omniagents --prune
claude plugin uninstall omniagents-design-patterns@omniagents --prune
claude plugin uninstall omniagents-writing@omniagents --prune
claude plugin uninstall code-review-graph@omniagents --prune
claude plugin uninstall context7@omniagents --prune
If the plugin was installed with a non-default scope, pass the matching
--scope flag:
claude plugin uninstall omniagents-python@omniagents --scope project --prune
claude plugin uninstall omniagents-python@omniagents --scope local --prune
npx claudepluginhub gao-hongnan/omniagents --plugin omniagents-pythonCode Review Graph MCP: tree-sitter knowledge graph tooling for impact analysis and structural review
Context7 MCP: up-to-date documentation lookup for libraries and frameworks via Upstash's hosted endpoint
TypeScript conventions: TSDoc + strict typing rules
Make your AI agent code with your project's architecture, rules, and decisions.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.