lthoangg/OpenAgentd

self-healing

Update or upgrade the agent's own configuration on request — swap the model, add tools or MCP servers, change the image-generation provider/model, or install a new skill. Use when the user says things like "upgrade yourself", "switch your model to X", "use…

لغة النص الأصلي: الإنجليزية

oad-testing

OpenAgentd testing reference — environment setup, run commands, and fix patterns for backend (pytest) and frontend (Bun/RTL). Load this for running, fixing, or adding coverage to existing tests. For writing a failing test before new code, use…

لغة النص الأصلي: الإنجليزية

oad-debug

OpenAgentd workflow for investigating bugs, regressions, sessions, and runtime issues.

لغة النص الأصلي: الإنجليزية

oad-debug-prod

Workflow and patterns for inspecting, analyzing, and diagnosing production logs and OTEL telemetry in OpenAgentd.

لغة النص الأصلي: الإنجليزية

skill-installer

Install new skills into the agent's skills directory by fetching from a URL or writing from scratch.

لغة النص الأصلي: الإنجليزية

oad-test-driven-development

OpenAgentd TDD workflow — write a failing test before the code that makes it pass, reproduce a bug with a test before fixing it. Use when implementing any logic, fixing any bug, or changing any existing behavior in backend (pytest) or frontend (Bun/RTL) code.

لغة النص الأصلي: الإنجليزية

oad-docs

OpenAgentd workflow for keeping the compact feature catalogue and README aligned with user-visible changes.

لغة النص الأصلي: الإنجليزية

oad-plan

Research first, propose a step-by-step implementation plan, and wait for explicit approval before writing any code.

لغة النص الأصلي: الإنجليزية

oad-release

OpenAgentd workflow for version bumps, release PRs, GitHub releases, and release notes.

لغة النص الأصلي: الإنجليزية

oad-search-doc

Semantic search over the retained OpenAgentd feature catalogue and repository instructions using the turbovec experiment index.

لغة النص الأصلي: الإنجليزية

oad-diagram

Select and create accurate software architecture, workflow, interaction, data, state, and deployment diagrams.

لغة النص الأصلي: الإنجليزية

guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

لغة النص الأصلي: الإنجليزية

oad-commit

OpenAgentd workflow for well-formatted, detailed conventional commits.

لغة النص الأصلي: الإنجليزية

oad-review

OpenAgentd five-axis code review workflow — correctness, readability, architecture, security, performance. Use before merging any change, before opening a PR, or when asked to review a diff.

لغة النص الأصلي: الإنجليزية