Menu
Semantic search over the retained OpenAgentd feature catalogue, ADRs, and repository instructions using the turbovec experiment index.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
OpenAgentd workflow for version bumps, release PRs, GitHub releases, and release notes.
Select and create accurate software architecture, workflow, interaction, data, state, and deployment diagrams.
OpenAgentd workflow for keeping the compact feature catalogue and README aligned with user-visible changes.
Research first, propose a step-by-step implementation plan, and wait for explicit approval before writing any code.
OpenAgentd TDD workflow โ 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.
OpenAgentd testing reference โ 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 oad/test-driven-development instead.
| name | oad/search-doc |
| description | Semantic search over the retained OpenAgentd feature catalogue, ADRs, and repository instructions using the turbovec experiment index. |
Search documents/ semantically only for product-capability, decision-rationale, or repository-policy questions. The codebase, tests, CLI help, and UI are authoritative for implementation and operation; use grep, glob, and source reads for those questions.
This wraps the experiment at experiments/turbovec_docs/ (turbovec index + local sentence-transformers embeddings). Reuse the index when current; rebuild it only after the retained Markdown corpus changes.
ls experiments/turbovec_docs/index/docs.tvim 2>/dev/null
documents/ has changed since the last build, rebuild it:uv run --group experiment python experiments/turbovec_docs/build_index.py
The corpus is intentionally small: feature catalogue, ADRs, and repository instructions. Rebuild whenever it might be stale rather than treating old search results as authoritative.
uv run --group experiment python experiments/turbovec_docs/search.py "<query>" -k 5
-k controls result count (default 5); lower it when one clear result is expected.experiments/turbovec_docs/README.md describes the experimental index and its limitations.experiment uv dependency group is dev/local-only; never assume it exists outside this workspace.