Boot a full local Bag of Words sandbox (backend + frontend + real LLM), drive it end-to-end through the UI with Playwright, and verify behavior at the DB / backend-log / HTTP layers. Use when a change needs real e2e validation (agent context, chat flows, file uploads, LLM behavior) rather than just unit tests.
The English summary is being prepared. Showing the original description.
Query, visualize, and analyze data in a Bag of Words (BOW) workspace via the bagofwords MCP tools. Use for creating reports, running tracked queries, and building dashboards.
The English summary is being prepared. Showing the original description.
Add a new data source / connection type (e.g. a SQL Server-like database) end to end — client with get_schemas/execute_query, config + credentials schemas, registry entry, icon, tests — plus the verification steps. Also covers adding or updating an MCP connector (a preset, not a new type). Use when adding or significantly extending a connector.
The English summary is being prepared. Showing the original description.
Add a new LLM model to the preset catalog, or a whole new LLM provider — with the mandatory pre-flight verification of model id, pricing, and context window against the provider's official docs. Use when asked to add/update LLM models, providers, or pricing.
The English summary is being prepared. Showing the original description.
Update the product docs at docs.bagofwords.com (Mintlify) with text and fresh screenshots after a user-facing change ships. Use when a merged change alters user-visible behavior, adds a feature, or when asked to update/refresh documentation.
The English summary is being prepared. Showing the original description.
The locale/i18n architecture of bagofwords — catalogs, resolution order, RTL, backend contracts — and the procedures for adding strings, adding a locale, or translating UI. Use when adding/changing user-facing strings, working on RTL, emails, localized errors, or anything locale-related.
The English summary is being prepared. Showing the original description.
Run a live QA pass over the app — first map all user-facing functionality, then boot the full stack and manually exercise flows with Playwright, recording pass/fail evidence and filing a QA report. Use for release QA, post-merge smoke passes, or "QA the app / this area" requests.
The English summary is being prepared. Showing the original description.
Build or refresh a product README showcase using a seeded Bag of Words workspace, polished in-product screenshots, and repository-ready visual assets. Use when positioning has changed, README screenshots are stale, a launch/demo workspace is needed, or the user asks to populate agents, reports, dashboards, evals, automations, connectors, or monitoring for product storytelling.
The English summary is being prepared. Showing the original description.
Bump the version and write a CHANGELOG.md release-notes entry after a user-facing change ships. Use when asked to "bump the version", "cut a release", "add a changelog entry", or "write release notes". Produces one minimal, user-facing, technical bullet per change.
The English summary is being prepared. Showing the original description.
Build a runnable reproduce→fix→verify loop for a bug or feature in a fresh sandbox, and record it as a feedback-loop doc. Use when investigating a reported bug, validating a root cause, or proving a fix works — before and after the change.
The English summary is being prepared. Showing the original description.
Run a Snyk security scan of the repo (frontend npm deps, backend pip deps, Dockerfile/base image, and Snyk Code SAST), triage findings, and remediate the real ones with verified fixes. Use for "scan with Snyk", "resolve the security issues", dependency-CVE cleanup, or a pre-release security pass.
The English summary is being prepared. Showing the original description.
Exhaustively audit the UI control by control and role by role — enumerate every button, link, and input on a set of pages, write down what each is supposed to do (derived from the handler code and the RBAC matrix), then drive a real browser as each role and record what it actually does, filing every mismatch as a finding. Use whenever the user wants to hunt UI bugs broadly rather than fix one known bug — "go through every page and every button", "we have lots of weird UI bugs", "sweep the app for breakage", "check that these controls actually work", "verify what admins vs members can see", or when producing a bug inventory for triage.
The English summary is being prepared. Showing the original description.
Capture mandatory before/after screenshots (and videos/GIFs for flows) for any change touching UI/UX, and attach them to the PR. Use whenever a change touches frontend/pages, components, layouts, or assets.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)