ワンクリックで
verified-status-report
Generate a project status summary, verify all claims against ground truth, and correct before finalizing
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Generate a project status summary, verify all claims against ground truth, and correct before finalizing
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Full clean rebuild of ORBIS — wipes web/dist, dist-sdist, src-tauri bundle, staged sidecar binary, pyapp env cache, WKWebView state, sidecar.log, and stale unix sockets, then rebuilds frontend → sdist → pyapp sidecar → tauri bundle in the correct order, and launches with stderr captured. Use when voice doesn't work, the orb shows weird state, "Load failed" appears anywhere in the UI, or anything feels off after a code change.
Step-by-step workflow for adding a new processing component to the ORBIS agent pipeline
Step-by-step workflow for integrating a new stage into the ORBIS audio/processing pipeline
Integrate a new ML component (classifier, reranker, etc.) into an existing agent pipeline by reading the codebase, identifying hook points, implementing the module, and wiring it in.
Commit pending changes, bump the patch version tag, and publish a beta release
Scaffold and plan a new marketing site — branding audit, stack selection, hero design, and deployment config
| name | verified-status-report |
| description | Generate a project status summary, verify all claims against ground truth, and correct before finalizing |
When producing a status report, handoff document, or current-state summary where factual accuracy matters. Use any time a human or agent will act on the reported figures (test counts, PR states, version numbers, etc.).
pytest --collect-only -q | tail -1 and grep -r "^def test_" tests/ | wc -lgh pr list --state opengit describe --tagsfind or ls in the relevant directoryExample 1 — Test count correction:
Draft says "131 passing tests". Verification runs pytest --collect-only -q and gets 509 collected. Draft is corrected to "509 tests collected by pytest (461 test functions by grep)".
Example 2 — PR state correction:
Draft says "PR #30 is open". Verification runs gh pr list --state open and finds no open PRs. Draft is corrected to "No open PRs; PR #30 was previously merged."