メニュー
Sub-skill of agent-teams: Workspace Work Profile (Updated 2026-03-10).
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/vamseeachanta/workspace-hub --skill agent-teams-workspace-work-profile-updated-2026-03-10コマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
SOC 職業分類に基づく
SKILL.md を表示中
| name | agent-teams-workspace-work-profile-updated-2026-03-10 |
| description | Sub-skill of agent-teams: Workspace Work Profile (Updated 2026-03-10). |
| version | 1.0.0 |
| category | workspace-hub |
| type | reference |
| scripts_exempt | true |
This workspace is engineering-heavy with sequential solver pipelines. Most work does NOT benefit from teams. Use this table before spawning:
| Work Type | Team Useful? | Notes |
|---|---|---|
| OrcaWave/AQWA solver runs | No | Sequential: mesh → solve → validate → report |
| WRK item staged pipeline | No | Each stage depends on previous stage output |
| Cross-review (Codex/Codex/Gemini) | No | Already scripted via cross-review.sh |
| L01–L06 validation cases | Maybe | Cases are independent — 2-3 agents viable |
| Multi-repo exploration | Maybe | Parallel file reads across submodules |
| Documentation/reporting | No | Single-pass generation |
| Bulk transforms (50+ files) | Yes | One agent per batch |
Key insight: The biggest efficiency gain in this workspace comes from better WRK scoping (1-2 goals per session), not from parallelising with teams. Use teams only when tasks are genuinely independent AND > 20 min each.