一键导入
project-initializer
Initializer agent for the project-level harness — turn a spec or issue into feature_list.json, init.sh, verify.yaml, and an initial commit.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Initializer agent for the project-level harness — turn a spec or issue into feature_list.json, init.sh, verify.yaml, and an initial commit.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | project-initializer |
| description | Initializer agent for the project-level harness — turn a spec or issue into feature_list.json, init.sh, verify.yaml, and an initial commit. |
| requires_tools | ["project_init","project_status","progress_append","bash_exec","file_read","file_write"] |
Use exactly once per project, when session_mode == feature_loop and .agx/project/ does not yet exist (system prompt will say "Initializer 阶段").
workspace_dir or first non-default taskspace).file_read if the user pointed at a file, otherwise capture the user's message as the source of truth.id (kebab-case, ≤ 32 chars),acceptance_criteria (observable behavior, not implementation steps),depends_on only for hard ordering constraints,priority (lower = sooner; reserve 100 for "later").project_init with the full feature list. The tool writes feature_list.json, seeds status.json with phase=initialize, and drops template init.sh + verify.yaml.init.sh via bash_exec (or file_write with the diff path = .agx/project/init.sh):
verify.yaml with the project's real test/lint commands. Keep the bootstrap step that runs init.sh.verify_run (no feature_id) to confirm the initial gate is green on a clean checkout.bash_exec:
git add .agx/project init.sh verify.yaml
git commit -m "chore(project): initialize harness with N features"
Keep this commit small — only harness files, no business code.progress_append (e.g. "[initialize-done] commit=<sha> features=N") and tell the user the project is ready for a Coding session.init.sh or verify.yaml.Guide for creating persistent Near desktop digital avatars (数字分身) via natural-language interview and the create_avatar tool. Use when the user wants to create an avatar, digital twin, specialist agent persona, or add someone to the avatar sidebar.
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.
Generate modern B2B desktop design system specs — tokens, layout, information hierarchy — for Near delivery POC.
Generate Playwright UI tests and visual smoke reports for delivery POC frontends.
Decompose customer RFP materials into pages, interactions, and acceptance criteria for Near delivery loop.
Scaffold Vite + React POC frontend in delivery worktree output directory.