chengzicv/chengzicv-career-skills / chengzicv-case-factory
chengzicv-case-factory
Verified为指定岗位与职级生成独立披露的虚拟简历及岗位入门。虚拟简历的写法、结构、个人优势、篇幅、标点和事实纪律全部沿用 chengzicv-resume;本 Skill 只负责虚拟案例设定、岗位研究、岗位入门与批次生产。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.4 KB |
| agents/openai.yaml | config | 610 B |
| onboarding/core-introduction.md | markdown | 744 B |
| references/batch-planning.md | markdown | 2.3 KB |
| references/depth-calibration.md | markdown | 980 B |
| references/examples/product-assistant-job-guide.md | markdown | 9.2 KB |
| references/examples/supply-chain-specialist-job-guide.md | markdown | 12.1 KB |
| references/gold-standard.md | markdown | 1.6 KB |
| references/legacy-manifest-schema.md | markdown | 8.0 KB |
| references/manifest-schema.md | markdown | 5.5 KB |
| references/product-boundary.md | markdown | 2.0 KB |
| references/production-contract.md | markdown | 3.7 KB |
| references/quality-gates.md | markdown | 4.1 KB |
| references/user-case-pack.md | markdown | 2.9 KB |
| references/virtual-case-design.md | markdown | 5.3 KB |
| references/virtual-experience-design.md | markdown | 4.6 KB |
| scripts/case_manifest.py | script | 43.5 KB |
| scripts/test_case_manifest.py | script | 6.4 KB |
references/batch-planning.md
View on GitHub# 批次选题与逐岗审核
## 范围与计划
用户给定的专业与岗位按明确组合处理,不默认全排列。数量与范围已确认就不反复问。先新建批次目录与计划,默认每岗一份虚拟简历和一篇岗位入门。
批次默认一次制作一岗,交齐两份、自查、提交用户 check;用户通过后才进入下一岗。修改意见落实当前岗,并成为后续偏好。用户明确授权连续生产时依其要求,不用本规则制造额外确认。
## 选题与差异
公开 JD 确定职级、企业、对象、动作、协作者及入门门槛。内部记录岗位与别名、来源、贯穿任务、个人职责、感受、相近岗位、经营或自主项目及可用材料。
各岗在工作对象、需求方、关键判断、资源约束、协作和结果上应有差异。经营项目不是统一“校园开店”模板;专业限制决定能做什么,不因无法制作桌面作品集就排除复杂岗位。
已有确认稿只复用岗位研究、事实深度和岗位文章口气;旧简历版式不复用,虚拟简历一律按 `../../chengzicv-resume/SKILL.md` 的当前标准重写。不因确认过一岗就默认批准其余岗位正文。
## 简历标准
虚拟简历不在此文件定义写法。动笔前按 SKILL.md「唯一简历标准」读取 `../../chengzicv-resume/SKILL.md`,以及 `../../chengzicv-resume/references/` 下的 `plainspoken-resume-style.md`、`advantage-block.md`、`evidence-safeguard.md`、`one-page-markdown-rules.md`。本批次只负责岗位选择、事实设定、双稿一致和逐岗审核。
## 内部进度
沿用 job_guide 清单兼容层,当前新批次显式要求 `job_guide` 与 `virtual_resume` 两份交付。文章登记在 `outputs.job_guide`,虚拟简历登记在 `additional_deliverables.virtual_resume`。完成 self-audit 前必须两份都存在。具体见 `manifest-schema.md`。
`status=complete` 只表示制作与自查完成,`user_review.approved=true` 才表示用户通过。批次逐岗审核时,前岗未通过不得推进下一岗的 research 或写作;不得自动填写用户认可。
旧文章单交付批次不自动迁移;用户追加简历时显式登记新的必交项,保留原稿和用户改动。不恢复 legacy_deep 四件套。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |