submit
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "submit":https://skillpi.com/zh/skills/deepskill-2f78ee7dc4650131cab9197a590af538dc785a9e8f63df65d1086ceea43f4404。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/41-sticerd-eee-sewage-econometrics-check/skills/submit/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/41-sticerd-eee-sewage-econometrics-check/skills/submit --skill submit来源与配置
查看 GitHub 源码brycewang-stanford/Auto-Empirical-Research-Skills固定提交 bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目面向文献与学术工具场景,提供“submit”技能的目录入口。公开标签:learning、论文投稿、学术审核、复制性审计。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。
文件浏览
--- name: submit description: Final submission verification gate for the sewage-house-prices paper. Runs full paper excellence review, replication audit, enforces score gates, and generates cover letter draft and submission checklist. This skill should be used when asked to "submit", "prepare for submission", or "submission checklist". argument-hint: "[journal name (optional)]" allowed-tools: ["Read", "Grep", "Glob", "Write", "Bash", "Agent"] --- # Submit Final submission gate combining full verification, score enforcement, and submission checklist. **Input:** `$ARGUMENTS` — target journal name (optional). --- ## Workflow ### Step 1: Pre-Flight Checks 1. Verify manuscript exists at `docs/overleaf/_main.tex` 2. Check for existing quality reports in `output/log/` 3. Verify analysis outputs exist in `output/tables/` and `output/figures/` 4. Check `Replication/` directory exists (if not, flag for `/data-deposit`) ### Step 2: Run Full Verification If `/paper-excellence` hasn't been run recently (check report dates in `output/log/`): - Run the full paper excellence review (econometrics, code, paper, bibliography) ### Step 3: Run Replication Audit If `Replication/` exists: - Run `/audit-replication Replication/` ### Step 4: Score Gate Check against thresholds: | Requirement | Threshold | Status | |-------------|-----------|--------| | Aggregate score | >= 90 | PASS/FAIL | | Econometrics component | >= 80 | PASS/FAIL | | Code component | >= 80 | PASS/FAIL | | Paper component | >= 80 | PASS/FAIL | | Replication (if exists) | >= 8/10 checks | PASS/FAIL | **If any requirement FAILS:** List specific blocking issues and stop. Do not generate submission materials. ### Step 5: Generate Submission Package If all gates pass: 1. **Cover letter draft** (save to `output/log/cover_letter_[journal]_[date].tex`): - Addressed to current editor - 1 paragraph: what the paper does (sewage spill capitalisation using EDM data) - 1 paragraph: why this journal (fit with environmental/housing economics) - 1 paragraph: originality confirmation - Suggested referees (3-5, from `/target-journal` if available) 2. **Final checklist** (save to `output/log/submission_checklist_[date].md`): ```markdown # Submission Checklist: [Journal] ## Manuscript - [ ] Title page with affiliations and contact info - [ ] Abstract within word limit - [ ] JEL codes (2-3): Q53, R31, Q58 - [ ] Keywords: sewage spills, house prices, hedonic pricing, environmental disamenity, EDM - [ ] Journal formatting guidelines followed ## Data and Code - [ ] Replication package assembled - [ ] Data availability statement in manuscript - [ ] Restricted data flagged (Land Registry, Zoopla) ## Quality Gates - [ ] Aggregate score: XX/100 (>= 90 required) - [ ] All components >= 80 - [ ] No unresolved CRITICAL issues ## Submission - [ ] Upload manuscript PDF - [ ] Upload replication package (if required) - [ ] Upload cover letter - [ ] Submit via [portal] ``` ### Step 6: Present Results ```markdown # Submission Report **Date:** YYYY-MM-DD **Target Journal:** [name] **Aggregate Score:** XX/100 ## Gate Status: [PASS / FAIL] | Component | Score | Threshold | Status | |-----------|-------|-----------|--------| | Aggregate | XX | >= 90 | ... | | Econometrics | XX | >= 80 | ... | | Code | XX | >= 80 | ... | | Paper | XX | >= 80 | ... | | Replication | X/10 | >= 8/10 | ... | ## Generated Materials - Cover letter: output/log/cover_letter_*.tex - Checklist: output/log/submission_checklist_*.md ## Remaining Steps (manual) 1. Review and customise cover letter 2. Upload to [submission portal] 3. Enter suggested referees 4. Submit ``` --- ## Principles - **This is the final gate.** Score >= 90 with all components >= 80. - **If it fails, stop.** List blocking issues. Don't generate submission materials for a failing paper. - **Cover letter is a draft.** The user must review and customise before sending. - **Manual submission.** This skill prepares materials but does NOT submit to journals. - **Be realistic.** If the paper isn't ready, say so clearly.
版本历史
-
v2026.07
GitHub ↗
原版更新说明
## Highlights - **First tagged release.** Every gate is green: `make check` (validate + 183 unit tests + eval-harness + numeric benchmarks), validate-catalog, quality-evals, and OpenSSF Scorecard on `main`. - **Rigor double loop at 13 method families.** Each family closes taxonomy tag → eval scenario (does the agent avoid the method's known traps?) → deterministic numeric benchmark (does it recover the true effect?). New this cycle: heterogeneous treatment effects (CATE) and quantile treatment effects (QTE). - **Paper-WorkFlow flagship at 29/29 executable rigor gates**, now merged to its `main` with a drift-gated README badge — the credibility artifact is checked by CI, so it can never silently go stale ([RIGOR.md](https://github.com/brycewang-stanford/Paper-WorkFlow/blob/main/RIGOR.md)). - **1,150 vendored skills / 69 collections**, all license-audited, security-scanned, tracked in a machine-readable catalog with CI-enforced freshness, and importable as a single whole-repo router skill. - **Hardened weekly upstream syncs**: synced trees must pass the full gate before merge; this cycle both sync PRs were verified, patched (StatsPAI's SkillOpt execution-gate card restored), and merged. - **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version. ## Known Follow-Ups - Ecosystem benchmark comparison (AERS vs econometrics agents on the shared benchmark suite) — [PLAN-2026-07 week 3](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/main/docs/PLAN-2026-07.md). - Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4). - GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4). ## Catalog - Top-level collections: **69** - `SKILL.md` files: **1150** - Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md)) ## Methodological rigor - Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md)) - Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md)) - Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md)) ### Method families (skills tagged) - `iv`: 27 - `rdd`: 25 - `panel-fe`: 19 - `staggered-did`: 17 - `bayesian`: 13 - `did`: 10 - `event-study`: 10 - `matching`: 10 - `synthetic-control`: 10 - `cate`: 8 - `dml`: 8 - `survival`: 3 - `quantile`: 2 ### Eval scenarios by category - `causal-identification`: 14 - `citation-hygiene`: 1 - `reproducibility`: 2 - `research-integrity`: 1 - `runtime-safety`: 1 - `statistical-validity`: 2 - `writing-compliance`: 3 - `writing-style`: 2 ## License buckets - AGPL-3.0: 1 - Apache-2.0: 1 - CC-BY-NC-4.0 (non-commercial): 1 - CC-BY-SA-4.0: 1 - CC-BY-SA-4.0 (repository default): 4 - GPL-3.0: 1 - MIT: 35 - MIT Non-Commercial: 1 - Mixed (per-skill; see folder): 2 - UNKNOWN - check upstream: 22 ## Quality gates - `make check` — catalog/provenance/audit/eval freshness, repo hygiene, Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke, and the strict numeric benchmark (reference-gold drift fails the build). - External links and OpenSSF Scorecard run on their scheduled workflows.
当前收录版本
0.0.1
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
面向学术研究场景,提供论文提交前的全面验证和投稿材料生成
评分依据
核心触发词'submit'、'准备投稿'、'提交清单'覆盖合理,边界清晰
评分依据
Phase/步骤清晰,有明确的出口条件和端到端示例
评分依据
工具来源明确,参数正确,覆盖主要异常情况
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。