BF stata-econ-workflow
完整实证研究工作流管理技能。整合 codex-stata-for-economists 的工程化方法论与 Stata-MCP 执行工具。 使用场景：(1) Stata do-file 编写、调试、执行与优化 (2) 实证研究流水线搭建与项目管理 (3) 论文结果复现与审查（replication/robustness）(4) 计量经济学方法选择与实现 (5) 研究日志溯源校验（log verification）(6) 提交前质量审核与评分 当用户提到以下关键词时触发：stata, do文件, do-file, dofile, dta, 面板数据, panel, did, 双重差分, 倍分法, 事件研究, event study, rd, 断点回归, iv, 工具变量, psm, 倾向得分, 合成控制, synth, ddml, 复现, replication, 实证, emprical, 科研, 计量, 计量经济学, 回归, regress, reghdfe, esttab, 系数, 标准误, p值, 置信区间, clustered SE, 聚类标准误, 固定效应, fixed effect, FE, 效能评估, 质量评分, quality, verify, log, 日志, 代码审查, study, paper, 模板, template, pipeline, workflow, 研究流程, 研究框架, do文件, 论文复现, 审稿, 论文发表, 研究设计, 方法选择, 因果推断, causal inference, 差分法, triple diff, DDD, 三重差分, 平行趋势, parallel trend, 安慰剂检验, placebo 不用于：与Stata/实证研究/计量经济学分析无关的通用对话。
完整实证研究工作流管理技能。整合 codex-stata-for-economists 的工程化方法论与 Stata-MCP 执行工具。 使用场景：(1) Stata do-file 编写、调试、执行与优化 (2) 实证研究流水线搭建与项目管理 (3)…
As a process F 33/100 · Will not run — References files that are not bundled: templates/master-do-template.do, templates/did-analysis-template.do, templates/ddml-analysis-template.do
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: templates/master-do-template.do - warning
missing-refreference to a missing file: templates/did-analysis-template.do - warning
missing-refreference to a missing file: templates/ddml-analysis-template.do
Process rating: all ten parameters 33/100
- 0Tools and files. 3 referenced file(s) missing: templates/master-do-template.do, templates/did-analysis-template.do, templates/ddml-analysis-template.do
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (stata-econ-workflow) differs from the folder (stata-econ-workflow-publish)
- 100Steps. 4 steps
- 100Execution cost. Instruction body is 824 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 768: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.