一键导入
oci-agent
oci-agent 收录了来自 Netflix-Skunkworks 的 5 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。
这个仓库中的 skills
Invoke this skill when making any modification to a notebook (.ipynb) in the OCI agent. Keywords: - .ipynb, Jupyter notebook - cell injection, comment-out cell - "# === INJECTED BY OCI AGENT === #" - "# === COMMENTED OUT BY OCI AGENT === #" - econml.ipynb, notebooks/ directory - parameterizing notebooks
Invoke this skill before executing any OCI analysis (notebook run). Keywords: - nb_runner.py, notebook execution - analysis spec, spec parameter injection - results.json, results serialization cell - .ipynb, notebooks/ directory - papermill-style parameterization
Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed. Keywords: - covariate balance failure, overlap warning, placebo warning - ATO_THRESHOLD, trimming extreme propensities - changing estimand: ATE → ATT, ATE → ATO - adding covariates, dataset insufficiency - actor-critic feedback loop, suggested spec changes
Invoke this skill when writing oci-report.md from an executed OCI analysis. Keywords: - oci-report.md, actor-critic report - results.json, analysis spec, analysis plan - diagnostics: covariate balance, overlap, placebo outcome - SMD, P1 confounders, propensity scores - ATE, ATT, ATO estimands - decision-grade results, diagnostic table
Invoke this skill when initiating an OCI analysis from a plan or user prompt — i.e. before any notebook is parameterized or executed. Keywords: - analysis spec, eval spec, spec.yaml - treatment, outcome, covariates, confounders - ATE, ATT, ATO, ato_threshold - econml.ipynb, analysis_notebook - ACIC, acic_treatment, acic_response