ce-reject-policy
Configure reject and defer decision policies and interpret RejectResult behavior in prediction and explanation flows.
npx skills add majiayu000/claude-skill-registry --skill ce-reject-policy --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# CE Reject Policy You are configuring reject / defer logic for production decision pipelines. Reject policies let the framework flag, skip, or selectively process instances where the model's prediction is ambiguous, novel, or uncertain — all without modifying the underlying model. **ADR reference**: ADR-029 (Reject Integration Strategy). Load `references/reject_policy_examples.md` for full code examples. --- ## The four policies ```python from calibrated_explanations.core.reject.policy import RejectPolicy ``` | Policy | Behaviour | |---|---| | `RejectPolicy.NONE` (default) | No reject logic. Returns the same type as without any policy. | | `RejectPolicy.FLAG` | Process ALL instances. Annotate rejected ones in `RejectResult.rejected`. | | `RejectPolicy.ONLY_REJECTED` | Process and return **only** rejected instances. | | `RejectPolicy.ONLY_ACCEPTED` | Process and return **only** accepted (non-rejected) instances. | **Legacy policy strings** (deprecated, emit `DeprecationWarning`): | Old name | Maps to | |---|---| | `"predict_and_flag"` / `"explain_all"` | `FLAG` | | `"explain_rejects"` | `ONLY_REJECTED` | | `"explain_non_rejects"` / `"skip_on_reject"` | `ONLY_ACCEPTED` | Use the enu
- The four policies
- RejectResult envelope
- Policy selection guide
- Out of Scope
- Evaluation Checklist
What does the ce-reject-policy skill do?
Configure reject and defer decision policies and interpret RejectResult behavior in prediction and explanation flows.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ce-reject-policy --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.