zrwangems/dsh-zrwang-plugin / ars/skills/sr-screener
sr-screener
Flagged系统综述文献筛选:把方案或 PROSPERO 协议转成资格规则,双盲筛选标题摘要与全文,第三人裁决冲突,输出 PRISMA 2020 计数、EndNote/Zotero RIS 分组与可交付给论文技能的 literature_corpus。Triggers: systematic review screening, screen papers, PRISMA counts, pilot screening, adjudicate conflicts | 文献筛选, 系统综述筛选, PRISMA 计数, 筛选冲突裁决。
_shared/contracts/passport/constraint_violation.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/passport/constraint_violation.schema.json",
"title": "Material Passport Constraint Violation Entry",
"description": "One entry in Material Passport Schema 9 constraint_violations[] aggregate. Per uncited claim that violates a manifest negative constraint, emitted by claim_ref_alignment_audit_agent §4 step 5 stream (d). Rides in its own aggregate because constraint violations on uncited claims are real HIGH-WARN gate-refuse blockers, but claim_audit_result.ref_slug is required and uncited_assertion is LOW-WARN advisory only — routing through uncited_assertions[] would silently downgrade a HIGH-WARN signal; routing through claim_audit_result would require a sentinel ref_slug. Drives the [HIGH-WARN-CONSTRAINT-VIOLATION-UNCITED ({violated_constraint_id})] formatter annotation; gate-refuse at the formatter hard gate alongside the other four HIGH-WARN classes. Cross-field invariants CV-INV-1..CV-INV-4 are lint-enforced in scripts/check_claim_audit_consistency.py. See docs/design/2026-05-15-issue-103-claim-alignment-audit-spec.md §3.5.",
"type": "object",
"additionalProperties": false,
"required": [
"finding_id",
"claim_text",
"section_path",
"violated_constraint_id",
"scoped_manifest_id",
"judge_verdict",
"rationale",
"judge_model",
"judge_run_at",
"rule_version"
],
"properties": {
"finding_id": {
"type": "string",
"pattern": "^CV-[0-9]{3,}$",
"description": "Per-passport unique finding identifier for constraint_violations[]. CV-INV-1 enforces uniqueness."
},
"claim_text": { "type": "string", "minLength": 1, "maxLength": 2000 },
"section_path": {
"type": "string",
"minLength": 1,
"description": "Hierarchical path from document root to the section containing the offending sentence."
},
"violated_constraint_id": {
"type": "string",
"pattern": "^(NC-C[0-9]{3,}-[0-9]+|MNC-[0-9]+)$",
"description": "Identifier of the violated constraint. NC-C{n}-{m} = claim-level (per INV-17 canonical parse rule); MNC-{m} = manifest-level. CV-INV-2 enforces cross-array resolvability against the active manifest."
},
"scoped_manifest_id": {
"type": "string",
"pattern": "^M-[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z-[0-9a-f]{4}$",
"description": "Points to the claim_intent_manifest.manifest_id owning the violated constraint. Required (no MANIFEST-MISSING sentinel admitted — constraints require an active manifest to exist)."
},
"manifest_claim_id": {
"type": ["string", "null"],
"pattern": "^C-[0-9]{3,}$",
"description": "For NC-C{n}-{m} (claim-level constraint), the parent claim_id from the manifest. For MNC-{m} (global), null. CV-INV-3 enforces polarity match with the constraint id prefix."
},
"judge_verdict": {
"const": "VIOLATED",
"description": "Frozen literal: only VIOLATED outcomes from the §4 negative-constraint judge prompt emit an entry here. NOT_VIOLATED outcomes produce no entry."
},
"rationale": { "type": "string", "minLength": 1, "maxLength": 2000 },
"judge_model": { "type": "string", "minLength": 1 },
"judge_run_at": { "type": "string", "format": "date-time" },
"rule_version": {
"const": "D4-a-v1",
"description": "Frozen literal for the v3.8.0 release. Future rule revisions bump the constant and require re-lint."
},
"upstream_owner_agent": {
"enum": ["synthesis_agent", "draft_writer_agent", "report_compiler_agent", null]
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |