zrwangems/dsh-zrwang-plugin / ars/skills/academic-paper
academic-paper
Flagged学术论文写作:按 IMRaD 或领域结构成稿,含大纲、论证地图、双语摘要、图表与题注、引用格式转换、返修与逐条回复、AI 使用声明。Triggers: write a paper, academic paper, paper outline, revise paper, reviewer comments, rebuttal, citation check, abstract | 写论文, 论文大纲, 修改论文, 审稿意见, 返修, 审稿回复, 引文核对, 写摘要。
_shared/contracts/passport/uncited_assertion.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/uncited_assertion.schema.json",
"title": "Material Passport Uncited Assertion Entry",
"description": "One entry in Material Passport Schema 9 uncited_assertions[] aggregate. Per uncited-assertion finding emitted by claim_ref_alignment_audit_agent §4 step 6 (D4-c three-condition token rule). Rides in its own aggregate because the finding has no ref_slug to evaluate — embedding it in claim_audit_result would either force a sentinel ref_slug value or relax claim_audit_result.required, both fighting that schema's grain. Always LOW-WARN advisory at the finalizer; gate-refuse is reserved for citation-level defects and constraint_violation. Cross-field invariants U-INV-1..U-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 §3.3.",
"type": "object",
"additionalProperties": false,
"required": [
"finding_id",
"sentence_text",
"section_path",
"trigger_tokens",
"detected_at",
"rule_version"
],
"properties": {
"finding_id": {
"type": "string",
"pattern": "^UA-[0-9]{3,}$",
"description": "Per-passport unique finding identifier for uncited_assertions[]. U-INV-1 enforces uniqueness."
},
"sentence_text": { "type": "string", "minLength": 1, "maxLength": 2000 },
"section_path": {
"type": "string",
"minLength": 1,
"description": "Hierarchical path from document root to the section containing the sentence, e.g. '2. Methods > 2.3 Sampling'."
},
"trigger_tokens": {
"type": "array",
"minItems": 1,
"items": { "type": "string" },
"description": "Concrete tokens that matched D4-c condition 1 (quantifiers or empirical-claim verbs). E.g. ['67%', 'showed']. U-INV-2 enforces non-empty."
},
"detected_at": { "type": "string", "format": "date-time" },
"rule_version": {
"const": "D4-c-v1",
"description": "Frozen literal for the v3.8.0 release. U-INV-3 enforces equality. Future rule revisions bump the constant and require re-lint."
},
"upstream_owner_agent": {
"enum": ["synthesis_agent", "draft_writer_agent", "report_compiler_agent", null]
},
"manifest_claim_id": {
"type": ["string", "null"],
"pattern": "^C-[0-9]{3,}$",
"description": "When the uncited sentence corresponds to a claim_id in the active claim_intent_manifest. Per D4-c last paragraph: manifest membership does NOT exempt a sentence from being flagged. When present, MUST be paired with scoped_manifest_id to disambiguate against C-001 collision across manifests."
},
"scoped_manifest_id": {
"type": ["string", "null"],
"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 referenced manifest_claim_id. The (scoped_manifest_id, manifest_claim_id) pair uniquely identifies which manifest's claim this uncited finding corresponds to, since C-001 may collide across manifests in the same passport. Required when manifest_claim_id != null (U-INV-4 cross-array integrity). Null when manifest_claim_id is null (the uncited sentence does not correspond to any manifest claim)."
}
}
}
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 |