zrwangems/dsh-zrwang-plugin / ars/skills/deep-research
deep-research
Flagged学术研究前置:把模糊想法收敛成可研究的问题,并做文献综述、事实核查、系统综述(PRISMA)与三向文献扫描。Triggers: research, deep research, literature review, systematic review, meta-analysis, PRISMA, fact-check, guide my research | 研究, 文献综述, 系统性文献回顾, 事实核查, 引导我研究, 帮我确定研究问题。输出 RQ Brief、方法论蓝图、带核验的注释书目。
_shared/contracts/passport/claim_drift.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/claim_drift.schema.json",
"title": "Material Passport Claim Drift Entry",
"description": "One entry in Material Passport Schema 9 claim_drifts[] aggregate. Per claim-intent-drift finding emitted by claim_ref_alignment_audit_agent §4 step 5 manifest set-diff. Rides in its own aggregate because claim-intent drift is detected by manifest set-diff (intended ≠ emitted), NOT by judge invocation — embedding drift findings as a defect_stage of claim_audit_result would force judgment=UNSUPPORTED to be recorded without the judge ever evaluating that claim, contaminating both the schema semantics and the calibration FNR/FPR metrics. Always LOW-WARN advisory at the finalizer (per D4-a — gate-refuse is reserved for explicit author negative constraints, not drift signals). Cross-field invariants D-INV-1..D-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 §3.4.",
"type": "object",
"additionalProperties": false,
"required": [
"finding_id",
"drift_kind",
"claim_text",
"detected_at",
"rule_version"
],
"properties": {
"finding_id": {
"type": "string",
"pattern": "^CD-[0-9]{3,}$",
"description": "Per-passport unique finding identifier for claim_drifts[]. D-INV-1 enforces uniqueness."
},
"drift_kind": {
"enum": ["EMITTED_NOT_INTENDED", "INTENDED_NOT_EMITTED"],
"description": "EMITTED_NOT_INTENDED: an emitted claim that was not in the manifest (the drafted prose introduced a claim the writer did not pre-commit to). INTENDED_NOT_EMITTED: a manifest claim that did not appear in the emitted prose (the writer dropped a pre-committed claim during drafting). Both are advisory — gate-refuse is reserved for negative_constraint_violation."
},
"claim_text": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "For EMITTED_NOT_INTENDED, the emitted sentence; for INTENDED_NOT_EMITTED, the manifest claim_text."
},
"manifest_claim_id": {
"type": ["string", "null"],
"pattern": "^C-[0-9]{3,}$",
"description": "For INTENDED_NOT_EMITTED, the dropped manifest claim_id (REQUIRED, conditional on drift_kind — enforced by D-INV-2). For EMITTED_NOT_INTENDED, null (drifted claim has no manifest_claim_id since it was never in the manifest). When present, MUST be paired with scoped_manifest_id."
},
"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. Required when drift_kind=INTENDED_NOT_EMITTED (paired with manifest_claim_id per D-INV-2 cross-array integrity, disambiguating C-001 collision across manifests). Null when drift_kind=EMITTED_NOT_INTENDED (the drifted claim has no manifest origin)."
},
"section_path": {
"type": ["string", "null"],
"minLength": 1,
"description": "For EMITTED_NOT_INTENDED, hierarchical path from document root to the section containing the drifted sentence (mirrors uncited_assertion.section_path). Null for INTENDED_NOT_EMITTED (dropped claim has no draft location)."
},
"detected_at": { "type": "string", "format": "date-time" },
"rule_version": {
"const": "D4-a-v1",
"description": "Frozen literal for the v3.8.0 release. D-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]
}
}
}
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 |