zrwangems/dsh-zrwang-plugin / ars/skills/academic-pipeline
academic-pipeline
Flagged学术研究总编排:研究→写作→诚信检查→评审→返修→复审→终检→定稿的十阶段流水线,每阶段停在用户确认点,含材料护照与 7 类 AI 研究失败模式检查。Triggers: academic pipeline, research to paper, full paper workflow, end-to-end paper | 完整论文流程, 从研究到论文, 端到端写论文, 论文流水线。
_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 |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |