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/audit/audit_verdict.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/audit/audit_verdict.schema.json",
"title": "Codex Audit Verdict File",
"description": "Schema for <run_id>.verdict.yaml — the human-readable verdict file produced by the wrapper after parsing the JSONL stream's single item.completed.agent_message event (per §3.3 / §3.5). This is the policy surface the orchestrator reads for ship/block decisions; JSONL is raw evidence (Layer 2) and sidecar is environmental evidence (Layer 3). Cross-field invariants (PASS/MINOR/MATERIAL/AUDIT_FAILED count consistency; finding_counts agrees with findings[]) are lint-enforced in scripts/check_audit_artifact_consistency.py (Phase 6.3 §3.7 family A rows A1/A2/A5/A6) — this schema enforces the per-file shape so wrapper-side lint can reject malformed verdicts before they reach the orchestrator.",
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"verdict_status",
"round",
"target_rounds",
"finding_counts",
"findings",
"generated_at",
"generated_by",
"generator_version"
],
"properties": {
"run_id": { "$ref": "#/$defs/run_id" },
"verdict_status": {
"type": "string",
"enum": ["PASS", "MINOR", "MATERIAL", "AUDIT_FAILED"],
"description": "Three completion states + AUDIT_FAILED for wrapper-side aborts (§4.6). Cross-field consistency with finding_counts and failure_reason is lint-enforced (§3.7 A1/A2)."
},
"round": { "type": "integer", "minimum": 1 },
"target_rounds": { "type": "integer", "minimum": 1 },
"finding_counts": {
"type": "object",
"additionalProperties": false,
"required": ["p1", "p2", "p3"],
"properties": {
"p1": { "type": "integer", "minimum": 0 },
"p2": { "type": "integer", "minimum": 0 },
"p3": { "type": "integer", "minimum": 0 }
}
},
"findings": {
"type": "array",
"items": { "$ref": "#/$defs/finding" },
"description": "May be []. When verdict_status == 'AUDIT_FAILED', findings MUST be [] (lint-enforced per §3.7 A6). When non-empty, finding_counts must agree with severity tallies (§3.7 A5, lint-enforced)."
},
"failure_reason": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"pattern": "^[^\\n\\r]+$",
"description": "One-line human-readable reason. Required iff verdict_status == 'AUDIT_FAILED' (§3.7 A2; lint-enforced)."
},
"generated_at": {
"type": "string",
"format": "date-time"
},
"generated_by": {
"type": "string",
"minLength": 1,
"description": "Path to the wrapper script that produced this verdict (canonical: 'scripts/run_codex_audit.sh')."
},
"generator_version": {
"type": "string",
"pattern": "^[0-9]+\\.[0-9]+\\.[0-9]+$",
"description": "Wrapper script semver."
}
},
"allOf": [
{
"title": "[doc-only] round vs target_rounds — enforced by lint, not schema",
"description": "JSON Schema 2020-12 has no native cross-field comparison; round <= target_rounds (§3.7 A3) is enforced by scripts/check_audit_artifact_consistency.py (Phase 6.3) and by the wrapper's --round/--target-rounds preflight (§4.2). This clause carries the comment so future readers don't try to add a non-existent schema-level constraint here."
},
{
"description": "AUDIT_FAILED requires failure_reason. Lint additionally enforces findings == [] and finding_counts all zero per §3.7 A2/A6.",
"if": {
"properties": { "verdict_status": { "const": "AUDIT_FAILED" } },
"required": ["verdict_status"]
},
"then": {
"required": ["failure_reason"]
}
},
{
"description": "Non-AUDIT_FAILED verdicts MUST NOT carry failure_reason (§3.7 A2 inverse direction).",
"if": {
"properties": {
"verdict_status": {
"type": "string",
"enum": ["PASS", "MINOR", "MATERIAL"]
}
},
"required": ["verdict_status"]
},
"then": {
"not": { "required": ["failure_reason"] }
}
}
],
"$defs": {
"run_id": {
"type": "string",
"pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}-[0-9]{2}-[0-9]{2}Z-[0-9a-f]{4}$",
"description": "Mirrored from passport/audit_artifact_entry.schema.json $defs.run_id; F1 in §3.7. Keep regex in sync."
},
"finding": {
"type": "object",
"additionalProperties": false,
"required": ["id", "severity", "dimension", "file", "line", "description", "suggested_fix"],
"properties": {
"id": {
"type": "string",
"pattern": "^F-[0-9]{3,}$",
"description": "Stable per-verdict-file identifier (e.g., 'F-007'). acknowledgement.finding_ids cross-references these (§3.7 B10)."
},
"severity": {
"type": "string",
"enum": ["P1", "P2", "P3"]
},
"dimension": {
"type": "string",
"enum": ["3.1", "3.2", "3.3", "3.4", "3.5", "3.6", "3.7", "4(f)"],
"description": "Audit template Section 3 dimension or '4(f)' for report_compiler_agent abstract-only checks."
},
"file": { "type": "string", "minLength": 1 },
"line": { "type": "integer", "minimum": 1 },
"description": { "type": "string", "minLength": 1 },
"suggested_fix": { "type": "string", "minLength": 1 }
}
}
}
}
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 |