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/writer/full.json
View on GitHub{
"contract_id": "academic_paper/writer_full/v1",
"mode": "writer_full",
"stage": "writer_full_drafting",
"baseline_version": "v3.6.6",
"acceptance_dimensions": [
{
"id": "D1",
"name": "section_completeness",
"description": "Every section in the Structure Architect's approved outline is written; no [MATERIAL GAP] placeholders remain unresolved at handoff to citation_compliance.",
"priority": "mandatory"
},
{
"id": "D2",
"name": "citation_density",
"description": "Every factual claim carries at least one citation; uncited factual claims either gain a source, are omitted, or are marked [MATERIAL GAP] for author review; hedging language alone does not satisfy this dimension. Exception (#548): absence/novelty claims cannot cite a source for an absence — they satisfy this dimension via documented-search provenance in the bounded form plus a citation to the named nearest prior work where adjacent work exists; the explicit absence-of-adjacent-work statement satisfies it otherwise.",
"priority": "mandatory"
},
{
"id": "D3",
"name": "argument_blueprint_fidelity",
"description": "Each section follows the CER chains delivered by argument_builder_agent (the Argument Blueprint runtime artefact); topic sentences match the claim, evidence cites assigned sources, and explanation links back to the section purpose. The Argument Blueprint, not the contract, is the source of CER chains.",
"priority": "mandatory"
},
{
"id": "D4",
"name": "total_word_count",
"description": "Final draft total stays within plus or minus 10 percent of the target declared in the Paper Configuration Record.",
"priority": "high"
},
{
"id": "D5",
"name": "per_section_word_count",
"description": "Each section stays within plus or minus 15 percent of the per-section allocation declared in the Paper Configuration Record.",
"priority": "high"
},
{
"id": "D6",
"name": "paragraph_structure",
"description": "Body paragraphs serve their section's purpose with a clear point, adequate cited support, explanation, and linkage, judged by clarity and evidential support rather than a TEEL percentage or length preset; author and venue requirements take priority. Inter-section transitions present.",
"priority": "normal"
},
{
"id": "D7",
"name": "register_consistency",
"description": "Academic register holds throughout; no colloquial mixing; discipline-appropriate phrasing per the Paper Configuration Record.",
"priority": "normal"
}
],
"pre_commitment_artifacts": {
"acceptance_criteria_paraphrase": {
"minimum_dimensions": "all"
}
},
"failure_conditions": [
{
"condition_id": "F1",
"severity": 90,
"expression": "any mandatory dimension scores 'block'",
"action": "writer_decision=escalate_to_evaluator"
},
{
"condition_id": "F4",
"severity": 75,
"expression": "any mandatory dimension scores 'warn'",
"action": "writer_decision=revise_in_phase_4b"
},
{
"condition_id": "F2",
"severity": 60,
"expression": "any high-priority dimension scores 'block'",
"action": "writer_decision=revise_in_phase_4b"
},
{
"condition_id": "F3",
"severity": 40,
"expression": "any high-priority dimension scores 'warn'",
"action": "writer_decision=revise_in_phase_4b"
},
{
"condition_id": "F0",
"severity": 10,
"expression": "every mandatory dimension scores 'pass'",
"action": "writer_decision=accept"
}
]
}
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 |