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/standing_constraint_entry.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "ars://shared/contracts/passport/standing_constraint_entry.schema.json",
"title": "Material Passport standing constraint entry 1.0",
"description": "One entry in Material Passport Schema 9 standing_constraints[] (#927): a run-wide constraint the user stated in their own turn, kept in the user's words. How entries are listed, confirmed, withdrawn, and carried: academic-pipeline/agents/pipeline_orchestrator_agent.md § Standing Constraints (#927).",
"type": "object",
"additionalProperties": false,
"required": [
"constraint_id",
"user_words",
"kind",
"applies_to_stages",
"confirmed_at"
],
"properties": {
"constraint_id": {
"type": "string",
"pattern": "^UC-[0-9]{3}$"
},
"user_words": {
"type": "string",
"minLength": 1,
"pattern": "\\S",
"description": "The user's words, unchanged."
},
"kind": {
"enum": [
"word_ceiling",
"prohibition",
"scope",
"other"
]
},
"max_words": {
"type": "integer",
"minimum": 1,
"description": "Ceiling on the paper body's word count. Required for kind word_ceiling, absent otherwise; a limit on any other count (an abstract, the whole manuscript with references) is kind other."
},
"applies_to_stages": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"enum": [
"1",
"2",
"2.5",
"3",
"4",
"3'",
"4'",
"4.5",
"5",
"6"
]
}
},
"stated_at_stage": {
"type": "string",
"minLength": 1,
"description": "The stage whose checkpoint answer carried the words; absent when they came from the initial instructions."
},
"confirmed_at": {
"type": "string",
"format": "date-time"
},
"withdrawn_at": {
"type": "string",
"format": "date-time"
},
"withdrawal_words": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
}
},
"allOf": [
{
"if": {
"properties": {
"kind": {
"const": "word_ceiling"
}
}
},
"then": {
"required": [
"max_words"
]
},
"else": {
"not": {
"required": [
"max_words"
]
}
}
},
{
"dependentRequired": {
"withdrawn_at": [
"withdrawal_words"
],
"withdrawal_words": [
"withdrawn_at"
]
}
}
]
}
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 |