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/submission/venue_profile.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/submission/venue_profile.schema.json",
"title": "Venue Profile",
"description": "#394 scholar-declared venue profile (spec docs/design/2026-06-10-394-submission-package-verifier-spec.md §4). The Family B comparison source for scripts/verify_submission_package.py --venue-profile. STANDALONE schema — never embedded in the passport entry schema (the Invariant 11 pattern). Declared values ONLY: the profile is never scraped or inferred from the journal name (the R-L3-2-D no-inference mirror) — a check whose field is null/absent reports NOT-CHECKED, never a guessed limit. Collected (optionally) at intake Step 3 when a target journal is named; storable and re-feedable across runs like any declared input.",
"type": "object",
"additionalProperties": false,
"required": [
"declared_by"
],
"properties": {
"venue_name": {
"type": [
"string",
"null"
],
"description": "Display only — NEVER used for inference or lookup (R-L3-2-D mirror)."
},
"word_limit": {
"type": [
"integer",
"null"
],
"minimum": 1,
"description": "Manuscript word ceiling (B1). Compared with a ±2% tolerance for format-conversion noise (spec §3.2)."
},
"word_count_scope": {
"type": [
"string",
"null"
],
"enum": [
"body_only",
"body_plus_references",
"all",
null
],
"description": "What the venue's counting rules include. The report declares what was actually counted; null = the verifier counts body_only and says so (the method is declared, never silently assumed venue-exact — spec §3.2/§10 item 4)."
},
"abstract_word_limit": {
"type": [
"integer",
"null"
],
"minimum": 1,
"description": "Abstract word ceiling (B2). Same ±2% tolerance class as word_limit."
},
"keyword_range": {
"type": [
"object",
"null"
],
"additionalProperties": false,
"required": [
"min",
"max"
],
"properties": {
"min": {
"type": "integer",
"minimum": 0
},
"max": {
"type": "integer",
"minimum": 1
}
},
"description": "Accepted keyword count range, inclusive (B3). Exact comparison — no tolerance."
},
"required_sections": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"minLength": 1
},
"description": "Section names the venue requires (B4), e.g. [\"Data Availability\", \"CRediT\"]. Matched case-insensitively against manuscript headings (declared name contained in a heading)."
},
"reference_limit": {
"type": [
"integer",
"null"
],
"minimum": 1,
"description": "Reference-list entry ceiling (B5). Exact comparison."
},
"acknowledgments_forbidden_in_blind": {
"type": [
"boolean",
"null"
],
"description": "Scholar-declared: the venue requires acknowledgments to be removed from the blind-review version. ONLY when true does A4 (acknowledgments present in the anonymized variant) become strict-eligible — by default A4's deterministic signal stays advisory because the de-anonymization judgment is the scholar's (spec §3.1 load-bearing)."
},
"blind_review": {
"type": [
"string",
"null"
],
"enum": [
"double",
"single",
"open",
null
],
"description": "Review model. `double` triggers the Family A residue scan even when no anonymized variant is present (slice 3, spec §3.1) — a declared-double-blind package with no blind version is itself a fail."
},
"declared_by": {
"const": "scholar",
"description": "The only provenance value that exists (spec §4): the profile is scholar-declared, full stop. The CLI refuses a profile without this stamp rather than consuming values of unknown origin."
}
}
}
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 |