zrwangems/dsh-zrwang-plugin / ars/skills/sr-screener
sr-screener
Flagged系统综述文献筛选:把方案或 PROSPERO 协议转成资格规则,双盲筛选标题摘要与全文,第三人裁决冲突,输出 PRISMA 2020 计数、EndNote/Zotero RIS 分组与可交付给论文技能的 literature_corpus。Triggers: systematic review screening, screen papers, PRISMA counts, pilot screening, adjudicate conflicts | 文献筛选, 系统综述筛选, PRISMA 计数, 筛选冲突裁决。
_shared/contracts/patch/legacy/v1_0/revision_patch.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/patch/legacy/v1_0/revision_patch.schema.json",
"title": "Revision Patch Document",
"description": "#89 Item 7 patch document (spec docs/design/2026-06-10-390-diff-patch-revision-mode-spec.md §3.2). The writer's revision deliverable: a closed-vocabulary list of block operations against an anchored base draft. Every hash in this document — base_draft_hash and every per-op old_hash — is a mechanical copy from the script-generated block manifest (§3.1); the writer never computes hashes. The DOC-BODY-START insert_after shape is the ONLY legal hash-less op: it names a position (after frontmatter, before the first body block), not an anchor block, so there is no content to precondition on. Schema validation is the apply script's step zero; everything the schema cannot see (target existence, hash staleness, per-block single-op rule, marker-free new_text) is Phase 1's job (§3.3).",
"type": "object",
"additionalProperties": false,
"required": ["patch_format_version", "revision_round", "base_draft_hash", "ops", "emitted_by"],
"properties": {
"patch_format_version": {
"type": "string",
"const": "1.0",
"description": "Pinned so a future Item 9 revision contract can audit exactly what shape it gates (spec §7)."
},
"revision_round": {
"type": "integer",
"minimum": 1,
"description": "1-based revision round this patch belongs to. Each patch is generated per-round against the current base (§3.1 trigger point c)."
},
"base_draft_hash": {
"$ref": "#/$defs/hash12",
"description": "First 12 hex chars of SHA-256 over the anchored base file's raw bytes — copied from the block manifest's base_draft_hash, never computed by the writer. Document-level staleness gate: any mismatch rejects the whole patch (§3.3 Phase 1)."
},
"ops": {
"type": "array",
"minItems": 1,
"description": "Block operations, defined simultaneously against the base — array order is not semantic; the apply script splices in base-document order (§3.2). Each block_id may appear in at most one op, in any role (Phase 1 enforces; the schema cannot see across items).",
"items": {
"oneOf": [
{"$ref": "#/$defs/replace_block"},
{"$ref": "#/$defs/insert_after_anchored"},
{"$ref": "#/$defs/insert_after_doc_body_start"},
{"$ref": "#/$defs/delete_block"}
]
}
},
"emitted_by": {
"type": "string",
"minLength": 1,
"description": "Emitting agent (e.g. draft_writer_agent). Provenance surface only; the role split itself is enforced by the #134 write guard, not by this field (§3.5)."
}
},
"$defs": {
"hash12": {
"type": "string",
"pattern": "^[0-9a-f]{12}$"
},
"block_id": {
"type": "string",
"pattern": "^B[0-9]{4,}$"
},
"roadmap_item_ids": {
"type": "array",
"minItems": 1,
"items": {"type": "string", "minLength": 1},
"description": "Schema 7 RoadmapItem IDs this op addresses. Presence is machine-checked; semantic fit is an LLM/human-layer judgment (§3.2 — Anti-Pattern 7 made visible, not impossible)."
},
"new_text": {
"type": "string",
"minLength": 1,
"description": "Replacement / inserted markdown. MUST NOT contain <!--block: markers (ID assignment is the apply script's exclusive authority) and MUST carry v3.7.1/v3.7.3 citation markers for any citation it introduces (§3.2). Segmented by the shared parser; multi-block text receives fresh IDs at apply time."
},
"replace_block": {
"type": "object",
"additionalProperties": false,
"required": ["op", "block_id", "old_hash", "new_text", "roadmap_item_ids"],
"properties": {
"op": {"const": "replace_block"},
"block_id": {"$ref": "#/$defs/block_id"},
"old_hash": {"$ref": "#/$defs/hash12"},
"new_text": {"$ref": "#/$defs/new_text"},
"roadmap_item_ids": {"$ref": "#/$defs/roadmap_item_ids"}
}
},
"insert_after_anchored": {
"type": "object",
"additionalProperties": false,
"required": ["op", "block_id", "old_hash", "new_text", "roadmap_item_ids"],
"properties": {
"op": {"const": "insert_after"},
"block_id": {"$ref": "#/$defs/block_id"},
"old_hash": {"$ref": "#/$defs/hash12"},
"new_text": {"$ref": "#/$defs/new_text"},
"roadmap_item_ids": {"$ref": "#/$defs/roadmap_item_ids"}
}
},
"insert_after_doc_body_start": {
"type": "object",
"additionalProperties": false,
"required": ["op", "block_id", "new_text", "roadmap_item_ids"],
"properties": {
"op": {"const": "insert_after"},
"block_id": {"const": "DOC-BODY-START"},
"new_text": {"$ref": "#/$defs/new_text"},
"roadmap_item_ids": {"$ref": "#/$defs/roadmap_item_ids"}
}
},
"delete_block": {
"type": "object",
"additionalProperties": false,
"required": ["op", "block_id", "old_hash", "roadmap_item_ids"],
"properties": {
"op": {"const": "delete_block"},
"block_id": {"$ref": "#/$defs/block_id"},
"old_hash": {"$ref": "#/$defs/hash12"},
"roadmap_item_ids": {"$ref": "#/$defs/roadmap_item_ids"}
}
}
}
}
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 |