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/patch/block_manifest.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/block_manifest.schema.json",
"title": "Block Manifest",
"description": "#89 Item 7 block manifest (spec docs/design/2026-06-10-390-diff-patch-revision-mode-spec.md §3.1). Machine-generated sidecar emitted by scripts/ars_anchorize_draft.py beside the anchored draft (<draft>.block-manifest.json) and included in the writer's revision-invocation context. It is the ONLY legitimate hash source for a patch document: the writer copies base_draft_hash and per-op old_hash values from here, never computes them (a Bucket A agent has all Bash denied when it runs as a separately dispatched subagent under the plugin hook, #134/#973, and an LLM asked to emit a SHA-256 would hallucinate one). Sidecar artifact, NOT a passport field (§6).",
"type": "object",
"additionalProperties": false,
"required": ["manifest_format_version", "base_draft_hash", "blocks"],
"properties": {
"manifest_format_version": {
"type": "string",
"const": "1.0"
},
"base_draft_hash": {
"type": "string",
"pattern": "^[0-9a-f]{12}$",
"description": "First 12 hex chars of SHA-256 over the anchored draft's raw bytes."
},
"blocks": {
"type": "array",
"description": "One entry per block, in document order.",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["block_id", "old_hash", "first_line_excerpt"],
"properties": {
"block_id": {
"type": "string",
"pattern": "^B[0-9]{4,}$"
},
"old_hash": {
"type": "string",
"pattern": "^[0-9a-f]{12}$",
"description": "First 12 hex chars of SHA-256 over the block's normalized text (§3.2 normalization; marker line excluded)."
},
"first_line_excerpt": {
"type": "string",
"maxLength": 80,
"description": "First content line (truncated) so the writer can sanity-check it is naming the block it thinks it is."
}
}
}
}
}
}
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 |