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/revision/claim_strength_drift_disposition.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/revision/claim_strength_drift_disposition.schema.json",
"title": "E6 Raw-Event-Bound Disposition Sidecar",
"description": "A deterministic audit sidecar recording one disposition and one runtime-recomputed raw session-event byte binding for every reported E6 finding. Build and replay validation must reopen explicitly named local artifacts and recompute their raw SHA-256; an arbitrary digest assertion alone cannot authorize continuation. The durable sidecar omits transient paths and raw message content. Byte binding does not authenticate source, content meaning, or actor identity, and does not prove semantic-detection completeness/correctness or scientific warrant.",
"type": "object",
"additionalProperties": false,
"required": [
"schema_version",
"finding_set_sha256",
"final_draft_sha256",
"revision_evidence_bundle_sha256",
"disposition_status",
"session_event_bindings",
"dispositions",
"pipeline_action"
],
"properties": {
"schema_version": { "const": "claim-strength-drift-disposition/1.0" },
"finding_set_sha256": { "$ref": "#/$defs/sha256" },
"final_draft_sha256": { "$ref": "#/$defs/sha256" },
"revision_evidence_bundle_sha256": { "$ref": "#/$defs/sha256" },
"disposition_status": { "const": "complete" },
"session_event_bindings": {
"type": "array",
"minItems": 1,
"items": { "$ref": "#/$defs/session_event_binding" }
},
"dispositions": {
"type": "array",
"minItems": 1,
"items": { "$ref": "#/$defs/disposition" }
},
"pipeline_action": {
"enum": ["authorized_to_continue", "restore_required", "paused"]
}
},
"$defs": {
"sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"nonempty_string": {
"type": "string",
"minLength": 1,
"maxLength": 2000
},
"event_id": {
"type": "string",
"pattern": "^ASSERTED-EVENT-[A-Za-z0-9._-]+$"
},
"finding_id": {
"type": "string",
"pattern": "^ADV-E6-[1-9][0-9]*$"
},
"session_event_binding": {
"type": "object",
"additionalProperties": false,
"required": ["event_id", "raw_session_event_sha256", "source_assertion", "actor_role_assertion", "byte_binding", "authenticity_status"],
"properties": {
"event_id": { "$ref": "#/$defs/event_id" },
"raw_session_event_sha256": { "$ref": "#/$defs/sha256" },
"source_assertion": { "const": "session_user_message" },
"actor_role_assertion": { "const": "author" },
"byte_binding": { "const": "runtime_recomputed_from_explicit_local_artifact" },
"authenticity_status": { "const": "not_authenticated" }
}
},
"disposition": {
"type": "object",
"additionalProperties": false,
"required": [
"finding_id",
"finding_sha256",
"session_event_id",
"action"
],
"properties": {
"finding_id": { "$ref": "#/$defs/finding_id" },
"finding_sha256": { "$ref": "#/$defs/sha256" },
"session_event_id": { "$ref": "#/$defs/event_id" },
"action": { "enum": ["restore", "authorize_with_reason", "pause"] },
"reason": { "$ref": "#/$defs/nonempty_string" }
},
"allOf": [
{
"if": {
"required": ["action"],
"properties": { "action": { "const": "authorize_with_reason" } }
},
"then": { "required": ["reason"] },
"else": { "not": { "required": ["reason"] } }
}
]
}
}
}
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 |