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/sprint_contract.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/sprint_contract.schema.json",
"title": "ARS Sprint Contract (Schema 13.2)",
"type": "object",
"additionalProperties": false,
"required": [
"contract_id",
"mode",
"stage",
"baseline_version",
"acceptance_dimensions",
"failure_conditions"
],
"$comment": "Schema 13.2 retains Schema 13.1's mode-conditional measurement_procedure and panel_size gates, and adds reviewer role-scoping in branch 13. Writer / evaluator contracts remain byte-unchanged and do not carry reviewer role fields.",
"properties": {
"contract_id": {
"type": "string",
"pattern": "^[a-z_]+/[a-z_]+/v\\d+$"
},
"mode": {
"enum": [
"reviewer_full",
"reviewer_methodology_focus",
"reviewer_calibration",
"reviewer_guided",
"writer_full",
"evaluator_full"
]
},
"stage": { "type": "string", "minLength": 1 },
"baseline_version": {
"type": "string",
"pattern": "^v\\d+\\.\\d+\\.\\d+$"
},
"panel_size": { "type": "integer", "minimum": 1 },
"acceptance_dimensions": {
"type": "array",
"minItems": 1,
"items": {
"type": "object",
"additionalProperties": false,
"required": ["id", "name", "description", "priority"],
"properties": {
"id": { "type": "string", "pattern": "^D[1-9][0-9]?$" },
"name": { "type": "string", "pattern": "^[a-z][a-z0-9_]*$" },
"description": { "type": "string", "minLength": 1 },
"priority": { "$ref": "#/$defs/priority" },
"eligible_roles": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": { "$ref": "#/$defs/reviewer_role" }
},
"owner_role": { "$ref": "#/$defs/reviewer_role" }
}
}
},
"measurement_procedure": {
"type": "object",
"additionalProperties": false,
"required": [
"reviewer_must_output_before_paper",
"scoring_plan_schema",
"paraphrase_minimum_dimensions"
],
"properties": {
"reviewer_must_output_before_paper": {
"type": "array",
"minItems": 2,
"items": { "type": "string", "minLength": 1 }
},
"scoring_plan_schema": {
"type": "object",
"additionalProperties": false,
"required": ["required"],
"properties": {
"required": {
"type": "array",
"minItems": 5,
"uniqueItems": true,
"items": {
"enum": [
"dimension_id",
"what_to_look_for",
"what_triggers_block",
"what_triggers_warn",
"what_triggers_fatal"
]
},
"$comment": "The five canonical Phase-1 fields are fixed by sprint_contract_protocol.md §4. minItems:5 + uniqueItems:true + enum-constrained items rejects empty lists, partial lists, and typoed entries at CI time instead of letting them fail at runtime as Phase-1 lint."
}
}
},
"paraphrase_minimum_dimensions": {
"anyOf": [
{ "const": "all" },
{ "type": "integer", "minimum": 1 }
]
}
}
},
"pre_commitment_artifacts": {
"type": "object",
"additionalProperties": false,
"required": ["acceptance_criteria_paraphrase"],
"$comment": "Schema 13.1 v3.6.6 §3.4.1 (writer-only). Carries only invariant, paper-agnostic policy: how many acceptance_dimensions the writer must paraphrase in Phase 4a paper-blind output. Everything paper-specific lives in upstream runtime artefacts and is read at Phase 4a / 4b runtime, not committed in the frozen contract baseline. Per-section word counts come from the Paper Configuration Record (intake_agent); section outline comes from the Structure Architect's approved outline (structure_architect_agent); CER chains come from the Argument Blueprint (argument_builder_agent). Writer dimensions D1 (section_completeness), D3 (argument_blueprint_fidelity), D4 (total_word_count), D5 (per_section_word_count) phrase their gates against those upstream artefacts rather than against contract-embedded values. Required for writer_full only (allOf branch 11).",
"properties": {
"acceptance_criteria_paraphrase": {
"type": "object",
"additionalProperties": false,
"required": ["minimum_dimensions"],
"$comment": "CONFIGURATION declaration, not the paraphrase content itself. Declares how many of the contract's acceptance_dimensions the writer must paraphrase in Phase 4a. The actual paraphrase text is a runtime artifact emitted by draft_writer_agent in its Phase 4a output (analogous to how reviewer paraphrase content lives in <phase1_output>, not in the contract). Mirrors reviewer measurement_procedure.paraphrase_minimum_dimensions semantics.",
"properties": {
"minimum_dimensions": {
"anyOf": [
{ "const": "all" },
{ "type": "integer", "minimum": 1 }
],
"$comment": "Default in shipped writer template: 'all'."
}
}
}
}
},
"disagreement_handling": {
"type": "object",
"additionalProperties": false,
"required": ["paraphrase_minimum_dimensions", "scoring_plan", "pre_commitment_check_protocol", "disagreement_resolution"],
"$comment": "Schema 13.1 v3.6.6 §3.4.2 (evaluator-only). Required for evaluator_full only (allOf branch 12).",
"properties": {
"paraphrase_minimum_dimensions": {
"anyOf": [
{ "const": "all" },
{ "type": "integer", "minimum": 1 }
],
"$comment": "How many of the contract's acceptance_dimensions the evaluator must paraphrase in Phase 6a paper-blind output (the contract_paraphrase artifact named in §1 design goal 2 / §4.3). Mirrors reviewer measurement_procedure.paraphrase_minimum_dimensions and writer pre_commitment_artifacts.acceptance_criteria_paraphrase.minimum_dimensions to keep the Phase-6a anti-drift gate hard-required at the schema layer rather than relying on prose-level commitments. Default in shipped evaluator template: 'all'."
},
"scoring_plan": {
"type": "object",
"additionalProperties": false,
"required": ["per_dimension_criteria"],
"properties": {
"per_dimension_criteria": {
"type": "array",
"minItems": 1,
"items": {
"type": "object",
"additionalProperties": false,
"required": ["dimension_id", "what_to_look_for", "what_triggers_block", "what_triggers_warn"],
"properties": {
"dimension_id": { "type": "string", "pattern": "^D[1-9][0-9]?$" },
"what_to_look_for": { "type": "string", "minLength": 1 },
"what_triggers_block": { "type": "string", "minLength": 1 },
"what_triggers_warn": { "type": "string", "minLength": 1 }
},
"$comment": "Mirrors reviewer measurement_procedure.scoring_plan_schema four-field structure. Evaluator commits these in Phase 6a paper-blind."
}
}
}
},
"pre_commitment_check_protocol": {
"type": "object",
"additionalProperties": false,
"required": ["check_writer_artifact"],
"properties": {
"check_writer_artifact": {
"const": "pre_commitment_artifacts",
"$comment": "Pinned to the single writer source for v3.6.6. Field shape exists (rather than inlining the const) for forward compatibility — when v3.6.7+ may add additional writer artifacts, this can relax to an enum without a breaking schema change."
}
}
},
"disagreement_resolution": {
"type": "object",
"additionalProperties": false,
"required": ["on_dimension_disagreement", "on_structural_drift"],
"$comment": "Both subfield enums use the fully-qualified evaluator_decision=* vocabulary so values can be passed directly into failure_conditions[].action without runtime transformation. Keeping a single canonical action vocabulary across §3.3.3 and §3.4.2 prevents drift between the two surfaces.",
"properties": {
"on_dimension_disagreement": {
"enum": [
"evaluator_decision=request_revision",
"evaluator_decision=accept_with_dissent_note",
"evaluator_decision=flag_for_reviewer_stage"
],
"$comment": "What the evaluator does when its own paper-blind scoring plan flags a dimension during paper-visible evaluation (the dimension hits its pre-committed what_triggers_block or what_triggers_warn anchors). Default in shipped templates: 'evaluator_decision=request_revision' for mandatory dimensions; runtime evaluator may downgrade non-mandatory dimensions to 'accept_with_dissent_note' (see F4 in evaluator/full.json)."
},
"on_structural_drift": {
"enum": [
"evaluator_decision=request_revision",
"evaluator_decision=accept_with_dissent_note",
"evaluator_decision=flag_for_reviewer_stage"
],
"$comment": "What the evaluator does when the actual draft structure deviates from the Structure Architect's approved outline (the upstream runtime artefact from structure_architect_agent that the writer follows in Phase 4b). Drift threshold lives in the evaluator's runtime judgement, not the schema; the contract carries only the default verdict to apply when drift is observed."
}
}
}
}
},
"failure_conditions": {
"type": "array",
"minItems": 1,
"items": {
"type": "object",
"additionalProperties": false,
"required": ["condition_id", "severity", "expression", "action"],
"properties": {
"condition_id": {
"type": "string",
"pattern": "^F(0|[1-9][0-9]?)$",
"$comment": "F0 reserved for accept-grade conditions per shipped templates §6.1+§6.2; spec §3.2 line 174 mistakenly writes ^F[1-9][0-9]?$ — DO NOT 'align' the schema back. Leading-zero forms (F00, F01) rejected to keep ordinal-position tie-break (§3.2 severity precedence) unambiguous."
},
"severity": { "type": "integer", "minimum": 0, "maximum": 100 },
"cross_reviewer_quantifier": { "enum": ["any", "majority", "all"] },
"expression": { "type": "string", "minLength": 1 },
"action": {
"type": "string",
"$comment": "Schema 13.1 v3.6.6 §3.3.3: base enum lifted; mode-conditional action enums enforced in allOf branches 4 (reviewer) / 5 (writer_full) / 6 (evaluator_full). The base property keeps only type:string as a structural placeholder so JSON Schema's intersection semantics do not block writer / evaluator action values."
}
}
}
},
"override_ladder": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["round", "trigger", "required"],
"properties": {
"round": { "type": "integer", "enum": [1, 2, 3] },
"trigger": { "type": "string", "minLength": 1 },
"required": {
"type": "array",
"items": { "type": "string", "minLength": 1 }
}
}
}
},
"agent_amendments": {
"type": "object",
"additionalProperties": false,
"properties": {
"stage_specific_notes": { "type": "string", "maxLength": 500 },
"additional_measurement_hints": {
"type": "array",
"items": { "type": "string", "minLength": 1 }
}
}
},
"generated_at": { "type": "string", "format": "date-time" }
},
"allOf": [
{
"$comment": "Branch 1 (existing Schema 13 §3.3): reviewer mode requires cross_reviewer_quantifier on every failure_conditions entry.",
"if": {
"properties": { "mode": { "pattern": "^reviewer_" } },
"required": ["mode"]
},
"then": {
"properties": {
"failure_conditions": {
"items": { "required": ["cross_reviewer_quantifier"] }
}
}
}
},
{
"$comment": "Branch 2 (existing Schema 13 §3.3): override_ladder three-round shape if present.",
"if": { "required": ["override_ladder"] },
"then": {
"properties": {
"override_ladder": {
"minItems": 3,
"maxItems": 3,
"prefixItems": [
{ "properties": { "round": { "const": 1 } } },
{ "properties": { "round": { "const": 2 } } },
{ "properties": { "round": { "const": 3 } } }
]
}
}
}
},
{
"$comment": "Branch 3 (new v3.6.6 §3.3.1): reviewer mode requires measurement_procedure (lifted from base required).",
"if": {
"properties": { "mode": { "pattern": "^reviewer_" } },
"required": ["mode"]
},
"then": {
"required": ["measurement_procedure"]
}
},
{
"$comment": "Branch 4 (new v3.6.6 §3.3.3): reviewer mode pins failure_conditions[].action to editorial_decision=* enum (re-pins the Schema 13 base enum; structurally identical for reviewer contracts).",
"if": {
"properties": { "mode": { "pattern": "^reviewer_" } },
"required": ["mode"]
},
"then": {
"properties": {
"failure_conditions": {
"items": {
"properties": {
"action": {
"enum": [
"editorial_decision=accept",
"editorial_decision=minor_revision",
"editorial_decision=major_revision",
"editorial_decision=reject"
]
}
}
}
}
}
}
},
{
"$comment": "Branch 5 (new v3.6.6 §3.3.3): writer_full pins failure_conditions[].action to writer_decision=* enum.",
"if": {
"properties": { "mode": { "const": "writer_full" } },
"required": ["mode"]
},
"then": {
"properties": {
"failure_conditions": {
"items": {
"properties": {
"action": {
"enum": [
"writer_decision=accept",
"writer_decision=revise_in_phase_4b",
"writer_decision=escalate_to_evaluator"
]
}
}
}
}
}
}
},
{
"$comment": "Branch 6 (new v3.6.6 §3.3.3): evaluator_full pins failure_conditions[].action to evaluator_decision=* enum.",
"if": {
"properties": { "mode": { "const": "evaluator_full" } },
"required": ["mode"]
},
"then": {
"properties": {
"failure_conditions": {
"items": {
"properties": {
"action": {
"enum": [
"evaluator_decision=accept",
"evaluator_decision=accept_with_dissent_note",
"evaluator_decision=request_revision",
"evaluator_decision=flag_for_reviewer_stage"
]
}
}
}
}
}
}
},
{
"$comment": "Branch 7 (new v3.6.6 §3.3.4): reviewer mode F0 contains action=editorial_decision=accept (re-pins the Schema 13 inline contains; structurally identical for reviewer contracts).",
"if": {
"properties": { "mode": { "pattern": "^reviewer_" } },
"required": ["mode"]
},
"then": {
"properties": {
"failure_conditions": {
"contains": {
"type": "object",
"properties": {
"condition_id": { "const": "F0" },
"action": { "const": "editorial_decision=accept" }
},
"required": ["condition_id", "action"]
}
}
}
}
},
{
"$comment": "Branch 8 (new v3.6.6 §3.3.4): writer_full F0 contains action=writer_decision=accept.",
"if": {
"properties": { "mode": { "const": "writer_full" } },
"required": ["mode"]
},
"then": {
"properties": {
"failure_conditions": {
"contains": {
"type": "object",
"properties": {
"condition_id": { "const": "F0" },
"action": { "const": "writer_decision=accept" }
},
"required": ["condition_id", "action"]
}
}
}
}
},
{
"$comment": "Branch 9 (new v3.6.6 §3.3.4): evaluator_full F0 contains action=evaluator_decision=accept.",
"if": {
"properties": { "mode": { "const": "evaluator_full" } },
"required": ["mode"]
},
"then": {
"properties": {
"failure_conditions": {
"contains": {
"type": "object",
"properties": {
"condition_id": { "const": "F0" },
"action": { "const": "evaluator_decision=accept" }
},
"required": ["condition_id", "action"]
}
}
}
}
},
{
"$comment": "Branch 10 (new v3.6.6 §3.3.5): reviewer mode requires panel_size (lifted from base required).",
"if": {
"properties": { "mode": { "pattern": "^reviewer_" } },
"required": ["mode"]
},
"then": {
"required": ["panel_size"]
}
},
{
"$comment": "Branch 11 (new v3.6.6 §3.5): writer_full requires pre_commitment_artifacts.",
"if": {
"properties": { "mode": { "const": "writer_full" } },
"required": ["mode"]
},
"then": {
"required": ["pre_commitment_artifacts"]
}
},
{
"$comment": "Branch 12 (new v3.6.6 §3.5): evaluator_full requires disagreement_handling.",
"if": {
"properties": { "mode": { "const": "evaluator_full" } },
"required": ["mode"]
},
"then": {
"required": ["disagreement_handling"]
}
},
{
"$comment": "Branch 13 (Schema 13.2): reviewer dimensions require role-scoping metadata.",
"if": {
"properties": { "mode": { "pattern": "^reviewer_" } },
"required": ["mode"]
},
"then": {
"properties": {
"acceptance_dimensions": {
"items": { "required": ["eligible_roles", "owner_role"] }
}
}
}
}
],
"$defs": {
"reviewer_role": {
"enum": ["eic", "methodology", "domain", "perspective", "da"]
},
"score": { "enum": ["block", "warn", "pass"] },
"priority": { "enum": ["mandatory", "high", "normal"] }
}
}
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 |