zrwangems/dsh-zrwang-plugin / ars/skills/academic-pipeline
academic-pipeline
Flagged学术研究总编排:研究→写作→诚信检查→评审→返修→复审→终检→定稿的十阶段流水线,每阶段停在用户确认点,含材料护照与 7 类 AI 研究失败模式检查。Triggers: academic pipeline, research to paper, full paper workflow, end-to-end paper | 完整论文流程, 从研究到论文, 端到端写论文, 论文流水线。
_shared/contracts/passport/reset_ledger_entry.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/passport/reset_ledger_entry.schema.json",
"title": "Passport Reset Ledger Entry",
"description": "One append-only ledger entry in reset_boundary[]. Two kinds: 'boundary' (recorded at a FULL checkpoint when ARS_PASSPORT_RESET=1) and 'resume' (recorded when resume_from_passport consumes a boundary entry). See academic-pipeline/references/passport_as_reset_boundary.md.",
"oneOf": [
{ "$ref": "#/$defs/boundary" },
{ "$ref": "#/$defs/resume" }
],
"$defs": {
"boundary": {
"type": "object",
"additionalProperties": false,
"required": [
"kind",
"hash",
"stage",
"next",
"generated_at",
"session_marker",
"version_label"
],
"properties": {
"kind": {
"const": "boundary",
"description": "Discriminator. 'boundary' = reset emitted at a FULL checkpoint."
},
"hash": {
"type": "string",
"pattern": "^[0-9a-f]{12}$",
"description": "First 12 lowercase hex characters of SHA-256 over the concatenated ledger (prior entries + this entry with hash set to the canonical placeholder '000000000000'). Placeholder rule is normative — see protocol doc §'The reset boundary protocol' step 2."
},
"stage": {
"type": "string",
"minLength": 1,
"description": "Stage number or name that just completed (e.g., '1', '2', '2.5', 'RESEARCH')."
},
"next": {
"type": ["string", "null"],
"minLength": 1,
"description": "Default next stage after resume. When pending_decision is unset, this is the authoritative route. When pending_decision is set, this field is advisory: the matched option's next_stage takes precedence, and next MAY be null (including when all branches terminate). The orchestrator MUST NOT auto-advance using next when pending_decision is present."
},
"generated_at": {
"type": "string",
"format": "date-time",
"description": "ISO 8601 timestamp of boundary creation."
},
"session_marker": {
"type": "string",
"minLength": 1,
"description": "Opaque identifier for the source session. Audit-only; not relied on for resume."
},
"version_label": {
"type": "string",
"minLength": 1,
"description": "Monotonic version label for the passport state at this boundary (e.g., 'v1.0', 'v1.1-revised'). Stage re-runs bump this."
},
"mode": {
"type": "string",
"description": "Mode of the just-completed stage (e.g., 'full', 'systematic-review')."
},
"verification_status": {
"type": "string",
"enum": ["VERIFIED", "UNVERIFIED", "STALE"],
"description": "Mirror of Schema 9 verification_status at this boundary. Copied for convenience; authoritative value lives in Schema 9 top-level."
},
"observer_snapshot_ref": {
"type": "string",
"description": "Optional path or ID of the collaboration_depth_agent observer output for this checkpoint. Audit-only."
},
"pending_decision": {
"type": "object",
"additionalProperties": false,
"required": ["question", "options"],
"properties": {
"question": {
"type": "string",
"minLength": 1,
"description": "Human-readable question the user must answer on resume (e.g., 'Stage 3 review outcome: revise, restructure, or abort?')."
},
"options": {
"type": "array",
"minItems": 2,
"uniqueItems": true,
"items": {
"type": "object",
"additionalProperties": false,
"required": ["value", "next_stage"],
"properties": {
"value": {
"type": "string",
"minLength": 1,
"description": "Branch identifier. Must be unique across the options array — chosen_branch on the resume entry matches this field."
},
"next_stage": {
"type": ["string", "null"],
"description": "Stage number or name to route to when this branch is chosen. null means terminate the pipeline."
},
"next_mode": {
"type": "string",
"minLength": 1,
"description": "Optional downstream mode override when this branch is chosen. Omit to use the default mode for next_stage."
}
}
},
"description": "Enumerated decision branches. Each option carries its own routing: on resume, the orchestrator looks up chosen_branch in options[].value, then uses that entry's next_stage and next_mode to determine actual routing. The boundary entry's next field is advisory (best-guess default) and is superseded by the matched option's next_stage at resume time. CLI stage=/mode= overrides from resume_from_passport still win over option routing."
}
},
"description": "Set when the boundary co-occurs with a MANDATORY user decision (Stage 3 rejection, Stage 5 finalization, etc.). When present, resume must re-prompt the user. Each option carries its own next_stage/next_mode routing; the boundary entry's 'next' field is advisory only and is overridden by the matched option's next_stage at resume time."
}
}
},
"resume": {
"type": "object",
"additionalProperties": false,
"required": [
"kind",
"consumes_hash",
"generated_at",
"session_marker"
],
"properties": {
"kind": {
"const": "resume",
"description": "Discriminator. 'resume' = resume_from_passport consumed a prior boundary entry."
},
"consumes_hash": {
"type": "string",
"pattern": "^[0-9a-f]{12}$",
"description": "Hash of the boundary entry this resume consumes. Append-only pointer — lets readers compute awaiting_resume state from the ledger alone."
},
"generated_at": {
"type": "string",
"format": "date-time",
"description": "ISO 8601 timestamp of resume event."
},
"session_marker": {
"type": "string",
"minLength": 1,
"description": "Opaque identifier for the resuming session."
},
"chosen_branch": {
"type": "string",
"description": "If the consumed boundary had pending_decision, record which option the user chose. Omit otherwise."
},
"user_override": {
"type": "object",
"additionalProperties": false,
"properties": {
"stage": { "type": "string" },
"mode": { "type": "string" }
},
"description": "Optional stage/mode overrides the user supplied on the resume command."
}
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |