jiaojie
FlaggedCreate or receive human-first AI task handoffs across chats, models, devices, and languages. Use when the user asks to hand off, export context, resume from a handoff, switch sessions while preserving work, says "交接一下", "接收交接", or supplies handoff.md, handoff.zip, handoff-audit.zip, an LCH Bundle/T0 package, OCH Snapshot, or LTM Packet. Default to one readable handoff.md; upgrade to handoff.zip only when required files must travel, and to handoff-audit.zip only for formal audit, cross-organization delivery, or proof. Preserve current intent, stop point, next action, decisions, constraints, rejected and failed paths, answered questions, materials, omissions, and revalidation needs. Do not use for generic summaries, memory lookup, hidden reasoning, completed trivial chats, or after the user declines.
examples/index.json
View on GitHub{
"schema_version": "jiaojie-public-corpus-v1",
"cases": [
{
"case_id": "coding-cross-language",
"domain": "coding",
"title": "Webhook deduplication across languages",
"synthetic": true,
"license": "MIT",
"publication_clearance": "APPROVED_BY_PROJECT_OWNER",
"status": "GOLD_CANDIDATE",
"human_verification": "NOT_PERFORMED",
"source_language": "zh-Hans",
"receipt_language": "fr",
"coverage": [
"cross_language",
"decision_evolution",
"technical_failure",
"user_veto",
"parallel_actions",
"stale_external_state"
],
"limitations": [
"Not a real user conversation",
"Not independent model evidence"
],
"path": "coding/coding-cross-language"
},
{
"case_id": "research-partial",
"domain": "research",
"title": "Market research with a missing licensed paper",
"synthetic": true,
"license": "MIT",
"publication_clearance": "APPROVED_BY_PROJECT_OWNER",
"status": "GOLD_CANDIDATE",
"human_verification": "NOT_PERFORMED",
"source_language": "en",
"receipt_language": "zh-Hans",
"coverage": [
"partial",
"missing_artifact",
"answered_question",
"source_authority"
],
"limitations": [
"Not a real user conversation",
"Not independent model evidence"
],
"path": "research/research-partial"
},
{
"case_id": "learning-intent-change",
"domain": "learning",
"title": "A learner changes from memorization to explanation practice",
"synthetic": true,
"license": "MIT",
"publication_clearance": "APPROVED_BY_PROJECT_OWNER",
"status": "GOLD_CANDIDATE",
"human_verification": "NOT_PERFORMED",
"source_language": "fr",
"receipt_language": "en",
"coverage": [
"intent_change",
"user_veto",
"technical_failure",
"answered_question"
],
"limitations": [
"Not a real user conversation",
"Not independent model evidence"
],
"path": "learning/learning-intent-change"
},
{
"case_id": "writing-authority",
"domain": "writing",
"title": "Bilingual article revision without publication authority",
"synthetic": true,
"license": "MIT",
"publication_clearance": "APPROVED_BY_PROJECT_OWNER",
"status": "GOLD_CANDIDATE",
"human_verification": "NOT_PERFORMED",
"source_language": "zh-Hans",
"receipt_language": "en",
"coverage": [
"same_artifact",
"negative_knowledge",
"authority_boundary",
"language_preservation"
],
"limitations": [
"Not a real user conversation",
"Not independent model evidence"
],
"path": "writing/writing-authority"
},
{
"case_id": "business-external-state",
"domain": "business",
"title": "Pricing decision with stale vendor terms",
"synthetic": true,
"license": "MIT",
"publication_clearance": "APPROVED_BY_PROJECT_OWNER",
"status": "GOLD_CANDIDATE",
"human_verification": "NOT_PERFORMED",
"source_language": "en",
"receipt_language": "es",
"coverage": [
"stale_external_state",
"authority_boundary",
"decision_evolution",
"user_veto"
],
"limitations": [
"Not a real user conversation",
"Not independent model evidence"
],
"path": "business/business-external-state"
},
{
"case_id": "product-design-parallel",
"domain": "product-design",
"title": "Mobile onboarding redesign with parallel actions",
"synthetic": true,
"license": "MIT",
"publication_clearance": "APPROVED_BY_PROJECT_OWNER",
"status": "GOLD_CANDIDATE",
"human_verification": "NOT_PERFORMED",
"source_language": "ja",
"receipt_language": "ko",
"coverage": [
"parallel_actions",
"missing_artifact",
"privacy_boundary",
"discarded_option"
],
"limitations": [
"Not a real user conversation",
"Not independent model evidence"
],
"path": "product-design/product-design-parallel"
},
{
"case_id": "general-chat-mixed-constraints",
"domain": "general-chat",
"title": "A complex personal plan with explicit boundaries",
"synthetic": true,
"license": "MIT",
"publication_clearance": "APPROVED_BY_PROJECT_OWNER",
"status": "GOLD_CANDIDATE",
"human_verification": "NOT_PERFORMED",
"source_language": "ko",
"receipt_language": "zh-Hans",
"coverage": [
"general_chat",
"stale_external_state",
"user_veto",
"authority_boundary"
],
"limitations": [
"Not a real user conversation",
"Not independent model evidence"
],
"path": "general-chat/general-chat-mixed-constraints"
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |