project-tracking

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Project Tracking

项目跟踪

Operate on tasks and goals in Epismo projects — from a quick status update to full goal restructuring.
Core principle: read current state → apply the smallest useful change.
For connection setup, surface conventions, scope model, share URL resolution, and error handling, see Epismo Basics. For workflow pack discovery and release, see Workflow Pack.
Surface selection: CLI and MCP connect to the same Epismo service. Use CLI if available; fall back to MCP if not. Never use both in the same session.
操作Epismo项目中的任务与目标 —— 从快速更新状态到全面重构目标。
核心原则:读取当前状态 → 应用最小的有效变更。
如需了解连接设置、界面约定、范围模型、共享URL解析及错误处理,请查看Epismo Basics。 如需了解工作流包的发现与发布,请查看Workflow Pack
界面选择: CLI和MCP连接至同一Epismo服务。若CLI可用则使用CLI;否则 fallback 至MCP。切勿在同一会话中同时使用两者。

Operations

操作

OperationCLIMCP
search track
epismo track search --type task|goal --filter '{...}'
epismo_track_search
get track
epismo track get --id <id>
epismo_track_get
create track
epismo track create --input '<json>'
epismo_track_create
update track
epismo track update --id <id> --input '<json>'
epismo_track_update
delete track
epismo track delete --id <id>
epismo_track_delete
apply track
epismo track apply --input '<json>'
epismo_track_apply
For filter keys, status values, entity relationships, and search recipes, see Search & Filter.
操作CLIMCP
search track
epismo track search --type task|goal --filter '{...}'
epismo_track_search
get track
epismo track get --id <id>
epismo_track_get
create track
epismo track create --input '<json>'
epismo_track_create
update track
epismo track update --id <id> --input '<json>'
epismo_track_update
delete track
epismo track delete --id <id>
epismo_track_delete
apply track
epismo track apply --input '<json>'
epismo_track_apply
如需了解筛选键、状态值、实体关系及搜索示例,请查看Search & Filter

Intent Router

意图路由

IntentWhen to chooseStepsKey reference
Update existing workField change on something that already exists (status, assignee, date, priority, content)3 Coordinate — Partial UpdateRunbook
Add one new itemExactly one task or goal; existing structure is valid3 Coordinate — New ItemRunbook
Plan multiple items or a new goalNew goal structure, multi-step plan, or batch creation2 Plan → 3 Coordinate — Large-ScaleRunbook
Unblock or rebalanceStalled queue, overloaded assignee, dependency bottleneck, noisy backlog4 Risk → 3 Coordinate — RecoveryRunbook
Design an AI-owned taskDelegating work to an AI agent with clear acceptance criteria3 Coordinate + AI DelegationAI Delegation
Unclear intentCannot confidently match any row above1 Intake — ask once
意图适用场景步骤关键参考
更新现有工作对已存在的对象进行字段变更(状态、经办人、日期、优先级、内容)3 Coordinate — 部分更新运行手册
添加单个新项仅创建一个任务或目标;现有结构有效3 Coordinate — 新建项运行手册
规划多个项或新目标新目标结构、多步骤计划或批量创建2 Plan → 3 Coordinate — 大规模规划运行手册
疏通阻塞或重新平衡停滞队列、经办人过载、依赖瓶颈、杂乱待办事项4 Risk → 3 Coordinate — 恢复运行手册
设计AI自主任务将工作委派给具备明确验收标准的AI Agent3 Coordinate + AI DelegationAI Delegation
意图不明确无法确定匹配上述任何一行1 Intake — 询问一次

4-Step Flow

四步流程

1 Intake

1 需求收集

Confirm the user's desired outcome, constraints, timeline, active workspace, and target project scope. Ask one clarifying question if intent is ambiguous. If unanswered, default to read-only and report findings.
确认用户期望的结果、约束条件、时间线、活跃工作区及目标项目范围。若意图不明确,提出一个澄清问题。若未得到回复,则默认以只读模式运行并报告结果。

2 Plan

2 规划

Run before structural changes (new goals, multi-item plans, dependency rewiring). Follow Runbook — Planning Checks: diagnose current state → select mode → design ownership contracts → confirm write destination → set next checkpoint. Always choose the smallest mode that satisfies the request.
在进行结构性变更(新目标、多任务计划、依赖关系重排)前执行此步骤。遵循运行手册 — 规划检查:诊断当前状态 → 选择模式 → 设计所有权协议 → 确认写入目标 → 设置下一个检查点。始终选择能满足请求的最小模式。

3 Coordinate

3 协调

Pick one execution mode from Runbook — Mode Selector:
  • Partial Update — localized field edits on existing entities.
  • New Item Creation — exactly one new task / goal.
  • Large-Scale Planning — multiple coordinated items with ownership contracts.
  • Recovery — address overload, stall, or noisy backlog.
When a task status changes to
done
, run a downstream dependents check: query
dependsOn=["<task-id>"]
and report what is now unblocked.
Operational state lives in tracks. Use workflow packs only when the structure should be reused beyond the current execution context — see Workflow Pack.
Design AI-owned tasks with AI Delegation. Use Track Operations for structured write output after the Runbook checks are complete.
运行手册 — 模式选择器中选择一种执行模式:
  • Partial Update(部分更新) — 对现有实体进行本地化字段编辑。
  • New Item Creation(新建项) — 恰好创建一个新任务/目标。
  • Large-Scale Planning(大规模规划) — 多个协同任务及所有权协议。
  • Recovery(恢复) — 解决过载、停滞或杂乱的待办事项。
当任务状态变更为
done
时,运行下游依赖项检查:查询
dependsOn=["<task-id>"]
并报告当前已解除阻塞的任务。
操作状态存储在跟踪项中。仅当结构需要在当前执行上下文之外复用才使用工作流包 — 详见Workflow Pack
依据AI Delegation设计AI自主任务。 在完成运行手册检查后,使用Track Operations生成结构化写入输出。

4 Risk

4 风险评估

Evaluate bottlenecks and dependency risk per Runbook. Run backlog hygiene (stale, duplicate, low-signal) during recovery.
根据运行手册评估瓶颈及依赖风险。在恢复过程中执行待办事项清理(陈旧、重复、低价值任务)。

Write Safety

写入安全规范

  1. Scope first — confirm the target project before any write. If unclear, ask once.
  2. No silent writes — if a clarification question is unanswered, continue read-only.
  3. Approval for risk — require explicit approval for large-scale plans, multi-entity recovery, and destructive changes.
  1. 先确认范围 — 在执行任何写入操作前确认目标项目。若不明确,询问一次。
  2. 禁止静默写入 — 若澄清问题未得到回复,继续以只读模式运行。
  3. 风险操作需审批 — 大规模规划、多实体恢复及破坏性变更需明确审批。

Source of Truth

权威来源

Repository:
https://github.com/epismoai/skills
代码仓库:
https://github.com/epismoai/skills