scope-management
Manage Scope entities — bounded containers grouping related work (sprint, milestone, project, quarter). Use when creating or updating a grouping boundary — sprint, milestone, quarter, project, release — that other entities will reference.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- scope-management
- metadata
- { "processkit": { "id": "SKILL-scope-management", "uses": [ { "skill": "event-log", "purpose": "Log events to keep the audit trail accurate after every write." }, { "skill": "index-management", "purpose": "Query existing entities and keep the SQLite index fresh after writes." }, { "skill": "id-management", "purpose": "Allocate unique entity identifiers via central ID generation." } ], "layer": 2, "created": 1775433600000, "version": "1.0.0", "category": "processkit", "provides": { "mcp_tools": [ "create_scope", "get_scope", "transition_scope", "list_scopes" ], "templates": [ "scope" ], "primitives": [ "Scope" ] }, "apiVersion": "processkit.projectious.work/v2" } }
- description
- Manage Scope entities — bounded containers grouping related work (sprint, milestone, project, quarter). Use when creating or updating a grouping boundary — sprint, milestone, quarter, project, release — that other entities will reference.
02 资源文件 5
- 资产文件assets/scope.yaml244 B
- 参考文档mcp/mcp-config.json215 B
- 参考文档mcp/SERVER.md1.1 KB
- 脚本mcp/server.py13.1 KB
- 脚本scripts/.gitkeep—
03 SKILL.md 正文
Scope Management
Intro
A Scope is a named, bounded container that groups related entities — a sprint, a milestone, a project, a release, a quarter. WorkItems, Processes, and Bindings reference scopes to say "I apply within this container."
MCP server. This skill ships a self-contained MCP server at
mcp/server.py(PEP 723 script — requiresuvand Python ≥ 3.10 on PATH). Agent harnesses reach its tools by reading a single MCP config file at startup, so the contents ofmcp/mcp-config.jsonmust be merged into the harness's MCP config and placed at the harness-specific path before this skill is usable. If processkit was installed by an installer, that wiring is the installer's responsibility; if processkit was installed manually, the project owner must do it by hand.
Overview
Kinds of scopes
| kind | Example |
|---|---|
sprint |
2-week iteration boundary |
milestone |
Named delivery target |
quarter |
Calendar quarter for OKRs |
project |
Long-lived initiative |
release |
A specific release version |
other |
Custom boundary |
Shape
---
apiVersion: processkit.projectious.work/v2
kind: Scope
metadata:
id: SCOPE-sprint-42
created: 2026-04-01T00:00:00Z
spec:
name: "Sprint 42"
kind: sprint
state: active
starts_at: 2026-04-01
ends_at: 2026-04-14
description: "Two weeks focused on the lint command and docs-site bootstrap."
goals:
- "Ship aibox lint v1"
- "Publish processkit docs-site"
---
Workflow
- Pick an ID:
SCOPE-<short-name>(e.g.,SCOPE-sprint-42,SCOPE-q2-2026). - Set
kindandstate(planned/active/completed/cancelled). - Set
starts_at/ends_atfor time-bounded scopes. - Write goals as concrete, testable bullet points.
- Save to
context/scopes/, logscope.created.
Using scopes
Reference via spec.scope: SCOPE-... on WorkItems, or use a Binding
(type: work-scope) when the scope relationship is temporal and an item
can move in or out of scope during its lifetime.
Gotchas
Agent-specific failure modes — provider-neutral pause-and-self-check items:
- Treating a Scope like a folder. Scope is a conceptual container, not a directory. Don't move files based on scope membership; reference the SCOPE-ID from entities and let the index resolve membership.
- Creating overlapping Scopes that double-count work. "Sprint 42" and "Q2 OKRs" can both contain the same workitem, but be explicit about which is the primary scope vs which is a secondary categorization. Otherwise reports double-count.
- Using
spec.scopedirectly when membership is temporal. If a workitem moves into and out of a sprint over its lifetime, use a Binding (type: work-scope) instead of pinningspec.scope. The Binding carriesvalid_from/valid_until; the field doesn't. - Forgetting to transition Scope state. Scopes have a
lifecycle:
planned → active → completed → cancelled. A Scope that saysstate: activefor six months past its end date poisons every "what's the current sprint" query. - Hallucinating SCOPE-IDs. When asked to add work to "the
current sprint", call
list_scopes(state: active)first. Don't inventSCOPE-sprint-42if it doesn't exist — create it explicitly viacreate_scope. - Reusing a Scope across different timeframes. "Sprint 42" in
Q2 2025 and "Sprint 42" in Q2 2026 are different Scopes — same
number, different time. Use distinct IDs
(
SCOPE-2025-Q2-sprint-42andSCOPE-2026-Q2-sprint-42) so history is unambiguous. - Naming scopes ambiguously. "Q1" without a year is meaningless in three months. Always include the year and the kind in the name; the ID can stay short.
Full reference
Fields
| Field | Type | Notes |
|---|---|---|
name |
string | Human-readable. Shown in listings. |
kind |
enum | sprint/milestone/quarter/project/release/other |
state |
enum | planned/active/completed/cancelled |
starts_at |
date | Optional. For time-bounded scopes. |
ends_at |
date | Optional. |
goals |
list[string] | Concrete outcomes expected. |
description |
string | Longer context. |
parent |
string | Optional parent scope (quarter → sprint). |
Nested scopes
A sprint can be nested within a quarter via spec.parent. Queries resolve
transitively: "all work in Q2 2026" includes all sprints that sit inside it.
Closing a scope
When a scope ends:
- Set
state: completed. - Log
scope.completed. - Do not delete the file — historical WorkItems reference it.
- Optionally write a retrospective DecisionRecord linked via
spec.related_decisions.
04 同仓库更多 Skills
standard-ui-design
暂无简介
standard-agent-use
Company standard for working with AI agents. Use when deciding what to delegate to agents, capturing open work, keeping agent memory or knowledge notes, improving an agent workflow, or introducing agent work in a team or for a client.
standard-agent-building
暂无简介
skill-management
Manage Skill package manifests as v1 ontology entities.
schema-management
Manage generated processkit schema contracts through deterministic MCP rebuild and inspection workflows.
proposition-management
Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.