proposition-management
Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- proposition-management
- metadata
- { "processkit": { "id": "SKILL-proposition-management", "uses": [ { "skill": "event-log", "purpose": "Record proposition creation and updates." }, { "skill": "index-management", "purpose": "Query Proposition interfaces and discriminators." } ], "layer": 1, "created": 1784764800000, "version": "1.0.0-alpha.1", "category": "processkit", "provides": { "mcp_tools": [ "create_proposition", "get_proposition", "update_proposition", "query_propositions" ], "primitives": [ "Proposition" ] }, "apiVersion": "processkit.projectious.work/v2" } }
- description
- Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.
02 资源文件 4
- 参考文档mcp/mcp-config.json247 B
- 参考文档mcp/SERVER.md447 B
- 脚本mcp/server.py9.2 KB
- 脚本scripts/test_proposition_management.py4.0 KB
03 SKILL.md 正文
Proposition Management
Intro
Proposition management records epistemic and prioritization statements without splitting each variant into a false top-level entity kind.
Overview
Use create_proposition(kind="claim", ...) for an ordinary claim. Generated
overlays additionally support risk, belief, world-fact,
wsjf-estimate, and assumption. Read and query every variant through the
shared Proposition interface. Updates revalidate the selected discriminator
overlay and preserve one PROP- identity.
Gotchas
- Do not create a top-level Risk entity. Risk is a Proposition
discriminator and must retain
kind: Propositionin frontmatter. - Do not omit likelihood or impact for risks. The generated Risk overlay requires both.
- Do not silently change a proposition's discriminator.
kindis fixed after creation; supersede when semantics fundamentally change. - Do not treat confidence as a percentage. The contract accepts a value from zero to one.
- Do not query filenames to find risks. Use the Proposition interface and
riskdiscriminator stored in the index.
Full reference
Claims accept status, confidence, ownership, evidence, scope, source, validity, and supersession metadata. Risks add likelihood and impact fields; beliefs add rationale; world facts require a source; WSJF estimates require cost of delay and job size; assumptions add validation timing and method.
Anti-patterns:
- Recording a task or defect as a Proposition instead of a WorkItem.
- Conflating risk acceptance with evidence that the risk is false.
- Rewriting a historical statement instead of recording supersession.
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.
ontology-management
Manage generated v1 ontology entities that do not require a dedicated domain server.