skill-management
Manage Skill package manifests as v1 ontology entities.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- skill-management
- metadata
- { "processkit": { "id": "SKILL-skill-management", "layer": 1, "created": 1784764800000, "version": "1.0.0-alpha.1", "category": "processkit", "provides": { "mcp_tools": [ "create_skill", "get_skill", "update_skill", "transition_skill", "list_skills" ], "primitives": [ "Skill" ] }, "apiVersion": "processkit.projectious.work/v2" } }
- description
- Manage Skill package manifests as v1 ontology entities.
02 资源文件 4
- 参考文档mcp/mcp-config.json235 B
- 参考文档mcp/SERVER.md468 B
- 脚本mcp/server.py8.9 KB
- 脚本scripts/test_skill_management.py1.8 KB
03 SKILL.md 正文
Skill Management
Intro
Skill management projects Agent Skills packages into the v1 Skill ontology
without inventing a second canonical file. The package SKILL.md remains the
source of truth and is validated, indexed, and governed through MCP.
Overview
Use create_skill for a small conformant package, update_skill for manifest
metadata, and transition_skill for lifecycle state changes. Use
skill-builder for richer authoring and skill-reviewer for quality review.
All writes validate the projected manifest against the generated Skill schema, refresh the read index, and emit an event.
Gotchas
- Do not create a parallel
context/skills/*.mdentity. The package manifest is the canonical Skill representation. - Do not use metadata updates for lifecycle changes. State changes belong
to
transition_skill. - Do not replace skill-builder. This server provides ontology lifecycle parity; skill-builder still owns full package design.
- Do not use unsafe names or categories. Names are kebab-case and paths
remain beneath
context/skills/.
Full reference
The server indexes each package as Skill with its declared SKILL-* ID.
Projected fields include name, description, version, state, category, layer,
uses, provides, commands, triggers, owners, and capabilities.
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
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.
ontology-management
Manage generated v1 ontology entities that do not require a dedicated domain server.