Defame1297
5e296bcfef
skill-author/agent-author's #89 retarget needs to know exactly how each .apm/ primitive compiles to Claude Code and Copilot CLI output. The existing microsoft-apm corpus only had a full schema for skills and one minimal example for agents, and nothing for prompts/instructions/hooks. Deepened via APM's own Python source (not just docs) where prose was thin. Key finding for #89: agents have no per-target integrator, so apm compile does a naive verbatim copy to both Claude and Copilot, unlike prompts/instructions/hooks which each get real per-target reconstruction. That means the agent primitive's `tools:` field can't express both harnesses' incompatible vocabularies at once — a real upstream gap, not something we can schema our way around.
docs/
Plugin documentation. Not read automatically by Claude Code or GitHub Copilot CLI — reference specific files from skill bodies or agent prompts as needed.
Files
| Path | Purpose |
|---|---|
plugin-marketplace-architecture.md |
Claude Code vs Copilot CLI divergence, two-manifest pattern, plugin constraints, cross-tool compatibility |
adding-agents.md |
How to add agent definitions to the kyberforge plugin |
research/
Upstream reference material gathered during skill authoring. Not shipped with the plugin — used at development time only.
| Path | Purpose |
|---|---|
research/docs/agentskillsio/ |
agentskills.io spec, skill authoring, description optimization, eval design, scripts |
research/docs/agentsmd/ |
agents.md format spec and cross-tool configuration reference |
research/examples/skill-write/ |
Upstream skill examples reviewed when authoring skill-write and skill-audit |