smashimo/oh-my-pi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(coding-agent): identify user-invoked skills and expose skill directory

Browse Source 
User-invoked skills (typed /skill:, steered, follow-up, interrupted/
resumed via compaction, ACP, RPC) only appended a bare "Skill: <path>"
line, so the model neither learned the user had invoked that specific
skill nor where the skill directory was. Relative paths in skill bodies
(scripts/, templates/) could not be resolved.

Route all user-invoked paths through a self-identifying, baseDir-aware
prompt template; keep hidden autoload skills on the minimal non-user
format. Interactive skillCommands now carries the loaded Skill object
instead of a bare path so baseDir flows through without reconstruction.
The invocation kind defaults to "user" to keep buildSkillPromptMessage
source-compatible.

Op: correct
Restores: spec:user-invoked-skill-prompt-self-identifies-and-exposes-skill-directory
This commit is contained in:
metaphorics
2026-06-30 23:11:05 +09:00
parent 5bc68f57cd
commit fa64097992
15 changed files with 163 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/coding-agent/src/modes/rpc/rpc-mode.ts
+1 -1
View File
@@ -94,7 +94,7 @@ export async function tryRunRpcSkillCommand(
const skillName = commandName.slice("skill:".length);
const skill = session.skills.find(candidate => candidate.name === skillName);
if (!skill) return false;
const built = await buildSkillPromptMessage(skill, args);
const built = await buildSkillPromptMessage(skill, args, "user");
await session.promptCustomMessage({
customType: SKILL_PROMPT_MESSAGE_TYPE,
content: built.message,