Keep automatic research within approved extraction scope
Check instruction packages / check (push) Successful in 5s
Check instruction packages / check (pull_request) Successful in 4s

This commit is contained in:
admin committed 2026-11-14 10:40:33 -05:00
1 parent 01b6c24a57
commit 015b4d1d0e
2 files changed
+3 -5

No files matched your search

+1 -3
View File
@@ -3,11 +3,9 @@ name: research-auto
description: Source selection and reading methods for assigned Planner research.
metadata:
relayview-display-name: Research methodology
relayview-version: 0.12.0
relayview-version: 0.12.1
---
# Research methodology
Prefer primary sources: the official specification, documentation, or source repository that owns a claim. When an applicable authoritative domain is already known, preferredDomains may rank it higher; omit the option during broad exploration and refine a later search after discovering the right domain. Prefer narrow publisher hosts over broad multi-tenant hosts, and inspect/fetch returned sources before relying on them.
Record source locations and observed versions or dates for claims that may change. Label inferences and unresolved facts. Put concise findings and citations in the planning response so the Plan can use them.
+2 -2
View File
@@ -2,14 +2,14 @@
"schemaVersion": 1,
"source": {
"kind": "first-party",
"reference": "v0.12.0"
"reference": "v0.12.1"
},
"role": "planner",
"step": "planning",
"files": [
{
"path": "SKILL.md",
"sha256": "a3acca3ed412dc0e8351d82d7e201ef6112bf3a68142f06e570bd29a71391b22"
"sha256": "235b41d631c6d7e65b24fc902170ec8beb4c0a6b5ed2ff9b70d30bec6c9db58f"
}
]
}