diff --git a/.github/ISSUE_TEMPLATE/dev-work.yml b/.github/ISSUE_TEMPLATE/dev-work.yml
index 290fdb2..02ef3b9 100644
--- a/.github/ISSUE_TEMPLATE/dev-work.yml
+++ b/.github/ISSUE_TEMPLATE/dev-work.yml
@@ -7,7 +7,7 @@ body:
value: |
One template for all implementation work. Set the issue **type** (Feature, Bug, or Task) instead of picking a different template.
If this belongs to an epic, add it as a sub-issue of the epic.
- After filing, add a written-by label (`by: human`, `by: ai`, `by: ai-assisted`).
+ After filing, add a written-by label: `by: human` if a person wrote it, `by: ai-assisted` if AI drafted it and a person reviewed it or gave the substance, `by: ai` if AI filed it without review.
Also add the scope label: the dotted name of the workspace it came from (like `s.app.argos.argos-dev`), or `main`.
- type: textarea
id: what
diff --git a/.github/ISSUE_TEMPLATE/epic.yml b/.github/ISSUE_TEMPLATE/epic.yml
index 1e4076b..2af8dfe 100644
--- a/.github/ISSUE_TEMPLATE/epic.yml
+++ b/.github/ISSUE_TEMPLATE/epic.yml
@@ -8,7 +8,7 @@ body:
value: |
An epic groups dev work tickets; link them as sub-issues.
If it came from an idea or spike, link it below and close it as completed.
- After filing, add a written-by label (`by: human`, `by: ai`, `by: ai-assisted`).
+ After filing, add a written-by label: `by: human` if a person wrote it, `by: ai-assisted` if AI drafted it and a person reviewed it or gave the substance, `by: ai` if AI filed it without review.
Also add the scope label: the dotted name of the workspace it came from (like `s.app.argos.argos-dev`), or `main`.
- type: input
id: from
diff --git a/.github/ISSUE_TEMPLATE/idea.yml b/.github/ISSUE_TEMPLATE/idea.yml
index d4df93d..278236b 100644
--- a/.github/ISSUE_TEMPLATE/idea.yml
+++ b/.github/ISSUE_TEMPLATE/idea.yml
@@ -8,7 +8,7 @@ body:
**Pipeline:** idea → spikes (sub-issues) → epic → dev work.
Keep an idea short. If it is small enough to just try, file a spike instead.
Don't prescribe a solution. Each area stays open for one or more spikes to explore, not a chosen design.
- After filing, add a written-by label (`by: human`, `by: ai`, `by: ai-assisted`).
+ After filing, add a written-by label: `by: human` if a person wrote it, `by: ai-assisted` if AI drafted it and a person reviewed it or gave the substance, `by: ai` if AI filed it without review.
Also add the scope label: the dotted name of the workspace it came from (like `s.app.argos.argos-dev`), or `main`.
- type: textarea
id: idea
diff --git a/.github/ISSUE_TEMPLATE/spike.yml b/.github/ISSUE_TEMPLATE/spike.yml
index f777bb5..ea05484 100644
--- a/.github/ISSUE_TEMPLATE/spike.yml
+++ b/.github/ISSUE_TEMPLATE/spike.yml
@@ -8,7 +8,7 @@ body:
A spike lays out what to explore and what we expect. It does **not** hold answers: post findings as comments and link draft PRs. It's done when the lead approves its draft PR.
Don't prescribe a solution. Describe what to learn and leave the how to whoever picks it up.
One approach per spike, not a set to choose between. Title it `: `, the area shared by its siblings. Prefer filing it under an idea (as a sub-issue), but a spike can stand alone.
- After filing, add a written-by label (`by: human`, `by: ai`, `by: ai-assisted`).
+ After filing, add a written-by label: `by: human` if a person wrote it, `by: ai-assisted` if AI drafted it and a person reviewed it or gave the substance, `by: ai` if AI filed it without review.
Also add the scope label: the dotted name of the workspace it came from (like `s.app.argos.argos-dev`), or `main`.
- type: textarea
id: exploring
diff --git a/software/application-software/workspace-inherit/.claude/skills/create-ticket/SKILL.md b/software/application-software/workspace-inherit/.claude/skills/create-ticket/SKILL.md
index 210a059..12f09fa 100644
--- a/software/application-software/workspace-inherit/.claude/skills/create-ticket/SKILL.md
+++ b/software/application-software/workspace-inherit/.claude/skills/create-ticket/SKILL.md
@@ -52,15 +52,16 @@ How every ticket reads, on any project:
## Draft
+- Unless the user already said, ask first whether they want to review a draft or have it filed directly.
- Check the code first: the work may be done or already tracked.
- One `### ` per field in template order, following each field's description; omit empty optional fields.
- Diagrams: required on epics, optional on dev work. The project's `ticket-conventions` says what they show.
-- Labels: the template's category (`idea`, `spike`, `epic`, `dev work`), one written-by (`by: human` if the user dictated it, `by: ai-assisted` if they gave the substance, `by: ai` if you wrote it, including rewrites), and at least one of the project's area labels.
+- Labels: the template's category (`idea`, `spike`, `epic`, `dev work`), one written-by (`by: human` if the user dictated it, `by: ai-assisted` if they reviewed your draft or gave the substance, `by: ai` if you filed it directly), and at least one of the project's area labels.
- Rewriting an old ticket: keep its intent and assignees; bring it up to these rules and update vocabulary, labels, issue type, and parent.
- Folding one ticket into another: add it as a requirement on the target, then close it as not planned. Every close gets a one-line comment saying why.
## File
-Check for open duplicates, then show the full draft (title, type if any, labels, parent, body) in the chat, not only in a file. File or edit only what the user OKs.
+Check for open duplicates. If the user wants it filed directly, file it without showing a draft. Otherwise show the full draft (title, type if any, labels, parent, body) in the chat, not only in a file, and file or edit only what the user OKs.
Use the REST API (GraphQL may be blocked): POST repos///issues with title, body, labels, the issue type from the table, and the user as assignee (on a spike, whoever will run it; ask), then, if it has a parent, POST repos///issues//sub_issues with the new issue's id. If it waits on another issue, POST repos///issues//dependencies/blocked_by with the blocking issue's id. Report the URL.