@rse/ase 0.0.35 → 0.0.36

package/package.json

@@ -6,7 +6,7 @@
     "homepage":                             "http://github.com/rse/ase",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
     "bugs":                                 { "url": "http://github.com/rse/ase/issues" },
-    "version":                              "0.0.35",
+    "version":                              "0.0.36",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

package/plugin/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.0.35",
+    "version":     "0.0.36",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/.github/plugin/plugin.json

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.0.35",
+    "version":     "0.0.36",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/meta/ase-dialog.md

@@ -36,6 +36,7 @@ Let the *user interactively choose* an answer.
         1.  Start with <config></config> (set config to empty).
             Do not output anything in this step!
 
+            Start with <n>0</n> (set entry count to zero).
             <for items="2 3 4 5">
                 Take from <config/> the line number <item/>.
                 If this line does not exist, <break/>.
@@ -43,8 +44,14 @@ Let the *user interactively choose* an answer.
                 If <config/> is not empty, set <config><config/>, </config> (append comma).
                 Set <config><config/>{ label: "<label/>",
                 description: "<description/>" }</config> (append a config entry).
+                Set <n/> to <n/> + 1 (increment entry count).
             </for>
 
+            If <n/> is less than 2:
+            Set <result>ERROR: user-dialog requires 2-4 answer lines, got <n/></result>
+            and *SKIP* the following step 2 (do not call `AskUserQuestion`)
+            and continue with step 3 dispatch.
+
         2.  Call the `AskUserQuestion` tool of the agent harness with:
 
             `AskUserQuestion({
@@ -65,11 +72,11 @@ Let the *user interactively choose* an answer.
             -   If the tool result contains `user doesn't want to proceed`,
                 `tool use was rejected`, or `user declined to answer
                 questions`, or the result clearly indicates that the
-                dialog was cancelled, rejected or skipped, set set
+                dialog was cancelled, rejected or skipped, set
                 <result>CANCEL</result>.
 
             -   Otherwise, extract the selected <answer/> from the
-                tool result `"<question-description/>"="<answer/>".
+                tool result `"<question-description/>"="<answer/>"`.
                 Set <result><answer/></result>.
                 If <result/> is then NOT one
                 the "label" values from <config/>, set
@@ -84,15 +91,22 @@ Let the *user interactively choose* an answer.
         1.  Start with <config></config> (set config to empty).
             Do not output anything in this step!
 
+            Start with <n>0</n> (set entry count to zero).
             <for items="2 3 4 5">
                 Take from <config/> the line number <item/>.
                 If this line does not exist, <break/>.
                 If this line exists, parse it according to the format `<label/>: <description/>`.
                 If <config/> is not empty, set <config><config/>, </config> (append comma).
                 Set <config><config/>"<label/>: <description/>"</config> (append a config entry).
+                Set <n/> to <n/> + 1 (increment entry count).
             </for>
 
-        2.  Call the `AskUserQuestion` tool of the agent harness with:
+            If <n/> is less than 2:
+            Set <result>ERROR: user-dialog requires 2-4 answer lines, got <n/></result>
+            and *SKIP* the following step 2 (do not call `ask_user`)
+            and continue with step 3 dispatch.
+
+        2.  Call the `ask_user` tool of the agent harness with:
 
             `ask_user({
                 question: "<question-label>: <question-description/>",

package/plugin/meta/ase-getopt.md

@@ -9,13 +9,13 @@ set placeholders into the context as a side-effect.
 
 1.  **Determine Parameters**:
     Set <getopt-skill><arg1/></getopt-skill>.
-    Set <getopt-spec/><arg2/></getopt-spec>.
-    Set <getopt-opts/><arg3/>/getopt-opts>.
-    Set <getopt-args/><content/></getopt-args>.
+    Set <getopt-spec><arg2/></getopt-spec>.
+    Set <getopt-opts><arg3/></getopt-opts>.
+    Set <getopt-args><content/></getopt-args>.
 
 2.  **Short-Circuit for Quick Processing**:
     If <getopt-opts/> contains `quick` *AND*
-    <getopt-args/> does *NOT* match the regexp `^\s*-':
+    <getopt-args/> does *NOT* match the regexp `^\s*-`:
     Set <getopt-arguments><getopt-args/></getopt-arguments> and
     then just silently *SKIP* the following steps 3-7!
 
@@ -46,7 +46,7 @@ set placeholders into the context as a side-effect.
     ```json
     {
         "opts": { "<long1/>": <value1/>, "<long2/>": <value2/>, ... },
-        "argv": [ "<arg1/>", "<arg2/>", ... ]
+        "argv": [ "<arg1/>", "<arg2/>", ... ],
         "args": "..."
     }
     ```
@@ -56,7 +56,7 @@ set placeholders into the context as a side-effect.
     Set <getopt-option-<long/>/> to the corresponding value from
     `<getopt-result/>.opts[<long/>]`.
     Set <getopt-arguments/> to the value of `<getopt-result/>.args`.
-    Set <getopt-info/> to `<getopt-result/>`.info`.
+    Set <getopt-info/> to `<getopt-result/>.info`.
 
 7.  **Display Results**:
     Just output the following <template/>:

package/plugin/meta/ase-plan.md

@@ -8,7 +8,7 @@ Every *task plan* uses a strict and fixed format:
 
 # ✪ TASK PLAN: **<title/>**
 
-◉ task id: **<ase-task-id/>** // ✳ created: **<timestamp-created/>** // ✎ modified: **<timestamp-modified/>**
+◉ task id: **<task-id/>** // ✳ created: **<timestamp-created/>** // ✎ modified: **<timestamp-modified/>**
 
 ## ※ CONTEXT
 
@@ -45,6 +45,9 @@ You *MUST* honor the following hints on this *task plan* format:
     is changed, what benefit results or what the rationale is behind the
     change.
 
+-   The <task-id/> has to be substituted with the current value of
+    <ase-task-id/> in the current session context.
+
 -   The <timestamp-created/> is the timestamp when this feature
     crafting specification was created. The
     <timestamp-modified/> is the timestamp when this feature

package/plugin/meta/ase-skill.md

@@ -19,9 +19,11 @@ Skill Output
     explicitly requested.
 
 -   *IMPORTANT*: You *MUST* output all <template/> sections *EXACTLY* as provided
-    (including newlines), except for removing trailing spaces and
-    replacing the placeholders `<xxx/>` and `[...]` and replacing XML
-    entities (like `&#x25CB;`) with the corresponding Unicode characters.
+    (including newlines), *EXCEPT* for expanding control items, removing
+    trailing spaces, replacing the placeholders `<xxx/>` and `[...]`,
+    replacing XML entities (like `&#x25CB;`) with the corresponding
+    Unicode characters, and the potential reduction of prose according
+    to the currently defined persona style.
 
 -   *IMPORTANT*: The active *persona style* (see `ase-persona.md`) *MUST* be applied
     to all *free-text placeholders* within <template/> sections — i.e. any placeholder
@@ -30,8 +32,6 @@ Skill Output
     punctuation, labels) remains unchanged; only the *authored content* inside free
     placeholders carries the persona style.
 
--   *IMPORTANT*: You *MUST* *NEVER* output any `---` lines.
-
 -   *IMPORTANT*: For *Diagrams*: whenever the response needs a
     diagram (structural, control-flow, state, sequence, class,
     entity-relationship, or metrics), you *MUST* invoke the
@@ -108,10 +108,10 @@ Skill Control Flow
     <expand name="<define-name/>" [arg1="<expand-arg1/>" [arg2="<expand-arg2/>]" [...]]]><expand-content/></expand>:
 
     This specifies the *expansion* of previous <define/>.
-    This construct is expanded into its <define-body/> with `<args/>`
-    substituted with `<expand-arg1/> <expand-arg2/> [...]`, `<arg1/>`
-    substituted with <expand-arg1/>, and `<content/>` substituted with
-    <expand-content/>.
+    This construct is expanded into the <define-body/> of <define/>
+    with `<args/>` substituted with `<expand-arg1/> <expand-arg2/>
+    [...]`, `<arg1/>` substituted with <expand-arg1/>, and `<content/>`
+    substituted with <expand-content/>.
     Do not output anything else.
 
 -   *IMPORTANT*: You *MUST* honor the following control flow construct:
@@ -159,9 +159,10 @@ Skill Sequential Processing
     `TaskCreate` tool to create a corresponding set of processing steps.
 
     Each `<step id="xxx" [...]/>` corresponds to a `TaskCreate({
-    subject: "xxx", description: "xxx", activeForm: "xxx" })`. In
-    other words, use the text of the `id` attribute of <step/> for the
-    `subject`, `description`, and `activeForm` fields of `TaskCreate`.
+    subject: "xxx", description: "xxx", activeForm: "xxx" })`. In other
+    words, use the text of the `id` attribute of <step/> for both
+    the `subject`, the `description`, and the `activeForm` fields of
+    `TaskCreate`.
 
     Make the `TaskCreate` tool calls *sequentially*, *not* in parallel,
     so the user can see intermediate results.

package/plugin/package.json

@@ -6,7 +6,7 @@
     "homepage":                             "http://github.com/rse/ase",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
     "bugs":                                 { "url": "http://github.com/rse/ase/issues" },
-    "version":                              "0.0.35",
+    "version":                              "0.0.36",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

package/plugin/skills/ase-arch-analyze/SKILL.md

@@ -135,7 +135,7 @@ interface quality, quality attributes, and architecture governance.
     README files, or folder structure.
 
     Investigate the following architecture quality aspects across
-    6 thematic blocks:
+    7 thematic blocks:
 
     **Block 1 — Component Boundaries**:
 

package/plugin/skills/ase-arch-discover/SKILL.md

@@ -21,6 +21,10 @@ allowed-tools:
 Discover Components
 ===================
 
+<skill name="ase-arch-discover">
+Discover Components
+</skill>
+
 Your role is an experienced, *expert-level software architect*,
 specialized in *finding components* (libraries/frameworks) for the technology stack.
 

package/plugin/skills/ase-code-craft/SKILL.md

@@ -167,13 +167,13 @@ permitted way to persist artifacts is via `task_save(...)`.
 
 4.  **Choose Feature Crafting Approach**:
 
-    1.  If <getopt-option-auto/> is equal `true`:
+    1.  If <getopt-option-auto/> is equal `false`:
         Let the *user interactively choose* the preferred feature approach A<n/>
         with the help of the <user-dialog-tool/> tool. Use *single-selection* only
         and provide small *code change previews*. Mark your recommended
         feature approach with ` ⚝ **RECOMMENDATION** ⚝` here again.
 
-    2.  If <getopt-option-auto/> is not equal `true`:
+    2.  If <getopt-option-auto/> is equal `true`:
         Set <n/> to the number of the feature approach A<n/> you recommend.
         Output a hint with the following <template/>:
 
@@ -217,7 +217,7 @@ permitted way to persist artifacts is via `task_save(...)`.
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand processing off to editing.

package/plugin/skills/ase-code-explain/SKILL.md

@@ -18,6 +18,10 @@ allowed-tools:
 Explain Source Code
 ===================
 
+<skill name="ase-code-explain">
+Explain Source Code
+</skill>
+
 Your role is an experienced, *expert-level software developer*,
 specialized in *explaining source code*.
 

package/plugin/skills/ase-code-insight/SKILL.md

@@ -20,6 +20,10 @@ allowed-tools:
 Project Insight
 ===============
 
+<skill name="ase-code-insight">
+Project Insight
+</skill>
+
 Your role is an experienced, *expert-level software developer*,
 specialized in *analyzing source code* and giving insights.
 

package/plugin/skills/ase-code-lint/SKILL.md

@@ -14,6 +14,10 @@ effort: medium
 Lint Source Code
 ================
 
+<skill name="ase-code-lint">
+Lint Source Code
+</skill>
+
 Your role is an experienced, *expert-level software developer*,
 specialized in *analyzing source code*.
 

package/plugin/skills/ase-code-refactor/SKILL.md

@@ -171,14 +171,14 @@ permitted way to persist artifacts is via `task_save(...)`.
 
 4.  **Choose Refactoring Approach**:
 
-    1.  If <getopt-option-auto/> is equal `true`:
+    1.  If <getopt-option-auto/> is equal `false`:
         Let the *user interactively choose* the preferred refactoring approach A<n/>
         with the help of the <user-dialog-tool/> tool. Use *single-selection* only
         and provide small *code change previews*. Mark your recommended
         refactoring approach with ` ⚝ **RECOMMENDATION** ⚝` here again.
         Except for the interactive selection, do not output anything in this step.
 
-    2.  If <getopt-option-auto/> is not equal `true`:
+    2.  If <getopt-option-auto/> is equal `true`:
         Set <n/> to the number of the refactoring approach A<n/> you recommend.
         Output a hint with the following <template/>:
 
@@ -222,7 +222,7 @@ permitted way to persist artifacts is via `task_save(...)`.
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand processing off to editing.

package/plugin/skills/ase-code-resolve/SKILL.md

@@ -223,13 +223,13 @@ permitted way to persist artifacts is via `task_save(...)`.
 
 4.  **Choose Problem Resolution Approach**:
 
-    1.  If <getopt-option-auto/> is equal `true`:
+    1.  If <getopt-option-auto/> is equal `false`:
         Let the *user interactively choose* the preferred resolution approach A<n/>
         with the help of the <user-dialog-tool/> tool. Use *single-selection* only
         and provide small *code change previews*. Mark your recommended
         resolution approach with ` ⚝ **RECOMMENDATION** ⚝` here again.
 
-    2.  If <getopt-option-auto/> is not equal `true`:
+    2.  If <getopt-option-auto/> is equal `true`:
         Set <n/> to the number of the resolution approach A<n/> you recommend.
         Output a hint with the following <template/>:
 
@@ -280,7 +280,7 @@ permitted way to persist artifacts is via `task_save(...)`.
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand processing off to editing.

package/plugin/skills/ase-meta-changes/SKILL.md

@@ -20,6 +20,10 @@ allowed-tools:
 Update ChangeLog Entries
 ========================
 
+<skill name="ase-meta-changes">
+Update ChangeLog Entries
+</skill>
+
 Your role is an experienced, *expert-level software developer*,
 specialized in *Git version control*.
 

package/plugin/skills/ase-meta-chat/SKILL.md

@@ -24,6 +24,10 @@ allowed-tools:
 Query Foreign LLMs for Chat
 ===========================
 
+<skill name="ase-meta-chat">
+Query Foreign LLMs for Chat
+</skill>
+
 Your role is to act as a proxy to query a foreign LLM for a single chat message.
 
 <objective>
@@ -44,9 +48,10 @@ Query foreign LLM for: <query>$ARGUMENTS</query>
     </step>
 
 2.  <step id="STEP 2: Spawn Agents">
-    Spawn a *sub-task* with the companion `ase-meta-chat` *agent* for
-    the selected foreign LLMs, and pass the *second and all remaining*
-    words of the following <query/> as the query for the selected LLM.
+    Spawn a *sub-task* with the companion `ase-meta-chat` *agent* (and
+    not this *skill*, but the agent of the same name) for the selected
+    foreign LLMs, and pass the *second and all remaining* words of the
+    following <query/> as the query for the selected LLM.
     </step>
 
 3.  <step id="STEP 3: Return Responses">

package/plugin/skills/ase-meta-commit/SKILL.md

@@ -16,6 +16,10 @@ allowed-tools:
 Git Commit
 ==========
 
+<skill name="ase-meta-commit">
+Git Commit
+</skill>
+
 Your role is an experienced, *expert-level software developer*,
 specialized in *Git commit messages*.
 

package/plugin/skills/ase-meta-evaluate/SKILL.md

@@ -17,6 +17,10 @@ effort: high
 Evaluate Alternatives
 =====================
 
+<skill name="ase-meta-evaluate">
+Evaluate Alternatives
+</skill>
+
 Your role is an experienced, *expert-level assistant*,
 specialized in *evaluating alternatives*.
 
@@ -195,9 +199,10 @@ multi-*criteria* decision matrix.
         abs(<rating-K/>). Do not output anything.
 
     -   If <rating-K/> is exactly zero, skip the division entirely
-        and treat <percentage/> as if it were less than 0.10
-        (i.e. fall through to the *small distance* branch below),
-        since a zero best rating signals a near-tied evaluation.
+        and treat <percentage/> as if it were equal to <distance/>
+        (so a true zero tie with <distance/> = 0 falls into the
+        *MULTIPLE BEST* branch below, and a non-zero gap with zero
+        best falls into the *small distance* branch below).
 
     -   By construction, <rating-K/> is the maximum rating across
         all alternatives, so <distance/> >= 0 always holds; using

package/plugin/skills/ase-meta-quorum/SKILL.md

@@ -7,7 +7,8 @@ user-invocable: true
 disable-model-invocation: false
 effort: medium
 allowed-tools:
-    - "Task"
+    - "Agent"
+    - "TaskCreate"
 ---
 
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
@@ -16,6 +17,10 @@ allowed-tools:
 Query Multiple AIs for Quorum Answer
 ====================================
 
+<skill name="ase-meta-quorum">
+Query Multiple AIs for Quorum Answer
+</skill>
+
 Your role is an *expert-level assistant*.
 
 <objective>
@@ -26,7 +31,7 @@ by querying *multiple* AIs for an *optimal consensus*.
 <flow>
 1.  <step id="STEP 1: Determine Own Answer">
     Determine your own answer.
-    For yourself (Anthropic Claude), first answer the following *<query/>* in advance:
+    For yourself (Anthropic Claude), first answer the following <query/> in advance:
 
     <query>
     $ARGUMENTS.
@@ -53,7 +58,7 @@ by querying *multiple* AIs for an *optimal consensus*.
 3.  <step id="STEP 3: Query Foreign AIs">
     For each of the following foreign AIs and their potentially
     available, given, corresponding MCP servers, use a *sub-task* and
-    the `ase-meta-chat` *agent* to perform the above same *<query/>* zero
+    the `ase-meta-chat` *agent* to perform the above same <query/> zero
     or more times and in *parallel* again:
 
     - OpenAI ChatGPT: `chat-openai-chatgpt`
@@ -71,8 +76,9 @@ by querying *multiple* AIs for an *optimal consensus*.
 
 5.  <step id="STEP 5: Determine Consensus Rating">
     Determine, on a Likert scale of 0..<n/>, the amount of the overall
-    consensus <c/> of all the responses. The <n/> is 1 plus the number of
-    available AIs above. If all responses disagree, the consensus <c/> is zero.
+    consensus <c/> of all the responses. The <n/> is the *total number of
+    responders* (yourself plus all available foreign AIs above).
+    If all responses disagree, the consensus <c/> is zero.
     If all responses agree, <c/> is <n/>.
 
     If not all AIs agree, determine a <disagreement/> information,

package/plugin/skills/ase-meta-search/SKILL.md

@@ -21,6 +21,10 @@ allowed-tools:
 Search the Internet/Web
 =======================
 
+<skill name="ase-meta-search">
+Search the Internet/Web
+</skill>
+
 Your role is an expert-level *web specialist*.
 
 <objective>

package/plugin/skills/ase-meta-why/SKILL.md

@@ -14,6 +14,10 @@ effort: medium
 Five-Whys Root-Cause Analysis
 =============================
 
+<skill name="ase-meta-why">
+Five-Whys Root-Cause Analysis
+</skill>
+
 Your role is an *expert-level assistant*.
 
 <objective>
@@ -38,10 +42,10 @@ addressing surface-level symptoms.
 
 2.  <step id="STEP 2: ROOT-CAUSE ANALYSIS">
     Find the root-cause of <problem/> by following the following iteration cycle.
-    Start with a <question/> equal to the <problem/>.
+    Start with a <question/> set equal to the <problem/>.
 
     <for items="1 2 3 4 5">
-        Ask <question/> and document the <answer/> with the following template:
+        Ask <question/> and document the answer in <answer/> with the following template:
         Don't stop at symptoms, keep digging for systemic issues.
         Multiple root-causes may exist -- explore different branches.
         Consider both technical, domain-specific, process-related or organizational causes.
@@ -50,7 +54,7 @@ addressing surface-level symptoms.
         &#x26AA; **WHY <item/>**: <answer/>
         </template>
 
-        Then, for the next iteration let <question/> now be the last <answer/>.
+        Then, for the next iteration set <question/> now to be the last <answer/>.
         The magic is NOT in exactly 5 "Why" -- you can <break/> the iteration
         when you already reached the root-cause.
     </for>

package/plugin/skills/ase-task-edit/SKILL.md

@@ -178,7 +178,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
         -   If <getopt-option-plan/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Previous Plan: Should the previous plan content be overwritten, refined, or preserved?
                 OVERWRITE: Continue operation, overwrite previous plan.
                 REFINE: Continue operation, refine previous plan.
@@ -322,7 +322,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Mark plan finalized, exit planning loop.
                 IMPLEMENT: Hand off plan to implementation.

package/plugin/skills/ase-task-implement/SKILL.md

@@ -133,7 +133,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing and PRESERVE task plan.
                 DELETE: Stop processing and DELETE the task plan.
@@ -151,7 +151,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
         -   If <result/> is `DELETE`:
             Only output the following <template/> and then use the
             `Skill` tool to invoke the `ase:ase-task-delete` skill in
-            order to *implement* the updated plan. Immediately stop
+            order to *delete* the updated plan. Immediately stop
             processing the current skill once the `Skill` tool was used.
 
             <template>

package/plugin/skills/ase-task-list/SKILL.md

@@ -19,7 +19,7 @@ Task List
 List Task Plans
 </skill>
 
-1.  Call the `task_list({ verbose: true })` tool from the `ase` MCP service.
+1.  Call the `task_list(verbose: true)` tool from the `ase` MCP service.
     The result is a structured object with a `tasks` array where each
     entry has an `id` field and an `mtime` field (formatted as
     `YYYY-MM-DD HH:MM`).

package/plugin/skills/ase-task-preflight/SKILL.md

@@ -155,7 +155,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand processing off to editing.

package/plugin/skills/ase-task-reboot/SKILL.md

@@ -148,7 +148,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
 
-            <expand name="user-dialog>
+            <expand name="user-dialog">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand processing off to editing.