@rse/ase 0.9.9 → 0.9.10

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":                              "0.9.9",
+    "version":                              "0.9.10",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

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

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.9.9",
+    "version":     "0.9.10",
     "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":     "0.9.9",
+    "version":     "0.9.10",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/meta/ase-dialog.md

@@ -11,6 +11,7 @@ User Dialog
 </if>
 
 <define name="user-dialog">
+
 Let the *user interactively choose* an answer.
 
 1.  Take the following question specification:
@@ -140,13 +141,17 @@ Let the *user interactively choose* an answer.
 </define>
 
 <define name="custom-dialog">
-Let the *user interactively choose* an answer.
+
+In the following, you *MUST* *NOT* use the <user-dialog-tool/> tool!
+Instead, you *MUST* just show a custom output, let the user enter input,
+and then you set the result accordingly. For this, closely follow the
+following procedure:
 
 1.  Take the following question specification:
+    <spec><content/></spec>
 
-    <spec>
-        <content/>
-    </spec>
+    Take the following options:
+    <opts><arg1/></opts>
 
     The first line of <spec/> (separated by newlines) is of the format:
     `<question-label/>: <question-description/>`
@@ -166,13 +171,17 @@ Let the *user interactively choose* an answer.
 
         Set <text></text> (set to empty).
         Set <keys></keys> (set to empty).
-        Set <n>1</n> (set entry count to one).
-        Set <width/> to the maximum length plus 3 of all <label/> strings in <spec/>.
+        Set <n>0</n> (set entry count to zero).
+        Set <width/> to the maximum length plus 3 of the <label/> strings in the
+        contiguous answer lines of <spec/> starting at line 2 (the answer labels only,
+        excluding the question label on line 1, and stopping at the first missing line --
+        the same lines the entry loop below renders).
 
         <for items="2 3 4 5 6 7 8 9">
             Take from <spec/> the line number <item/>.
             If this line does not exist, <break/>.
             If this line exists, parse it according to the format `<label/>: <description/>`.
+            Set <n/> to <n/> + 1 (increment entry count).
             Set <label-key/> to <ase-tpl-key digit="<n/>"/>.
             Set <label-text/> to `<ase-tpl-pad width="<width/>" text="<label/>:"/>`.
             Append an entry to <text/>:
@@ -182,7 +191,6 @@ Let the *user interactively choose* an answer.
             <ase-tpl-boxline><label-key/>  ▶  **<label-text/>** <description/></ase-tpl-boxline>
             </text>
 
-            Set <n/> to <n/> + 1 (increment entry count).
             <if condition="<keys/> is empty">
                 Set <keys><label-key/></keys>
             </if>
@@ -191,47 +199,67 @@ Let the *user interactively choose* an answer.
             </else>
         </for>
 
+        <if condition="<opts/> contains `--other`">
+            Set <hint>Please choose *one* option by typing <keys/>/**CANCEL**, or other free-text instruction.</hint>.
+        </if>
+        <else>
+            Set <hint>Please choose *one* option by typing <keys/>/**CANCEL**.</hint>.
+        </else>
+
         Set:
 
         <text>
-        <ase-tpl-boxed title="QUESTION" subtitle="<question-label/>">
+        <ase-tpl-boxed title="DIALOG" subtitle="<question-label/>">
 
         <ase-tpl-boxline>**<question-description/>**</ase-tpl-boxline>
 
         <text/>
 
-        Please choose *one* option by typing <keys/>/**CANCEL** or free-text instruction.
+        <hint/>
 
         </ase-tpl-boxed>
         </text>
 
-        If <n/> is less than 3:
-        Set <result>ERROR: user-dialog requires 2-8 answer lines, got less</result>
-        and *SKIP* the following step 2 and continue with step 3 dispatch.
+        If <n/> is less than 2:
+        Set <result>ERROR: custom-dialog requires 2-8 answer lines, got <n/></result>
+        and *SKIP* the following step 2.2 and continue with step 2.3 dispatch.
 
     2.  Output the following <template/>, end the current turn, wait for the
-        user input, store the user input in <result/> and then continue with step 3:
+        user input, store the user input in <result/> and then continue with
+        step 2.3 below:
 
         <template>
         <text/>
         </template>
 
-    3.  Check the result and dispatch accordingly:
+    3.  Do not output anything in this step!
+        Check the <result/> and dispatch accordingly:
 
-        -   If <result/> indicates that the user doesn't want to proceed,
-            or the user declined to answer the question, or that the dialog
-            was cancelled, rejected or skipped, set <result>CANCEL</result>.
+        1.  If <result/> is `cancel`, `CANCEL`, `reject`, `REJECT`, or
+            otherwise indicates that the user doesn't want to proceed,
+            or the user declined to answer the question, or that
+            the dialog was cancelled, rejected or skipped, set
+            <result>CANCEL</result>.
 
-        -   Otherwise, determine the selected <label/>
+        2.  Otherwise, determine the selected <label/>
             by mapping the <result/> (usually containing one of the
-            "key" or "label" strings) to one of the answer labels. Set
-            <result><label/></result>.
+            "key" or "label" strings) to one of the answer labels in
+            <spec/>. Set <result><label/></result>.
 
-            If <result/> is then *NOT* one of the "label" values from
-            <spec/>, set <result>OTHER: <result/></result> (prefix
-            result with "OTHER").
+        3.  If <result/> is then *NEITHER* one of the "key"
+            *NOR* "label" values from <spec/>:
+            <if condition="<opts/> contains `--other`">
+                Set <result>OTHER: <result/></result>
+                (prefix result with "OTHER").
+            </if>
+            <else>
+                Output the following <template/> and then *START OVER*
+                by *GOING* to step 2.2 above.
 
-        Do not output anything in this step!
+                <template>
+                ⧉ **ASE**: ERROR: **Invalid option selected!**
+                </template>
+            </else>
 
 </define>
 

package/plugin/meta/ase-format-arch.md

@@ -77,14 +77,14 @@ distinct **Artifact**s (listed under their <artifact-name/> and their
 The **Artifact**s have the following cross-references:
 
 ```text
-ARCH-02-FV Functionality View   ──(depends on)─► ARCH-02-FV Functionality View
-ARCH-03-IV Information View     ──(entity)─►     SPEC-05-DM Data Model
+ARCH-02-FV Functionality View   ──(depends on)─► ARCH-01-CV Context View
+ARCH-03-IV Information View     ──(entity)─►     SPEC-07-DM Data Model
 ARCH-03-IV Information View     ──(owner)─►      ARCH-02-FV Functionality View
 ARCH-04-CO Concurrency View     ──(hosts)─►      ARCH-02-FV Functionality View
 ARCH-06-DP Deployment View      ──(hosts)─►      ARCH-02-FV Functionality View
 ARCH-07-OV Operations View      ──(element)─►    ARCH-02-FV Functionality View
 ARCH-07-OV Operations View      ──(element)─►    ARCH-06-DP Deployment View
-ARCH-08-QP Quality Perspectives ──(addresses)─►  SPEC-04-NR Non-Functional Requirements
+ARCH-08-QP Quality Perspectives ──(addresses)─►  SPEC-05-NR Non-Functional Requirements
 ARCH-08-QP Quality Perspectives ──(affects)─►    ARCH-02-FV Functionality View
 ARCH-08-QP Quality Perspectives ──(affects)─►    ARCH-06-DP Deployment View
 ARCH-09-DR Decision Record      ──(affects)─►    ARCH-02-FV Functionality View

package/plugin/meta/ase-format-spec.md

@@ -563,7 +563,7 @@ manages, defining how information is organized and connected.
 
     ### RELATIONS
 
-    -   `<spec-dm-relation-id/>`: [`<spec-dm-relation-target/>`](#<spec-dm-relation-id/>)(`<spec-dm-relation-cardinality/>`):<br/>
+    -   `<spec-dm-relation-id/>`: [`<spec-dm-relation-target/>`](#<spec-dm-relation-target-id/>)(`<spec-dm-relation-cardinality/>`):<br/>
         <spec-dm-relation-description/>,
         **BECAUSE** <spec-dm-relation-rationale/>.
 
@@ -615,7 +615,7 @@ manages, defining how information is organized and connected.
     -   <spec-dm-relation-target/>: the <spec-dm-entity-name/> of the
         entity the directed relation targets.
 
-    -   <spec-dm-relation-id/>: the <spec-dm-entity-id/> of the
+    -   <spec-dm-relation-target-id/>: the <spec-dm-entity-id/> of the
         entity the directed relation targets.
 
     -   <spec-dm-relation-cardinality/>: the cardinality of the entity
@@ -724,8 +724,17 @@ making the forbidden moves as explicit as the allowed ones.
         is implicitly forbidden.
 
     -   Every <spec-sm-state-name/> used in a transition *MUST* be
-        declared in the `### STATES` block, and every non-final state
-        *MUST* have at least one outgoing transition.
+        declared in the `### STATES` block, and every state with no
+        outgoing transition *MUST* be listed in <spec-sm-lifecycle-final/>
+        (a state with no outgoing transition that is not final would be a
+        stuck dead-end). The converse does *not* hold: a
+        <spec-sm-lifecycle-final/> state *MAY* still have outgoing
+        transitions, modeling a resting state that can later be left again
+        (e.g. a `Closed` state with a `reopen` transition back to
+        `Active`). Thus <spec-sm-lifecycle-final/> designates the states in
+        which the entity may legally come to rest, which is a superset of,
+        but not necessarily equal to, the set of declared states that have
+        no outgoing transition.
 
     -   In case a transition has no side effect, the
         entire `<spec-sm-transition-effect/>,` clause is omitted.

package/plugin/meta/ase-getopt.md

@@ -26,8 +26,10 @@ set placeholders into the context as a side-effect.
         For each option token in <getopt-spec/> of the form
         `--<long/>[|-<short/>][=<default/>|=(<c1/>|<c2/>|...)[...]]`, set
         <getopt-option-<long/>/> to <default/> (for `=<default/>`
-        form), or to <c1/> (the first choice, for `=(<c1/>|<c2>/|...)`
-        form, or for the list form `=(<c1/>|<c2>/|...)...`),
+        form), or to the *single token* <c1/> (the first choice, both
+        for the choice form `=(<c1/>|<c2>/|...)` and for the list form
+        `=(<c1/>|<c2>/|...)...` -- an *unsupplied* list-option always
+        defaults to the single token <c1/>, *not* to a whole list),
         or to `false` (for value-less options). Then set
         <getopt-arguments><getopt-args/></getopt-arguments>.
 
@@ -52,11 +54,13 @@ set placeholders into the context as a side-effect.
     `=(<c1>|<c2>|...)` declares a value-taking option restricted to the
     listed fixed choices (the first choice acts as the default), and the
     trailing `...` (as in `=(<c1>|<c2>|...)...`) declares a value-taking
-    option whose value is a *comma-separated list* of choice tokens
-    (the first choice still acts as the default; only the *first*
-    token of the list is validated by the parser against the choice
-    set -- subsequent tokens are *not* validated, and skills validate
-    each remaining token themselves as they consume it).
+    option whose *supplied* value is a *comma-separated list* of choice
+    tokens (when *unsupplied*, the option defaults to the *single
+    token* `<c1>`, identical to the non-list choice form -- the list
+    semantics apply only to an explicitly supplied value; only the
+    *first* token of a supplied list is validated by the parser against
+    the choice set -- subsequent tokens are *not* validated, and skills
+    validate each remaining token themselves as they consume it).
 
 4.  **Short-Circuit for Error**:
     If <text/> starts with `ERROR:`:

package/plugin/meta/ase-skill.md

@@ -215,6 +215,11 @@ Skill Identification
     @${CLAUDE_SKILL_DIR}/help.md
     </template>
 
+-   *IMPORTANT*:
+    You *MUST* *NOT* output any summaries, explanations, or next
+    steps at the end of a skill beside the explicit outputs via any
+    <template/>.
+
 Template Patterns
 -----------------
 
@@ -227,12 +232,13 @@ Template Patterns
     </template>
 
 -   When `<ase-tpl-head title="<title/>"/>` should be expanded, use
-    (where <bar/> = "─" x (67 - length("⧉ ASE: <title/>")), i.e., <bar/> is
-    the "─" character repeated (67 - length("⧉ ASE: <title/>")) times):
+    (where <title-len/> is the number of characters in the string
+    `⧉ ASE: <title/>`, and <bar/> is the `─` character repeated exactly
+    (67 - <title-len/>) times):
 
     <template>
 
-    ╭────━━━━**(** `⧉ ASE`: **`<title/>`** **)**━━━━────<bar/>┈┈┈┈┈┈┈┈┈┈
+    ╭────━━━━**(** ⧉ ASE: **`<title/>`** **)**━━━━────<bar/>┈┈┈┈┈┈┈┈┈┈
 
     </template>
 
@@ -245,12 +251,13 @@ Template Patterns
     </template>
 
 -   When `<ase-tpl-foot title="<title/>"/>` should be expanded, use
-    (where <bar/> = "─" x (67 - length("⧉ ASE: <title/>")), i.e., <bar/> is
-    the "─" character repeated (67 - length("⧉ ASE: <title/>")) times):
+    (where <title-len/> is the number of characters in the string
+    `⧉ ASE: <title/>`, and <bar/> is the `─` character repeated exactly
+    (67 - <title-len/>) times):
 
     <template>
 
-    ╰────━━━━**(** `⧉ ASE`: **`<title/>`** **)**━━━━────<bar/>┈┈┈┈┈┈┈┈┈┈
+    ╰────━━━━**(** ⧉ ASE: **`<title/>`** **)**━━━━────<bar/>┈┈┈┈┈┈┈┈┈┈
 
     </template>
 
@@ -272,14 +279,14 @@ Template Patterns
 
     -   <if condition="<subtitle/> is not empty">
             Set <raw-title>⧉ ASE: <title/>: <subtitle/><raw-title>.
-            Set <render-title>`⧉ ASE`: **`<title/>`**: `<subtitle/>`</render-title>.
+            Set <render-title>⧉ ASE: **`<title/>`**: `<subtitle/>`</render-title>.
         </if>
         <else>
             Set <raw-title>⧉ ASE: <title/><raw-title>.
-            Set <render-title>`⧉ ASE`: **`<title/>`**</render-title>.
+            Set <render-title>⧉ ASE: **`<title/>`**</render-title>.
         </else>
-    -   Set <bar/> to ("─" x (67 - length("<raw-title/>"))),
-        i.e., set <bar/> to the "─" character repeated (67 - length("<raw-title/>")) times.
+    -   Set <raw-title-len/> to the number of characters in <raw-title/>.
+    -   Set <bar/> to the `─` character repeated exactly (67 - <raw-title-len/>) times.
     -   Set <body> to <content/> with all line-starts prefixed with `│ `.
 
     <template>

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":                              "0.9.9",
+    "version":                              "0.9.10",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

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

@@ -42,10 +42,13 @@ for the technology stack to *provide* the *needed functionality*
 
     2.  If <functionality/> is not clear, not precise, or not specific
         enough, let the *user interactively choose* the intended
-        functionality. For this you *MUST* use the custom `custom-dialog`
-        and *NOT* the `AskUserQuestion` based "user-dialog":
+        functionality.
 
-        <expand name="custom-dialog">
+        In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+        tool! Instead, you *MUST* just show a custom output, let the
+        user enter input, and then you set the result accordingly.
+
+        <expand name="custom-dialog" arg1="--no-other">
             Functionality: Which functionality should the components provide?
             <answer-1/>: (grounded candidate functionality 1)
             <answer-2/>: (grounded candidate functionality 2)
@@ -112,7 +115,7 @@ for the technology stack to *provide* the *needed functionality*
         <keyword-L/> (L=1-M), which allow you to search for suitable
         components.
 
-    3.. In the to be discovered result set of components <component-K/>
+    3.  In the to be discovered result set of components <component-K/>
         (K=1-N), remember the component name as <name-K/>, the
         official package name as <package-K/>, the latest version as
         <version-K/>, the stars as <stars-K/>, the created date as

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

@@ -220,10 +220,10 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         anything else in this step:
 
         <template>
-        ●   **APPROACH A<n/>**<annotation/>: *<summary/>*
+        ●   **APPROACH A<n/>**<annotation/>: **<summary/>**
         ○   [...]
-        ⊕   **PRO**: [...]
-        ⊖   **CON**: [...]
+        ⊕   *PRO*: [...]
+        ⊖   *CON*: [...]
         </template>
 
         Hints:
@@ -241,18 +241,19 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     7.  <if condition="<getopt-option-auto/> is not equal `true`">
 
-        You *MUST* use the custom `custom-dialog` and *NOT* the
-        `AskUserQuestion`-based `user-dialog` to let the *user
-        interactively choose* the preferred approach A<n/>.
+        In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+        tool! Instead, you *MUST* just show a custom output, let the
+        user enter input, and then you set the result accordingly.
 
-        Per approach A<n/>, use the option `A<n/>: <short-summary/>`
-        where <short-summary/> is an ultra brief summary of the approach
-        A<n/>. For your recommended approach, use
-        `A<n/>: ⚝ **RECOMMENDATION** ⚝: <short-summary/>` instead.
+        Let the user choose the preferred approach A<n/> by raising
+        a question with the following custom dialog, where per
+        approach A<n/>, you determine an ultra brief summary
+        <short-summary/> and then use the answer option `A<n/>:
+        ⚝ **RECOMMENDATION** ⚝: <short-summary/>` for your
+        recommended approach plus zero or more answer options `A<n/>:
+        <short-summary/>` for all other approaches:
 
-        Now raise the user dialog:
-
-        <expand name="custom-dialog">
+        <expand name="custom-dialog" arg1="--no-other">
             Select Approach: Select your preferred crafting approach to follow?
             A<n/>: <short-summary/>
             [...]
@@ -353,6 +354,6 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
             Then call the tool `Skill(skill: "ase:ase-task-edit", args: "<args/>")`.
             </else>
 
-    <step>
+    </step>
 
 </flow>

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

@@ -7,10 +7,11 @@ user-invocable: true
 disable-model-invocation: false
 effort: high
 allowed-tools:
-    - "Bash(git)"
-    - "Bash(sort)"
-    - "Bash(uniq)"
-    - "Bash(head)"
+    - "Bash(git *)"
+    - "Bash(grep *)"
+    - "Bash(sort *)"
+    - "Bash(uniq *)"
+    - "Bash(head *)"
     - "Skill"
     - "Agent"
 ---

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

@@ -152,7 +152,7 @@ related to a set of code quality aspects.
                 3.  Append the following <template/> to <diff-file/>:
 
                     <template>
-                    @@ -<old-start/>,<n/> +<new-start/>,<m/> @@
+                    @@ -<old-start/>,<old-count/> +<new-start/>,<new-count/> @@
                      <context-before/>
                     -<old-text/>
                     +<new-text/>
@@ -164,10 +164,10 @@ related to a set of code quality aspects.
                         the line of <context-before/> (one before <line/>).
                     -   The <new-start/> is the same as <old-start/> (the unchanged
                         <context-before/> line shares the same start in both files).
-                    -   The <n/> is the total number of old-side hunk lines, i.e.,
+                    -   The <old-count/> is the total number of old-side hunk lines, i.e.,
                         the number of lines in <context-before/>, <old-text/>, and
                         <context-after/> combined.
-                    -   The <m/> is the total number of new-side hunk lines, i.e.,
+                    -   The <new-count/> is the total number of new-side hunk lines, i.e.,
                         the number of lines in <context-before/>, <new-text/>, and
                         <context-after/> combined.
 
@@ -215,11 +215,11 @@ related to a set of code quality aspects.
 
         6.  <if condition="<getopt-option-auto/> is not 'true'">
 
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            not the `AskUserQuestion` based `user-dialog`:
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
 
-            <expand name="custom-dialog">
+            <expand name="custom-dialog" arg1="--other">
                 CORRECTION: How would you like to proceed with this proposed correction?
                 ACCEPT: Apply the proposed correction.
                 REJECT: Skip this proposed correction.

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

@@ -209,10 +209,10 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         anything else in this step:
 
         <template>
-        ●   **APPROACH A<n/>**<annotation/>: *<summary/>*
+        ●   **APPROACH A<n/>**<annotation/>: **<summary/>**
         ○   [...]
-        ⊕   **PRO**: [...]
-        ⊖   **CON**: [...]
+        ⊕   *PRO*: [...]
+        ⊖   *CON*: [...]
         </template>
 
         Hints:
@@ -230,18 +230,19 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     7.  <if condition="<getopt-option-auto/> is not `true`">
 
-        You *MUST* use the custom `custom-dialog` and *NOT* the
-        `AskUserQuestion`-based `user-dialog` to let the *user
-        interactively choose* the preferred approach A<n/>.
+        In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+        tool! Instead, you *MUST* just show a custom output, let the
+        user enter input, and then you set the result accordingly.
 
-        Per approach A<n/>, use the option `A<n/>: <short-summary/>`
-        where <short-summary/> is an ultra brief summary of the approach
-        A<n/>. For your recommended approach, use
-        `A<n/>: ⚝ **RECOMMENDATION** ⚝: <short-summary/>` instead.
+        Let the user choose the preferred approach A<n/> by raising
+        a question with the following custom dialog, where per
+        approach A<n/>, you determine an ultra brief summary
+        <short-summary/> and then use the answer option `A<n/>:
+        ⚝ **RECOMMENDATION** ⚝: <short-summary/>` for your
+        recommended approach plus zero or more answer options `A<n/>:
+        <short-summary/>` for all other approaches:
 
-        Now raise the user dialog:
-
-        <expand name="custom-dialog">
+        <expand name="custom-dialog" arg1="--no-other">
             Select Approach: Select your preferred refactoring approach to follow?
             A<n/>: <short-summary/>
             [...]
@@ -342,7 +343,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
             Then call the tool `Skill(skill: "ase:ase-task-edit", args: "<args/>")`.
             </else>
 
-    <step>
+    </step>
 
 </flow>
 

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

@@ -259,10 +259,10 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         anything else in this step:
 
         <template>
-        ●   **APPROACH A<n/>**<annotation/>: *<summary/>*
+        ●   **APPROACH A<n/>**<annotation/>: **<summary/>**
         ○   [...]
-        ⊕   **PRO**: [...]
-        ⊖   **CON**: [...]
+        ⊕   *PRO*: [...]
+        ⊖   *CON*: [...]
         </template>
 
         Hints:
@@ -280,18 +280,19 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     7.  <if condition="<getopt-option-auto/> is not `true`">
 
-        You *MUST* use the custom `custom-dialog` and *NOT* the
-        `AskUserQuestion`-based `user-dialog` to let the *user
-        interactively choose* the preferred approach A<n/>.
+        In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+        tool! Instead, you *MUST* just show a custom output, let the
+        user enter input, and then you set the result accordingly.
 
-        Per approach A<n/>, use the option `A<n/>: <short-summary/>`
-        where <short-summary/> is an ultra brief summary of the approach
-        A<n/>. For your recommended approach, use
-        `A<n/>: ⚝ **RECOMMENDATION** ⚝: <short-summary/>` instead.
+        Let the user choose the preferred approach A<n/> by raising
+        a question with the following custom dialog, where per
+        approach A<n/>, you determine an ultra brief summary
+        <short-summary/> and then use the answer option `A<n/>:
+        ⚝ **RECOMMENDATION** ⚝: <short-summary/>` for your
+        recommended approach plus zero or more answer options `A<n/>:
+        <short-summary/>` for all other approaches:
 
-        Now raise the user dialog:
-
-        <expand name="custom-dialog">
+        <expand name="custom-dialog" arg1="--no-other">
             Select Approach: Select your preferred resolution approach to follow?
             A<n/>: <short-summary/>
             [...]
@@ -399,7 +400,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
             Then call the tool `Skill(skill: "ase:ase-task-edit", args: "<args/>")`.
             </else>
 
-    <step>
+    </step>
 
 </flow>
 

package/plugin/skills/ase-docs-proofread/SKILL.md

@@ -129,7 +129,7 @@ Analyze documents for spelling, punctuation, or grammar errors
             ```diff
             --- <file/> (original)
             +++ <file/> (corrected)
-            @@ -<old-start/>,<n/> +<new-start/>,<m/> @@
+            @@ -<old-start/>,<old-count/> +<new-start/>,<new-count/> @@
              <context-before/>
             -<old-text/>
             +<new-text/>
@@ -143,10 +143,10 @@ Analyze documents for spelling, punctuation, or grammar errors
                 the line of <context-before/> (one before <line/>).
             -   The <new-start/> is the same as <old-start/> (the unchanged
                 <context-before/> line shares the same start in both files).
-            -   The <n/> is the total number of old-side hunk lines, i.e.,
+            -   The <old-count/> is the total number of old-side hunk lines, i.e.,
                 the number of lines in <context-before/>, <old-text/>, and
                 <context-after/> combined.
-            -   The <m/> is the total number of new-side hunk lines, i.e.,
+            -   The <new-count/> is the total number of new-side hunk lines, i.e.,
                 the number of lines in <context-before/>, <new-text/>, and
                 <context-after/> combined.
 
@@ -154,11 +154,11 @@ Analyze documents for spelling, punctuation, or grammar errors
 
         4.  <if condition="<getopt-option-auto/> is not 'true'">
 
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            not the `AskUserQuestion` based `user-dialog`:
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
 
-            <expand name="custom-dialog">
+            <expand name="custom-dialog" arg1="--other">
                 CORRECTION: How would you like to proceed with this proposed correction?
                 ACCEPT: Apply the proposed correction.
                 REJECT: Skip this proposed correction.

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

@@ -1,6 +1,6 @@
 ---
 name: ase-meta-brainstorm
-argument-hint: "[--help|-h] [--max-clarify|-c=3] [--min-ideas|-i=12] [--min-rank|-r=7] [--max-shortlist|-s=4] <topic>"
+argument-hint: "[--help|-h] [--max-clarify|-c <num>] [--min-ideas|-i <num>] [--min-rank|-r <num>] [--max-shortlist|-s <num>] <topic>"
 description: >
     Collaboratively brainstorm a topic by diverging on ideas, converging
     through clustering and scoring, and distilling a shortlist with
@@ -121,11 +121,13 @@ Honor the following tenets throughout the brainstorming:
             question <question-M/>, and let the user select the
             <answer-M/> out of the candidate answers <answer-M-K/> (leave
             out the answer lines of those candidate answers you have
-            not determined). For this you *MUST* use the custom
-            `custom-dialog` and *NOT* the `AskUserQuestion` based
-            "user-dialog":
+            not determined).
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--other">
                 <facet-M/>: <question-M/>
                 <answer-M-1/>: (first grounded candidate answer)
                 <answer-M-2/>: (second grounded candidate answer)
@@ -214,15 +216,30 @@ Honor the following tenets throughout the brainstorming:
 
         <template>
         <ase-tpl-bullet-secondary/> **IDEA CLUSTER <C/>/<c/>**: <cluster-C/> - <cluster-summary-C/>,
-        **IDEAS**: <N/>, <M/>[, ...]
+        **IDEAS**: <idea-index-C/>
         </template>
 
+        Here, <idea-index-C/> is the comma-separated list of the indices
+        <N/> of those retained ideas <idea-N/> that belong to cluster
+        <cluster-C/> (e.g. `2, 5, 9`).
+
     2.  *Score*: for each retained idea <idea-N/> in the clusters, rank its *fit* against the
         purpose and constraints on a Likert scale of 0 (poor) to 10
         (excellent), considering *value*, *uniqueness*, *risk*, and
         *alignment with the existing code base*. Keep only ideas in the
         clusters with a rank of at least <getopt-option-min-rank/>.
 
+        If *no* idea meets the <getopt-option-min-rank/> floor, the floor
+        filter would empty the set and leave the downstream steps without
+        any options. In this case, *disregard* the floor and instead keep
+        the up-to-<getopt-option-max-shortlist/> highest-ranked ideas, and
+        output the following <template/> to flag that even the strongest
+        ideas fall below the bar:
+
+        <template>
+        <ase-tpl-bullet-signal/> **NOTICE**: no idea reached the minimum rank of <getopt-option-min-rank/>/10 - shortlisting the highest-ranked ideas regardless.
+        </template>
+
     3.  From the scored ideas <idea-N/>, distill a *shortlist* of the top
         <getopt-option-max-shortlist/> options, sorted by rank from highest to lowest.
 

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

@@ -2,7 +2,7 @@
 name: ase-meta-diaboli
 argument-hint: "[--help|-h] [--count|-c <count>] <thesis>"
 description: >
-    Challenge a thesis by playing "Devil’s Advocate" (latin: "Advocatus
+    Challenge a thesis by playing "Devil’s Advocate" (Latin: "Advocatus
     Diaboli"). Use when the user wants a thesis or statement
     relentlessly challenged or criticised.
 user-invocable: true
@@ -25,7 +25,7 @@ effort: xhigh
 </expand>
 
 <objective>
-    Play "Devil’s Advocate" (latin: "Advocatus Diaboli") by relentlessly
+    Play "Devil’s Advocate" (Latin: "Advocatus Diaboli") by relentlessly
     challenging or criticising the thesis: <thesis><getopt-arguments/></thesis>
 </objective>
 
@@ -48,7 +48,7 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
 2.  <step id="STEP 2: Determine Anti-Theses">
 
     Reason on the thesis in <thesis/> by playing *Devil's Advocate*
-    (latin: *Advocatus Diaboli*) by relentlessly challenging or
+    (Latin: *Advocatus Diaboli*) by relentlessly challenging or
     criticising it with the help of the following tenets:
 
     -   **Steelmanning**:
@@ -88,7 +88,7 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
 
     -   **Push the Logic to its Conclusion**:
         Ask "If we accept this, then what?" and apply "Reduction to
-        Absurdity" (latin: "Reductio Ad Absurdum"), because this disproves
+        Absurdity" (Latin: "Reductio Ad Absurdum"), because this disproves
         the thesis by showing that accepting it leads to a logically
         absurd, contradictory, or impossible conclusion.
 

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

@@ -109,7 +109,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
         3.  For each discovered *intent group*, emit the following row
             <template/>, where <intent/> is the intent label, <changes/>
-            is the total number of lines changes per feature in format
+            is the total number of lines changed per feature in format
             `+N/-M`, <files/> is the list of affected file references,
             and <description/> is a *brief* one-to-two-sentence
             narrative of what changed and why:

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

@@ -88,12 +88,20 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
         from the MCP server `search-exa`.
     </expand>
 
-    If the `websearch` backend is *selected*:
+    If the `websearch` backend is *selected* and the tool
+    `WebSearch` is available:
 
     <expand name="agent" arg1="websearch">
         Call the tool `WebSearch(query: "<query/>")`.
     </expand>
 
+    If the `websearch` backend is *selected* and the tool `web_search` is
+    available and the tool `WebSearch` is not available:
+
+    <expand name="agent" arg1="websearch">
+        Call the tool `web_search(query: "<query/>")`.
+    </expand>
+
     </step>
 
 2.  <step id="STEP 2: Consolidate Search Answers">

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

@@ -123,10 +123,12 @@ addressing surface-level symptoms.
 
             Then choose, among the <answer-k/>, the *most causally-significant*
             candidate -- the one most likely to lead to the true root-cause --
-            and *justify* the choice in one line (state explicitly *why* it
-            beats the other candidates, e.g. it alone also explains the timing,
-            scope, or magnitude of the level's fact). A bare "most significant"
-            is *not* sufficient; if no candidate clearly dominates, say so.
+            set <chosen-k/> to its candidate index (the <k/> of the chosen
+            <answer-k/>), and *justify* the choice in one line (state explicitly
+            *why* it beats the other candidates, e.g. it alone also explains the
+            timing, scope, or magnitude of the level's fact). A bare "most
+            significant" is *not* sufficient; if no candidate clearly dominates,
+            say so.
 
             <template>
             <ase-tpl-bullet-secondary/> **WHY <n/> → chosen <n/>.<chosen-k/>**: <justification/>

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

@@ -203,11 +203,12 @@ explicitly requested by this procedure via outputs based on a <template/>!
                 </template>
 
         -   If <getopt-option-next/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            *NOT* the `AskUserQuestion` based "user-dialog":
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--no-other">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand off plan to editing.

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

@@ -226,11 +226,12 @@ Set <content-dirty>true</content-dirty>.
             Set <result><getopt-option-plan/></result>.
 
         -   If <getopt-option-plan/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            *NOT* the `AskUserQuestion` based "user-dialog":
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--other">
                 Previous Plan: Should the previous plan content be overwritten, refined, or preserved?
                 OVERWRITE: Continue operation, overwrite previous plan.
                 REFINE: Continue operation, refine previous plan.
@@ -376,11 +377,12 @@ Set <content-dirty>true</content-dirty>.
                 </template>
 
         -   If <getopt-option-next/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            *NOT* the `AskUserQuestion` based "user-dialog":
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--other">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Mark plan finalized, exit planning loop.
                 GRILL: Hand off plan to grilling.

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

@@ -239,11 +239,12 @@ explicitly requested by this procedure via outputs based on a <template/>!
                 </template>
 
         -   If <getopt-option-next/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            *NOT* the `AskUserQuestion` based "user-dialog":
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--no-other">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand off plan to editing.

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

@@ -184,11 +184,12 @@ explicitly requested by this procedure via outputs based on a <template/>!
                 </template>
 
         -   If <getopt-option-next/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            *NOT* the `AskUserQuestion` based "user-dialog":
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--no-other">
                 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.

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

@@ -196,11 +196,12 @@ explicitly requested by this procedure via outputs based on a <template/>!
                 </template>
 
         -   If <getopt-option-next/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            *NOT* the `AskUserQuestion` based "user-dialog":
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--no-other">
                 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

@@ -181,11 +181,12 @@ explicitly requested by this procedure via outputs based on a <template/>!
                 </template>
 
         -   If <getopt-option-next/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next
-            step. For this you *MUST* use the custom `custom-dialog` and
-            *NOT* the `AskUserQuestion` based "user-dialog":
 
-            <expand name="custom-dialog">
+            In the following, you *MUST* *NOT* use the <user-dialog-tool/>
+            tool! Instead, you *MUST* just show a custom output, let the
+            user enter input, and then you set the result accordingly.
+
+            <expand name="custom-dialog" arg1="--no-other">
                 Next Step: How would you like to proceed with the plan?
                 DONE: Stop processing.
                 EDIT: Hand off plan to editing.