@rse/ase 0.9.8 → 0.9.10

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

@@ -37,13 +37,29 @@ for the technology stack to *provide* the *needed functionality*
 
 <flow>
 1.  <step id="STEP 1: Determine Functionality">
-    -   Derive the needed <functionality/> from the <request/>, but keep
+    1.  Derive the needed <functionality/> from the <request/>, but keep
         the functionality description very *brief* but still *precise*.
 
-    -   If <functionality/> is not clear or not precise enough, raise
-        questions to the user with the help of an interactive user dialog tool.
+    2.  If <functionality/> is not clear, not precise, or not specific
+        enough, let the *user interactively choose* the intended
+        functionality.
 
-    -   Display the determined final functionality with just the following
+        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)
+            <answer-3/>: (grounded candidate functionality 2)
+            <answer-4/>: (grounded candidate functionality 3)
+        </expand>
+
+        Then use the <result/> and its corresponding grounded candidate
+        functionality to adjust <functionality/> accordingly.
+
+    3.  Display the determined final functionality with just the following
         <template/>:
 
         <template>
@@ -52,32 +68,32 @@ for the technology stack to *provide* the *needed functionality*
     </step>
 
 2.  <step id="STEP 2: Determine Technology Stack">
-    -   Determine the used technology stack:
+    1.  Determine the used technology stack:
 
-        -   If a file `package.json` is found in the top-level directory
+        1.  If a file `package.json` is found in the top-level directory
             of the project and contains an entry `typescript` under `dependencies`
             or `devDependencies`, then <stack>TypeScript</stack>.
 
-        -   Else, if a file `package.json` is found in the top-level directory
+        2.  Else, if a file `package.json` is found in the top-level directory
             of the project, then <stack>JavaScript</stack>.
 
-        -   Else, if a file `build.gradle.kts` or `settings.gradle.kts`
+        3.  Else, if a file `build.gradle.kts` or `settings.gradle.kts`
             is found in the top-level directory, then <stack>Kotlin</stack>.
 
-        -   Else, if a file `build.gradle` is found in the top-level directory and
+        4.  Else, if a file `build.gradle` is found in the top-level directory and
             is applying `kotlin`, `org.jetbrains.kotlin.jvm`, `kotlin-android`,
             or `kotlin-multiplatform` plugins, then <stack>Kotlin</stack>.
 
-        -   Else, if a file `pom.xml` is found in the top-level directory and
+        5.  Else, if a file `pom.xml` is found in the top-level directory and
             contains `kotlin-maven-plugin` or `kotlin-stdlib` dependencies, then
             <stack>Kotlin</stack>.
 
-        -   Else, if a file `pom.xml` or `build.gradle` is found in the top-level directory
+        6.  Else, if a file `pom.xml` or `build.gradle` is found in the top-level directory
             of the project, then <stack>Java</stack>.
 
-        -   Else, use <stack>Unknown</stack>.
+        7.  Else, use <stack>Unknown</stack>.
 
-    -   Display the determined final technology stack with just the
+    2.  Display the determined final technology stack with just the
         following <template/>:
 
         <template>
@@ -86,7 +102,7 @@ for the technology stack to *provide* the *needed functionality*
     </step>
 
 3.  <step id="STEP 3: Discover Components">
-    -   If <stack/> is "Unknown", the technology stack could not be
+    1.  If <stack/> is "Unknown", the technology stack could not be
         determined and no component discovery backend is available.
         Inform the user with just the following <template/> and then
         *STOP* the entire flow (do not perform any further steps):
@@ -95,26 +111,26 @@ for the technology stack to *provide* the *needed functionality*
         <ase-tpl-bullet-normal/> **RESULT**: technology stack could not be determined -- component discovery is only supported for JavaScript, TypeScript, Java, and Kotlin projects.
         </template>
 
-    -   From <stack/> and <functionality/>, derive essential keywords
+    2.  From <stack/> and <functionality/>, derive essential keywords
         <keyword-L/> (L=1-M), which allow you to search for suitable
         components.
 
-    -   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
         <created-K/>, the last updated date as <updated-K/>, the total
         number of downloads in the last month as <downloads-K/>.
 
-    -   If <stack/> is "JavaScript" or "TypeScript":
+    4.  If <stack/> is "JavaScript" or "TypeScript":
 
-        -   Based on the essential keywords <keyword-L/> (L=1-M),
+        1.  Based on the essential keywords <keyword-L/> (L=1-M),
             use the `ase-meta-search` skill in a subagent to *generally*
             discover an initial set of a maximum of <getopt-option-limit/> *NPM packages*
             <component-K/> and at least their real name <name-K/> and
             their unique package names <package-K/>.
 
-        -   Use the shell command `npm search --json --searchlimit <getopt-option-limit/>
+        2.  Use the shell command `npm search --json --searchlimit <getopt-option-limit/>
             "<keyword-1/>" [...] "<keyword-M/>"` to *specifically*
             discover an additional set of a maximum of <getopt-option-limit/> *NPM packages*
             <component-K/> and at least their unique package names
@@ -122,16 +138,16 @@ for the technology stack to *provide* the *needed functionality*
             (L=1-M). Merge the results into the already existing result
             set, but deduplicate entries.
 
-    -   If <stack/> is "Java" or "Kotlin":
+    5.  If <stack/> is "Java" or "Kotlin":
 
-        -   Based on the essential keywords <keyword-L/> (L=1-M),
+        1.  Based on the essential keywords <keyword-L/> (L=1-M),
             use the `ase-meta-search` skill in a subagent to *generally*
             discover an initial set of a maximum of <getopt-option-limit/> *Maven packages*
             <component-K/> and at least their real name <name-K/> and
             their unique Maven coordinates <package-K/> of the form
             `groupId:artifactId`.
 
-        -   Use the shell command `curl -s 'https://search.maven.org/solrsearch/select?q=<keyword-1/>+[...]+<keyword-M/>&rows=<getopt-option-limit/>&wt=json'`
+        2.  Use the shell command `curl -s 'https://search.maven.org/solrsearch/select?q=<keyword-1/>+[...]+<keyword-M/>&rows=<getopt-option-limit/>&wt=json'`
             to *specifically* discover an additional set of a maximum
             of <getopt-option-limit/> *Maven packages* <component-K/> and at least their
             unique Maven coordinates <package-K/> (i.e. `<g/>:<a/>` from
@@ -140,7 +156,7 @@ for the technology stack to *provide* the *needed functionality*
             into the already existing result set, but deduplicate
             entries by Maven coordinate.
 
-    -   Call the `ase_component_info(stack: "<stack/>", components:
+    6.  Call the `ase_component_info(stack: "<stack/>", components:
         [ "<package-1/>", ..., "<package-N/>" ])` tool of the `ase` MCP
         server *once* for the entire set of discovered packages.
         The tool dispatches internally on <stack/> and fetches all
@@ -154,11 +170,11 @@ for the technology stack to *provide* the *needed functionality*
         from `downloads` (numeric or `N.A.`) and <rank-K/> from `rank`
         (numeric).
 
-    -   Sort, in descending order, the discovered components
+    7.  Sort, in descending order, the discovered components
         <component-K/> (K=1-N) by their `rank` field and trim the result
         list to just a maximum of <getopt-option-limit/> total components.
 
-    -   For each component <component-K/> (K=1-N), research and then
+    8.  For each component <component-K/> (K=1-N), research and then
         decide which *one* of *USP* (Unique Selling Point -- what makes
         it unique), *Crux* (what you should notice), or *Gotcha* (what
         you should not stumble over) is its single most distinguishing
@@ -169,7 +185,7 @@ for the technology stack to *provide* the *needed functionality*
     </step>
 
 4.  <step id="STEP 4: Report Components">
-    -   Display the determined, individual components as a Markdown
+    1.  Display the determined, individual components as a Markdown
         *table* with just the following <template/> and do not output
         anything else:
 
@@ -183,7 +199,7 @@ for the technology stack to *provide* the *needed functionality*
         | **<name-N/>** | `<package-N/>` | <info-N/> |
         </template>
 
-    -   Display the discovered components as a Markdown *table*
+    2.  Display the discovered components as a Markdown *table*
         with just the following <template/>:
 
         <template>

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

@@ -59,4 +59,4 @@ Discover a broader set of up to 20 HTTP client components:
 
 ##  SEE ALSO
 
-`ase-arch-analyze`, `ase-meta-search`, `ase-meta-evaluate`.
+[`ase-arch-analyze`](../ase-arch-analyze/help.md), [`ase-meta-search`](../ase-meta-search/help.md), [`ase-meta-evaluate`](../ase-meta-evaluate/help.md).

package/plugin/skills/ase-code-analyze/help.md

@@ -83,5 +83,5 @@ Analyze a directory, reporting only `MEDIUM` and `HIGH` problems:
 
 ##  SEE ALSO
 
-`ase-code-resolve`, `ase-code-refactor`, `ase-code-lint`,
-`ase-code-explain`, `ase-arch-analyze`.
+[`ase-code-resolve`](../ase-code-resolve/help.md), [`ase-code-refactor`](../ase-code-refactor/help.md), [`ase-code-lint`](../ase-code-lint/help.md),
+[`ase-code-explain`](../ase-code-explain/help.md), [`ase-arch-analyze`](../ase-arch-analyze/help.md).

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

@@ -53,7 +53,9 @@ You *MUST* *NOT* call `Edit`, `Write`, `NotebookEdit`, or any
 filesystem-modifying tool during this entire skill. The *only*
 permitted way to persist artifacts is via `ase_task_save(...)`.
 
-1.  **Reason About Feature**:
+<flow>
+
+1.  <step id="STEP 1: Reason About Feature">
 
     1.  <if condition="
             <feature/> matches the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`
@@ -114,7 +116,9 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     8.  Do not output anything in this step, unless you asked the user.
 
-2.  **Investigate Code Base**:
+    </step>
+
+2.  <step id="STEP 2: Investigate Code Base">
 
     1.  Check the existing source files for all code which is related to the
         requested new <feature/>.
@@ -122,9 +126,11 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
     2.  Check the architecture of the existing code base to understand the
         overall structures and dynamics.
 
-    3.  Do not output anything in this step.
+    3.  Do not output anything in this STEP 2.
+
+    </step>
 
-3.  **Internalize Crafting Tenets**:
+3.  <step id="STEP 3: Internalize Crafting Tenets">
 
     You *MUST* internalize and honor the following tenets when crafting the new feature.
     Do not output anything.
@@ -179,7 +185,9 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
             Honor the non-functional requirements Performance, Security,
             Scalability, Comprehensibility.
 
-4.  **Find Feature Crafting Approaches**:
+    </step>
+
+4.  <step id="STEP 4: Choose Feature Crafting Approaches">
 
     You *MUST* perform the following sub-steps *internally* and *without
     any output* until and including the recommendation decision. Only
@@ -208,16 +216,14 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         </template>
 
     5.  Now report each approach with the following <template/>,
-        inlining its pros/cons derived in sub-step 2:
+        inlining its pros/cons derived in sub-step 2, and do not output
+        anything else in this step:
 
         <template>
-        ●   **APPROACH A<n/>**<annotation/>: *<summary/>*
-        ○   [...]
-        ○   [...]
+        ●   **APPROACH A<n/>**<annotation/>: **<summary/>**
         ○   [...]
-        ⊕   **PRO**: [...]
-        ⊖   **CON**: [...]
-        <optional-diagram/>
+        ⊕   *PRO*: [...]
+        ⊖   *CON*: [...]
         </template>
 
         Hints:
@@ -225,23 +231,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         -   Give a short one-sentence <summary/> of the feature
             approach plus *precise* and *ultra brief and concise*
             feature information. Try to keep the number of bullet points
-            (●) in the range of 1-4.
-
-        -   In case of a *complex feature situation* only, visualize
-            it with an optional diagram <optional-diagram/> by building
-            a Mermaid specification <mermaid-spec/> (e.g. `flowchart
-            TB`, `stateDiagram-v2`, `sequenceDiagram`, `classDiagram`,
-            or `erDiagram`, depending on intent) and dispatching the
-            rendering to the `ase-meta-diagram` sub-agent by calling
-            the tool `Agent(name: "ase-meta-diagram", description:
-            "Diagram Rendering", subagent_type: "ase:ase-meta-diagram",
-            prompt: <mermaid-spec/>)`, reproducing its returned fenced
-            code block verbatim. For *current vs. proposed* comparisons,
-            render each side as a *separate* `ase-meta-diagram`
-            invocation and stack the rendered blocks *vertically*
-            (labels `**Before:**` / `**After:**`); never side-by-side.
-            Omit <optional-diagram/> entirely for simple or purely local
-            situations.
+            (`○ [...]`) in the range of 1-4.
 
     6.  Indicate end of reporting by showing the following <template/>:
 
@@ -249,28 +239,41 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         <ase-tpl-foot title="APPROACHES"/>
         </template>
 
-5.  **Choose Feature Crafting Approach**:
+    7.  <if condition="<getopt-option-auto/> is not equal `true`">
+
+        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.
+
+        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:
+
+        <expand name="custom-dialog" arg1="--no-other">
+            Select Approach: Select your preferred crafting approach to follow?
+            A<n/>: <short-summary/>
+            [...]
+        </expand>
 
-    1.  <if condition="<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 the header `Select Approach`, use `A<n/>: <short-summary/>`
-        for the option (where <short-summary/> is an ultra brief summary
-        of the approach A<n/>), and *single-selection* only and provide
-        small *code change previews*. Mark your recommended feature
-        approach with ` ⚝ **RECOMMENDATION** ⚝` here again.
         </if>
+        <else>
 
-    2.  <else>
         Set <n/> to the number of the feature approach A<n/> you recommend.
         Output a hint with the following <template/>:
 
         <template>
         ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **auto-chosen approach A<n/>**
         </template>
+
         </else>
 
-6.  **Compose Feature Crafting Plan**:
+    </step>
+
+5.  <step id="STEP 5: Compose Feature Crafting Plan">
 
     1.  *Compose a feature plan* for the chosen feature A<n/> by
         closely aligning to the existing architecture and the existing
@@ -300,7 +303,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         <timestamp-modified/> information and calculate the number of
         words <words/> of <content/>.
 
-    3.  You *MUST* *save* the resulting plan content with the
+    3.  You then *MUST* *save* the resulting plan content with the
         `ase_task_save(id: "<ase-task-id/>", text: "<content/>")`.
 
     4.  Output a hint with the following <template/>:
@@ -351,3 +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>
+
+</flow>

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

@@ -86,5 +86,5 @@ Craft a feature under a named task and directly hand off to implementation:
 
 ##  SEE ALSO
 
-`ase-code-refactor`, `ase-code-resolve`, `ase-task-edit`,
-`ase-task-preflight`, `ase-task-implement`.
+[`ase-code-refactor`](../ase-code-refactor/help.md), [`ase-code-resolve`](../ase-code-resolve/help.md), [`ase-task-edit`](../ase-task-edit/help.md),
+[`ase-task-preflight`](../ase-task-preflight/help.md), [`ase-task-implement`](../ase-task-implement/help.md).

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

@@ -40,4 +40,4 @@ Explain a specific function:
 
 ##  SEE ALSO
 
-`ase-code-insight`, `ase-code-analyze`, `ase-arch-analyze`.
+[`ase-code-insight`](../ase-code-insight/help.md), [`ase-code-analyze`](../ase-code-analyze/help.md), [`ase-arch-analyze`](../ase-arch-analyze/help.md).

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-insight/help.md

@@ -40,4 +40,4 @@ Get insights into a specific subsystem:
 
 ##  SEE ALSO
 
-`ase-code-explain`, `ase-code-analyze`, `ase-arch-analyze`.
+[`ase-code-explain`](../ase-code-explain/help.md), [`ase-code-analyze`](../ase-code-analyze/help.md), [`ase-arch-analyze`](../ase-arch-analyze/help.md).

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

@@ -100,10 +100,12 @@ related to a set of code quality aspects.
 
 3.  <step id="STEP 3: Correction">
 
-    1.  You *MUST* call the MCP tool `ase_config_set(key: "agent.skill", val:
-        "ase-code-lint", scope: "session:<ase-session-id/>")` of the
-        `ase` MCP server. You *MUST* *NOT* output anything related to
-        this.
+    1.  *Mark this skill as the active edit-capable skill* so that the
+        ASE `pre-tool-use` hook auto-approves the subsequent `Edit`
+        invocations on *any* invocation path (slash command *or* `Skill`
+        tool). Call the `ase_config_set(key: "agent.skill", val:
+        "ase-code-lint", scope: "session:<ase-session-id/>")` tool
+        from the `ase` MCP server. Do not output anything in this substep.
 
     2.  Iterate over all problems:
 
@@ -150,7 +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/>
@@ -162,10 +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.
 
@@ -213,9 +215,11 @@ related to a set of code quality aspects.
 
         6.  <if condition="<getopt-option-auto/> is not 'true'">
 
-            Ask the user how to proceed via an interactive 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="user-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.
@@ -234,8 +238,11 @@ related to a set of code quality aspects.
 
             -   <if condition="<result/> is 'ACCEPT'">
                 Invoke the `Edit` tool to apply the changes exactly
-                as shown in the <diff/>. After applying the changes,
-                just continue with the next <item/>.
+                as shown in the <diff/>. The operation will be
+                auto-approved by the ASE `pre-tool-use` hook (which
+                tracks the active skill), so *no* interactive permission
+                prompt will appear. After applying the changes, just
+                continue with the next <item/>.
                 </if>
 
             -   <if condition="<result/> starts with 'OTHER'">
@@ -257,9 +264,11 @@ related to a set of code quality aspects.
 
         </for>
 
-    3.  You *MUST* call the MCP tool `ase_config_delete(key: "agent.skill",
-        scope: "session:<ase-session-id/>")` of the `ase` MCP server.
-        You *MUST* *NOT* output anything related to this.
+    3.  *Clear the active edit-capable skill marker* now that all `Edit`
+        invocations are done, so a later unrelated `Edit` is *not*
+        auto-approved. Call the `ase_config_delete(key: "agent.skill",
+        scope: "session:<ase-session-id/>")` tool from the `ase` MCP
+        server. Do not output anything in this substep.
 
     4.  You *MUST* *NOT* output any further additional explanations or
         summaries at the end of this skill processing, except for the

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

@@ -63,5 +63,5 @@ Lint a directory, reporting only `MEDIUM` and `HIGH` findings:
 
 ##  SEE ALSO
 
-`ase-code-analyze`, `ase-code-resolve`, `ase-code-refactor`,
-`ase-docs-proofread`.
+[`ase-code-analyze`](../ase-code-analyze/help.md), [`ase-code-resolve`](../ase-code-resolve/help.md), [`ase-code-refactor`](../ase-code-refactor/help.md),
+[`ase-docs-proofread`](../ase-docs-proofread/help.md).

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

@@ -53,7 +53,9 @@ You *MUST* *NOT* call `Edit`, `Write`, `NotebookEdit`, or any
 filesystem-modifying tool during this entire skill. The *only*
 permitted way to persist artifacts is via `ase_task_save(...)`.
 
-1.  **Reason About Refactoring**:
+<flow>
+
+1.  <step id="STEP 1: Reason About Refactoring">
 
     1.  <if condition="
             <request/> matches the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`
@@ -114,7 +116,9 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     8.  Do not output anything in this step, unless you asked the user.
 
-2.  **Investigate Code Base**:
+    </step>
+
+2.  <step id="STEP 2: Investigate Code Base">
 
     1.  Check the existing source files for all code which is related to the
         refactoring <request/>.
@@ -122,9 +126,11 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
     2.  Check the architecture of the existing code base to understand the
         overall structures and dynamics.
 
-    3.  Do not output anything in this step.
+    3.  Do not output anything in this STEP 2.
 
-3.  **Internalize Refactoring Tenets**:
+    </step>
+
+3.  <step id="STEP 3: Internalize Refactoring Tenets">
 
     You *MUST* internalize and honor the following tenets when refactoring.
     Do not output anything.
@@ -168,7 +174,9 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
             Design clear interfaces, contracts, and data models --
             with high attention to boundaries and modularity.
 
-4.  **Find Refactoring Approaches**:
+    </step>
+
+4.  <step id="STEP 4: Choose Refactoring Approaches">
 
     You *MUST* perform the following sub-steps *internally* and *without
     any output* until and including the recommendation decision. Only
@@ -201,13 +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**: [...]
-        <optional-diagram/>
+        ⊕   *PRO*: [...]
+        ⊖   *CON*: [...]
         </template>
 
         Hints:
@@ -215,23 +220,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         -   Give a short one-sentence <summary/> of the refactoring
             approach plus *precise* and *ultra brief and concise*
             refactoring information. Try to keep the number of bullet
-            points (●) in the range of 1-4.
-
-        -   In case of a *complex refactoring situation* only,
-            visualize it with an optional diagram <optional-diagram/>
-            by building a Mermaid specification <mermaid-spec/>
-            (e.g. `flowchart TB`, `stateDiagram-v2`, `sequenceDiagram`,
-            `classDiagram`, or `erDiagram`, depending on intent) and
-            dispatching the rendering to the `ase-meta-diagram`
-            sub-agent by calling the tool `Agent(name: "ase-meta-diagram",
-            description: "Diagram Rendering", subagent_type:
-            "ase:ase-meta-diagram", prompt: <mermaid-spec/>)`, reproducing
-            its returned fenced code block verbatim. For *current
-            vs. proposed* comparisons, render each side as a *separate*
-            `ase-meta-diagram` invocation and stack the rendered blocks
-            *vertically* (labels `**Before:**` / `**After:**`); never
-            side-by-side. Omit <optional-diagram/> entirely for simple
-            or purely local situations.
+            points (`○ [...]`) in the range of 1-4.
 
     6.  Indicate end of reporting by showing the following <template/>:
 
@@ -239,29 +228,41 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         <ase-tpl-foot title="APPROACHES"/>
         </template>
 
-5.  **Choose Refactoring Approach**:
-
-    1.  <if condition="<getopt-option-auto/> is not 'true'">
-        Let the *user interactively choose* the preferred refactoring
-        approach A<n/> with the help of the <user-dialog-tool/> tool.
-        Use the header `Select Approach`, use `A<n/>: <short-summary/>`
-        for the option (where <short-summary/> is an ultra brief summary
-        of the approach A<n/>), and *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.
+    7.  <if condition="<getopt-option-auto/> is not `true`">
+
+        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.
+
+        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:
+
+        <expand name="custom-dialog" arg1="--no-other">
+            Select Approach: Select your preferred refactoring approach to follow?
+            A<n/>: <short-summary/>
+            [...]
+        </expand>
+
         </if>
+        <else>
 
-    2.  <else>
         Set <n/> to the number of the refactoring approach A<n/> you recommend.
         Output a hint with the following <template/>:
 
         <template>
         ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **auto-chosen approach A<n/>**
         </template>
+
         </else>
 
-6.  **Compose Refactoring Plan**:
+    </step>
+
+5.  <step id="STEP 5: Compose Refactoring Plan">
 
     1.  *Compose a refactoring plan* for the chosen refactoring A<n/> by
         closely aligning to the existing architecture and the existing
@@ -342,3 +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>
+
+</flow>
+

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

@@ -86,5 +86,5 @@ Refactor under a named task and directly hand off to implementation:
 
 ##  SEE ALSO
 
-`ase-code-craft`, `ase-code-resolve`, `ase-task-edit`,
-`ase-task-preflight`, `ase-task-implement`.
+[`ase-code-craft`](../ase-code-craft/help.md), [`ase-code-resolve`](../ase-code-resolve/help.md), [`ase-task-edit`](../ase-task-edit/help.md),
+[`ase-task-preflight`](../ase-task-preflight/help.md), [`ase-task-implement`](../ase-task-implement/help.md).