@rse/ase 0.9.43 → 0.9.45

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

@@ -285,9 +285,6 @@ over time.
     -   <spec-cj-step-name/> is a summary (5-10 words) of the *step* at its
         <spec-cj-step-touchpoint/>.
 
-    -   <spec-cj-step-actor/> is a `SPEC-PE-<spec-pe-persona-id/>` reference to the
-        corresponding **Aspect** of the Personas **Artifact**.
-
     -   <spec-cj-step-stage/> is one of:
 
         -   `Awareness`:     Customer is not aware of solution, but has a need.
@@ -297,6 +294,9 @@ over time.
         -   `Retention`:     Customer in the long-term stays a customer.
         -   `Advocacy`:      Customer is a fan of solution and tells the tribe.
 
+    -   <spec-cj-step-actor/> is a `SPEC-PE-<spec-pe-persona-id/>` reference to the
+        corresponding **Aspect** of the Personas **Artifact**.
+
     -   <spec-cj-step-goal/> is what the actor wants to achieve at this step.
 
     -   <spec-cj-step-touchpoint/> is where or how the interaction happens
@@ -311,7 +311,7 @@ over time.
         actor encounters at this step (optional).
 
     -   In case a <spec-cj-step/> has no pain point at all, the
-        entire `- Pain Point:` bullet point is omitted.
+        entire `-   Pain Point:` bullet point is omitted.
 
 Functional Requirements (FR)
 ----------------------------
@@ -518,7 +518,7 @@ constraining the Functional and Non-Functional Requirements.
         business rule.
 
     -   In case the rule constrains no specific requirement, the
-        entire `- Constrains:` bullet point is omitted.
+        entire `-   Constrains:` bullet point is omitted.
 
     -   In case the rationale is not present, the
         entire `, **BECAUSE** [...]` clause is omitted.
@@ -656,24 +656,24 @@ manages, defining how information is organized and connected.
 
     With:
 
-    -    <export-table-1/> is a Markdown table for the attributes with one
-         row per <spec-dm-attribute-id/>, sorted by <spec-dm-attribute-id/>
-         -- with the columns:
+    -   <export-table-1/> is a Markdown table for the attributes with one
+        row per <spec-dm-attribute-id/>, sorted by <spec-dm-attribute-id/>
+        -- with the columns:
 
-         -   `Attribute`     (`**<spec-dm-attribute-id/>**`)
-         -   `Type`          (`<spec-dm-attribute-qualifier/><spec-dm-attribute-type/>`)
-         -   `Description`   (`<spec-dm-attribute-description/>, **BECAUSE** <spec-dm-attribute-rationale/>.`)
+        -   `Attribute`     (`**<spec-dm-attribute-id/>**`)
+        -   `Type`          (`<spec-dm-attribute-qualifier/><spec-dm-attribute-type/>`)
+        -   `Description`   (`<spec-dm-attribute-description/>, **BECAUSE** <spec-dm-attribute-rationale/>.`)
 
-    -    <export-table-2/> is a Markdown table for the relation with one
-         row per <spec-dm-relation-id/>, sorted by <spec-dm-relation-id/> --
-         with the columns:
+    -   <export-table-2/> is a Markdown table for the relation with one
+        row per <spec-dm-relation-id/>, sorted by <spec-dm-relation-id/> --
+        with the columns:
 
-         -   `Relation`      (`**<spec-dm-relation-id/>**`)
-         -   `Target`        (`[<spec-dm-relation-target/>](#<spec-dm-relation-target-id/>) (<spec-dm-relation-cardinality/>)`)
-         -   `Description`   (`<spec-dm-relation-description/>, **BECAUSE** <spec-dm-relation-rationale/>.`)
+        -   `Relation`      (`**<spec-dm-relation-id/>**`)
+        -   `Target`        (`[<spec-dm-relation-target/>](#<spec-dm-relation-target-id/>) (<spec-dm-relation-cardinality/>)`)
+        -   `Description`   (`<spec-dm-relation-description/>, **BECAUSE** <spec-dm-relation-rationale/>.`)
 
-    -    In case a <spec-dm-entity/> has no relations at all, the
-         entire `### RELATIONS` block (including <export-table-2/>) is omitted.
+    -   In case a <spec-dm-entity/> has no relations at all, the
+        entire `### RELATIONS` block (including <export-table-2/>) is omitted.
 
 -   Export: `export.svg`
 
@@ -853,7 +853,7 @@ ambiguities to avoid, shared consistently across all Artifacts.
         <spec-gl-term-name/> where helpful.
 
     -   In case a term has no synonyms, the
-        entire `- Synonyms:` bullet point is omitted.
+        entire `-   Synonyms:` bullet point is omitted.
 
 Use Cases (UC)
 --------------
@@ -932,7 +932,7 @@ for main, alternative, and exceptional paths.
         **SCENARIO** blocks of this use case).
 
     -   In case the use case realizes no specific functional requirement,
-        the entire `- Requirements:` bullet point is omitted.
+        the entire `-   Requirements:` bullet point is omitted.
 
     -   In case a precondition or postcondition is not present, the
         respective bullet point is omitted.
@@ -1271,13 +1271,13 @@ turn.
 
     -   <spec-ds-storyboard-usecase/> is a
         `SPEC-UC-<spec-uc-usecase-id/>` reference to the corresponding
-        **Aspect** of the Use Case **Artifact** the storyboard
+        **Aspect** of the Use Cases **Artifact** the storyboard
         visualizes (optional).
 
     -   <spec-ds-storyboard-scenario/> is a
         `SPEC-UC-<spec-uc-usecase-id/>-<spec-uc-usecase-scenario-id/>`
         reference to the corresponding scenario **Aspect** of the Use
-        Case **Artifact** the storyboard visualizes (optional).
+        Cases **Artifact** the storyboard visualizes (optional).
 
     -   <spec-ds-frame-name/>: a short (2-5 word) label for the screen,
         turn, or state depicted by the storyboard frame. Frames are

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

@@ -40,8 +40,8 @@ You *MUST* honor the following hints on this *task* format:
     <template>`<code/>`</template> and *key aspects* as
     <template>*<aspect/>*</template>.
 
--   For <summary-what/> and <summary-why/> use *ultra brief* but
-    as *very precise* as possible description of the overall change. In
+-   For <summary-what/> and <summary-why/> use an *ultra brief* but
+    *as precise as possible* description of the overall change. In
     <summary-what/> tell what is changed. In <summary-why/> tell why it
     is changed, what benefit results or what the rationale is behind the
     change.
@@ -49,19 +49,17 @@ You *MUST* honor the following hints on this *task* format:
 -   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
-    specification was last modified. Both use an ISO-style format
-    value. The value of both can be determined by
-    a call to the `ase_timestamp(format: "yyyy-LL-dd HH:mm")`
-    tool of the `ase` MCP server and use the `text` field of
-    its response.
+-   The <timestamp-created/> is the timestamp when this task plan was
+    created. The <timestamp-modified/> is the timestamp when this
+    task plan was last modified. Both use an ISO-style format
+    value. The value of both can be determined by a call to the
+    `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of the `ase` MCP
+    server and use the `text` field of its response.
 
 -   The <title/> is a short summary of the <summary-what/>, no longer than
     50 characters.
 
--   The sections `##  CHANGES` and `##  VERIFICATION` all are just a short
+-   The sections `##  CHANGES` and `##  VERIFICATION` are each just a short
     list of 1-5 bullet points. Each bullet point is formatted as
     `- **<aspect/>**: <specification/>` where <aspect/> indicates
     the aspect of the section and <specification/> is 1-3 sentences

package/plugin/meta/ase-getopt.md

@@ -20,7 +20,7 @@ set placeholders into the context as a side-effect.
     3-6 are *structurally unreachable* and you *MUST NOT* call the
     `ase_getopt` MCP tool under any circumstances.
 
-    <if condition="<getopt-args/> does *NOT* match the regexp `(^|\s)-` (i.e. it does not start with an option)">
+    <if condition="<getopt-args/> does *NOT* match the regexp `(^|\s)-` (i.e. it does not contain an option)">
         Parse the options *locally*, without any MCP call:
 
         For each option token in <getopt-spec/> of the form

package/plugin/meta/ase-persona.md

@@ -18,7 +18,7 @@ requested communication style at any time during a session.
 -   If <ase-persona-style/> is `caveman`:
     You *MUST* use the terse, rough, and stuttering communication style of a *caveman*.
 
--   If <ase-persona-style/> is `writer`, `engineer`, `journalist`, `telegrapher` or `caveman`:
+-   If <ase-persona-style/> is `writer`, `engineer`, `journalist`, `telegrapher`, or `caveman`:
     -   You *MUST* *always keep* technical terms exactly, independent of other persona rules below.
     -   You *MUST* *always keep* errors quoted exactly, independent of other persona rules below.
     -   You *MUST* *always keep* code blocks unchanged, independent of other persona rules below.
@@ -28,7 +28,7 @@ requested communication style at any time during a session.
     -   You *MUST* bundle related aspects into paragraphs.
     -   You *MUST* output blank lines between paragraphs.
 
--   If <ase-persona-style/> is `engineer`, `journalist`, `telegrapher` or `caveman`:
+-   If <ase-persona-style/> is `engineer`, `journalist`, `telegrapher`, or `caveman`:
     -   You *MUST* use `○` as the bullet point marker symbol in bullet point lists.
     -   You *MUST* *drop* filler words
         ("just", "really", "basically", "actually", "simply", etc).
@@ -62,7 +62,7 @@ requested communication style at any time during a session.
         -   <keywords/> is only one to four keywords summarizing the <details/>
         -   <details/> is one to four prose sentences explaining the aspect
 
--   If <ase-persona-style/> is `telegrapher` or `caveman`:
+-   If <ase-persona-style/> is `telegrapher`, or `caveman`:
     -   You *MUST* *use only* bullet point lists without blank lines between bullet points.
     -   You *MUST* *use only* one bullet point per explanation aspect.
     -   You *MUST* *use* shorter synonyms

package/plugin/meta/ase-skill.md

@@ -218,7 +218,7 @@ Skill Identification
     following output <template/>:
 
     <template>
-    ⧉ **ASE**: ✪ skill: **<skill-name/>**, status: **skill finished**
+    ⧉ **ASE**: ✪ skill: **<skill-name/>**, ▶ status: **skill finished**
     </template>
 
 -   *IMPORTANT*: Set <objective></objective> (set to empty).
@@ -299,7 +299,7 @@ Template Patterns
 
     <template>
 
-    ╭────────────────────────────────────────────────────────────────────┈┈┈┈┈┈┈┈┈
+    ╭───────────────────────────────────────────────────────────────────┈┈┈┈┈┈┈┈┈┈
 
     </template>
 
@@ -330,7 +330,7 @@ Template Patterns
     <raw-title-len/> is the number of characters in <raw-title/>,
     and <bar/> is the `─` character repeated exactly max(0, 67 -
     <raw-title-len/>) times -- clamped to zero so an over-long title
-    never yields a negative count.
+    never yields a negative count):
 
     <template>
 

package/plugin/meta/ase-tenets.md

@@ -5,7 +5,7 @@ ASE Tenets
 The following are the **ASE Tenets** -- the guiding principles you
 *MUST* internalize when requested. They are organized into *Generic
 Tenets*, which always apply, and *Operation-Specific Tenets*, which
-apply only to a particular kind of operation (Crafting, Aligning,
+apply only to a particular kind of operation (Crafting, Reconciling,
 Refactoring, Resolving).
 
 GENERIC TENETS
@@ -80,7 +80,7 @@ CRAFTING TENETS
 ---------------
 
 When *crafting* from scratch a new artifact, a feature, or an aspect,
-you *MUST* honor the following so-called "CRAFTING TENETS":
+you *MUST* honor the following so-called **CRAFTING TENETS**:
 
 -   **Clear Minimal Scope**:
     Establish explicit boundaries for the new feature.
@@ -167,7 +167,7 @@ REFACTORING TENETS
 ------------------
 
 When *refactoring* existing artifacts or aspects,
-you *MUST* honor the following so-called **REFACTORING TENETS**
+you *MUST* honor the following so-called **REFACTORING TENETS**:
 
 -   **Behavior Preservation**:
     Refactoring changes only re-structure, never change any
@@ -200,7 +200,7 @@ RESOLVING TENETS
 ----------------
 
 When *resolving* a problem or challenge (bug-fixing),
-you *MUST* honor the following so-called **RESOLVING TENETS**
+you *MUST* honor the following so-called **RESOLVING TENETS**:
 
 -   **No Cleanups**:
     Strictly focus on resolving the problem and do not mix the task with

package/plugin/package.json

@@ -3,23 +3,23 @@
     "description":                          "Agentic Software Engineering (ASE)",
     "private":                              true,
     "keywords":                             [ "agentic", "ai", "coding", "tool", "cli", "software", "engineering" ],
-    "homepage":                             "http://github.com/rse/ase",
+    "homepage":                             "https://ase.tools",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
-    "bugs":                                 { "url": "http://github.com/rse/ase/issues" },
-    "version":                              "0.9.43",
+    "bugs":                                 { "url": "https://github.com/rse/ase/issues" },
+    "version":                              "0.9.45",
     "license":                              "Apache-2.0",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",
         "email":                            "rse@engelschall.com",
-        "url":                              "http://engelschall.com"
+        "url":                              "https://engelschall.com"
     },
     "devDependencies": {
         "@rse/stx":                         "1.1.6",
-        "markdownlint":                     "0.41.0",
-        "markdownlint-cli2":                "0.23.0",
-        "eslint":                           "10.6.0",
+        "markdownlint":                     "0.41.1",
+        "markdownlint-cli2":                "0.23.1",
+        "eslint":                           "10.7.0",
         "@eslint/markdown":                 "8.0.3",
-        "eslint-markdown":                  "0.12.0"
+        "eslint-markdown":                  "0.12.1"
     },
     "engines": {
         "npm":                              ">=10.0.0",

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

@@ -4,7 +4,6 @@ argument-hint: "[--help|-h] <source-reference>"
 description: Review software architecture, including package cohesion and inter-package coupling
 user-invocable: true
 disable-model-invocation: false
-model: opus
 effort: high
 allowed-tools:
     - "Bash(wc *)"
@@ -252,7 +251,7 @@ interface quality, quality attributes, and architecture governance.
       - *god-package*: *incoming ≥ 5* and *outgoing ≥ 3* -
         coordinator dumping ground that should be split along its
         internal topical clusters
-      - *fragment*: 1–2 files under a sibling parent that share a
+      - *fragment*: 1-2 files under a sibling parent that share a
         *name prefix* or *imported interface* with that sibling -
         consolidation candidate
 
@@ -278,7 +277,7 @@ interface quality, quality attributes, and architecture governance.
       which operations sit *between* the specific acquire and
       release in source order.
 
-    - *Package-graph construction (SA19–SA21)*: parse each file's
+    - *Package-graph construction (SA19-SA21)*: parse each file's
       import (or equivalent language construct) statement, keep
       only first-party packages within the analyzed scope, and
       persist two intermediate structures: the per-package

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

@@ -12,8 +12,8 @@
 ##  DESCRIPTION
 
 The `ase-arch-analyze` skill reviews the *software architecture* of
-the referenced source code, including *package cohesion* and *inter-
-package coupling*, for *potential problems* across component boundaries,
+the referenced source code, including *package cohesion* and
+*inter-package coupling*, for *potential problems* across component boundaries,
 structural organization, architecture principles, interface quality,
 quality attributes, and architecture governance.
 

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

@@ -134,7 +134,7 @@ for the technology stack to *provide* the *needed functionality*
     4.  If <stack/> is "JavaScript" or "TypeScript":
 
         1.  Based on the essential keywords <keyword-L/> (L=1-M),
-            use the `ase-meta-search` skill in a subagent to *generally*
+            use the `ase-meta-search` skill in a sub-agent to *generally*
             discover an initial set of a maximum of <pool/> *NPM packages*
             <component-K/> and at least their real name <name-K/> and
             their unique package names <package-K/>.
@@ -150,7 +150,7 @@ for the technology stack to *provide* the *needed functionality*
     5.  If <stack/> is "Java" or "Kotlin":
 
         1.  Based on the essential keywords <keyword-L/> (L=1-M),
-            use the `ase-meta-search` skill in a subagent to *generally*
+            use the `ase-meta-search` skill in a sub-agent to *generally*
             discover an initial set of a maximum of <pool/> *Maven packages*
             <component-K/> and at least their real name <name-K/> and
             their unique Maven coordinates <package-K/> of the form

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

@@ -33,8 +33,9 @@ demotes dependency-heavy components.
 ##  OPTIONS
 
 `--limit`|`-l=12`:
-    The *maximum* number of components searched per source and retained
-    in the final ranking (default: 12). Raise it for a broader, more
+    The *maximum* number of components retained in the final ranking
+    (default: 12); each discovery source may fetch up to twice this
+    number of candidates for ranking. Raise it for a broader, more
     exhaustive survey, lower it for a quicker, narrower lookup.
 
 `--staleness`|`-s=18`:

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

@@ -199,7 +199,6 @@ problems in *performance* and *efficiency*, or problems in *security*.
     Finally, output the following <template/> to give a final hint:
 
     <template>
-    ⧉ **ASE**: ☻ skill: **<skill-name/>**, ▶ status: **skill finished**
     ⧉ **ASE**: ↪ hint: **For deeper analysis, suggestions on solution approaches and then final problem resolution, use `/ase-code-resolve P{n}` in the same or even a different session.**
     </template>
 

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

@@ -2,7 +2,7 @@
 name: ase-code-craft
 argument-hint: "[--help|-h] [--auto|-a] [--dry|-d] [--quick|-Q] [--next|-n <option>[,...]] [<task-id>:] <feature>"
 description: >
-    Craft Source:
+    Craft Source Code:
     Use when user wants to "create", "add", or "craft" a new feature from scratch.
 user-invocable: true
 disable-model-invocation: false
@@ -109,7 +109,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
     7.  Ask the user for clarification if the goal of this crafting is too
         unclear.
 
-    8.  Do not output anything in this step, unless you asked the user.
+    8.  Do not output anything else in this step, unless you asked the user.
 
     </step>
 
@@ -139,15 +139,15 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     You *MUST* perform the following sub-steps *internally* and *without
     any output* until and including the recommendation decision. Only
-    sub-steps 4-6 below are allowed to produce output, and only if
+    sub-steps 4-7 below are allowed to produce output; sub-steps 4-6 only if
     <getopt-option-auto/> is equal `false` *and* <ase-project-boxing/>
     is *not* equal `black`.
 
     If <getopt-option-auto/> is equal `true` or <ase-project-boxing/> is
-    equal `black`, *skip* the reporting sub-steps 4-6 entirely (perform
-    no output at all) to speed up processing.
+    equal `black`, *skip* the reporting sub-steps 4-6 entirely (they
+    perform no output at all) to speed up processing.
 
-    1.  *Propose* corresponding *feature approach*, including optionally,
+    1.  *Propose* a corresponding *feature approach*, optionally including
         some *alternative* feature approaches. Do *not* output anything
         in this sub-step.
 
@@ -231,18 +231,18 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         closely aligning to the existing architecture and the existing
         code base. Use the <format/> defined for a task plan and inject
         the information from feature A<n/> and all derived realization
-        decisions into it. Store the resulting task plan in <content/>.
+        decisions into it. Store the resulting task plan in <task-content/>.
 
         If a `CHANGELOG.md` file exists in the project (or in any
         affected sub-package), the plan *MUST* include, as part of its
-        `## ※ CHANGES` section, an explicit bullet point describing
+        `##  CHANGES` section, an explicit bullet point describing
         the addition of a corresponding new entry to that `CHANGELOG.md`
         file, aligned with its existing style and conventions.
 
         <if condition="<getopt-option-dry/> is equal `true`">
         You *MUST* completely omit the `##  VERIFICATION` section
         (including its heading and all of its bullet points) from
-        <content/>.
+        <task-content/>.
         </if>
 
         You *MUST* *NOT* call `Edit`, `Write`, `NotebookEdit`, or any
@@ -253,10 +253,10 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         <timestamp-created/> and <timestamp-modified/> information. Then
         insert the current <ase-task-id/>, <timestamp-created/>, and
         <timestamp-modified/> information and calculate the number of
-        words <words/> of <content/>.
+        words <words/> of <task-content/>.
 
     3.  You then *MUST* *save* the resulting plan content with the
-        `ase_task_save(id: "<ase-task-id/>", text: "<content/>")`.
+        `ase_task_save(id: "<ase-task-id/>", text: "<task-content/>")`.
 
     4.  Output a hint with the following <template/>:
 

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

@@ -104,7 +104,7 @@ related to a set of code quality aspects.
     *silently drop* all other problems. With the default floor `LOW`, all
     problems are kept. `ACCEPTED` problems are *never* dropped.
 
-    You *MUST* *NOT* output anything else in this step 1.
+    You *MUST* *NOT* output anything else in this STEP 1.
 
     </step>
 
@@ -131,7 +131,7 @@ related to a set of code quality aspects.
     *(no problems detected)*
     </template>
 
-    You *MUST* *NOT* output anything else in this step 2.
+    You *MUST* *NOT* output anything else in this STEP 2.
 
     </step>
 
@@ -154,11 +154,14 @@ related to a set of code quality aspects.
         still perform substep 3 first. Never leave this marker active
         for a later, unrelated `Edit`.
 
-    2.  Iterate over all problems:
+    2.  Set <total/> to the number of problems in <problems/> and
+        <index/> to `0`. Then iterate over all problems:
 
         <for items="<problems/>">
 
-        1.  Set <aspect/>      to the `aspect`      field of <item/>.
+        1.  Increment <index/> by one (the 1-based position of the
+            current <item/> within <problems/>).
+            Set <aspect/>      to the `aspect`      field of <item/>.
             Set <severity/>    to the `severity`    field of <item/>.
             Set <description/> to the `description` field of <item/>.
             Set <change-set/>  to the `change-set`  field of <item/>.
@@ -193,6 +196,19 @@ related to a set of code quality aspects.
                     Set <new-text/>       to the `new_text`       field of <item/>.
                     Set <context-after/>  to the `context_after`  field of <item/>.
 
+                    Then *normalize* the hunk to its *minimal* form, so
+                    that the proposed diff shows exactly the lines the
+                    later `Edit` will actually change: while the *first*
+                    line of <old-text/> is identical to the *first* line
+                    of <new-text/>, *move* that line from both to the
+                    end of <context-before/> and increment <line/> by
+                    one; likewise, while the *last* line of <old-text/>
+                    is identical to the *last* line of <new-text/>,
+                    *move* that line from both to the front of
+                    <context-after/>. Finally, *trim* <context-before/>
+                    to its *last* two lines and <context-after/> to its
+                    *first* two lines.
+
                 2.  *Skip* this substep entirely when <ase-project-boxing/>
                     is equal `grey` - the full unified diff is suppressed
                     there, so none of the <hunk-body/>, <old-count/>,
@@ -288,13 +304,13 @@ related to a set of code quality aspects.
         4.  Report the problem with the following <template/>:
 
             <template>
-            <ase-tpl-bullet-signal/> **<aspect/> PROBLEM** (`<severity/>`): <context/>
+            <ase-tpl-bullet-signal/> [<index/>/<total/>]: **<aspect/> PROBLEM** (`<severity/>`): <context/>
 
             <description/>
 
             </template>
 
-        5.  <if condition="<getopt-option-auto/> is not 'true' and <ase-project-boxing/> is not equal `black`">
+        5.  <if condition="<getopt-option-auto/> is not equal `true` and <ase-project-boxing/> is not equal `black`">
 
             <if condition="<ase-project-boxing/> is equal `grey`">
 
@@ -341,7 +357,7 @@ related to a set of code quality aspects.
 
             </else>
 
-        6.  <if condition="<getopt-option-auto/> is not 'true'">
+        6.  <if condition="<getopt-option-auto/> is not equal `true`">
 
             In the following, you *MUST* *NOT* use your built-in
             <user-dialog-tool/> tool! Instead, you *MUST* just show a
@@ -359,7 +375,7 @@ related to a set of code quality aspects.
             <else>
 
             Set <result>ACCEPT</result>.
-            You *MUST* *NOT* output anything else in this step 6.
+            You *MUST* *NOT* output anything else in this sub-step 6.
 
             </else>
 
@@ -367,11 +383,13 @@ 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/>. 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/>.
+                as given by the hunks of the current <change-set/>
+                (rendered as <diff/>, unless suppressed under grey
+                boxing). 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'">

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

@@ -3,7 +3,7 @@ name: ase-code-refactor
 argument-hint: "[--help|-h] [--auto|-a] [--dry|-d] [--quick|-Q] [--next|-n <option>[,...]] [<task-id>:] <request>"
 description: >
     Refactor Code:
-    Use when user wants to "refactor", or "change" the code base.
+    Use when user wants to "refactor" or "change" the code base.
 user-invocable: true
 disable-model-invocation: false
 effort: xhigh
@@ -18,7 +18,7 @@ allowed-tools:
 @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
 
 <skill name="ase-code-refactor">
-Refactor Artifacts
+Refactor Source Code
 </skill>
 
 <expand name="getopt"
@@ -109,7 +109,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
     7.  Ask the user for clarification if the goal of this refactoring is
         too unclear.
 
-    8.  Do not output anything in this step, unless you asked the user.
+    8.  Do not output anything else in this step, unless you asked the user.
 
     </step>
 
@@ -139,16 +139,16 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     You *MUST* perform the following sub-steps *internally* and *without
     any output* until and including the recommendation decision. Only
-    sub-steps 4-6 below are allowed to produce output, and only if
+    sub-steps 4-7 below are allowed to produce output; sub-steps 4-6 only if
     <getopt-option-auto/> is equal `false` *and* <ase-project-boxing/>
     is *not* equal `black`.
 
     If <getopt-option-auto/> is equal `true` or <ase-project-boxing/> is
-    equal `black`, *skip* the reporting sub-steps 4-6 entirely (perform
-    no output at all) to speed up processing.
+    equal `black`, *skip* the reporting sub-steps 4-6 entirely (they
+    perform no output at all) to speed up processing.
 
-    1.  *Propose* corresponding *refactoring approach*, including
-        optionally, some *alternative* refactoring approaches. Do *not*
+    1.  *Propose* a corresponding *refactoring approach*, optionally
+        including some *alternative* refactoring approaches. Do *not*
         output anything in this sub-step.
 
     2.  *Reflect* on and *critique* the proposed approaches by deriving,
@@ -231,18 +231,18 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         closely aligning to the existing architecture and the existing
         code base. Use the <format/> defined for a task plan and inject
         the information from refactoring A<n/> and all derived realization
-        decisions into it. Store the resulting task plan in <content/>.
+        decisions into it. Store the resulting task plan in <task-content/>.
 
         If a `CHANGELOG.md` file exists in the project (or in any
         affected sub-package), the plan *MUST* include, as part of its
-        `## ※ CHANGES` section, an explicit bullet point describing
+        `##  CHANGES` section, an explicit bullet point describing
         the addition of a corresponding new entry to that `CHANGELOG.md`
         file, aligned with its existing style and conventions.
 
         <if condition="<getopt-option-dry/> is equal `true`">
         You *MUST* completely omit the `##  VERIFICATION` section
         (including its heading and all of its bullet points) from
-        <content/>.
+        <task-content/>.
         </if>
 
         You *MUST* *NOT* call `Edit`, `Write`, `NotebookEdit`, or any
@@ -253,10 +253,10 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         <timestamp-created/> and <timestamp-modified/> information. Then
         insert the current <ase-task-id/>, <timestamp-created/>, and
         <timestamp-modified/> information and calculate the number of
-        words <words/> of <content/>.
+        words <words/> of <task-content/>.
 
     3.  You then *MUST* *save* the resulting plan content with the
-        `ase_task_save(id: "<ase-task-id/>", text: "<content/>")`.
+        `ase_task_save(id: "<ase-task-id/>", text: "<task-content/>")`.
 
     4.  Output a hint with the following <template/>:
 

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

@@ -56,7 +56,7 @@ plan via `ase_task_save` and then hands off to `ase-task-edit`,
     skill. For all other head tokens, the *entire* list is forwarded
     to `ase-task-edit`, which consumes its head itself. This lets an
     entire pipeline be pre-scripted in one shot. Recognized tokens at
-    this skill: `none` (default, hand-off to `ase-task-edit`
+    this skill: `none` (default, hand off to `ase-task-edit`
     interactively), `DONE` (stop), `EDIT` (hand off to
     `ase-task-edit`), `PREFLIGHT` (hand off to `ase-task-preflight`),
     or `IMPLEMENT` (hand off to `ase-task-implement`). Example: