@rse/ase 0.0.55 → 0.0.56

package/package.json

@@ -6,7 +6,7 @@
     "homepage":                             "http://github.com/rse/ase",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
     "bugs":                                 { "url": "http://github.com/rse/ase/issues" },
-    "version":                              "0.0.55",
+    "version":                              "0.0.56",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

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

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.0.55",
+    "version":     "0.0.56",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

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

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.0.55",
+    "version":     "0.0.56",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/agents/ase-meta-search.md

@@ -4,8 +4,8 @@ description: Query the Web
 model: sonnet
 effort: low
 tools:
-    - "mcp__perplexity__perplexity_search"
-    - "mcp__brave__brave_web_search"
+    - "mcp__search-perplexity__perplexity_search"
+    - "mcp__search-brave__brave_web_search"
     - "mcp__search-exa__web_search_exa"
     - "WebSearch"
 ---

package/plugin/meta/ase-control.md

@@ -16,12 +16,12 @@ Control Flow Constructs
 -   *IMPORTANT*: You *MUST* honor the following control flow construct:
     <expand name="<define-name/>" [arg1="<expand-arg1/>" [arg2="<expand-arg2/>" [...]]]><expand-content/></expand>:
 
-    This specifies the *expansion* of previous <define/>.
-    This construct is expanded into the <define-body/> of <define/>
-    with `<args/>` substituted with `<expand-arg1/> <expand-arg2/>
-    [...]`, `<arg1/>` substituted with <expand-arg1/>, and `<content/>`
-    substituted with <expand-content/>.
-    Do not output anything else.
+    This specifies the *expansion* of previous <define/>. This
+    construct is expanded to the <define-body/> of <define/> with
+    `<args/>` substituted with `<expand-arg1/> <expand-arg2/> [...]`,
+    `<arg1/>` substituted with <expand-arg1/>, `<arg2/>` substituted
+    with <expand-arg2/>, etc, and `<content/>` substituted with
+    <expand-content/>. Do not output anything else.
 
 -   *IMPORTANT*: You *MUST* honor the following control flow construct:
     <flow><flow-body/></flow>:

package/plugin/meta/ase-dialog.md

@@ -38,7 +38,7 @@ Let the *user interactively choose* an answer.
 
             Start with <n>0</n> (set entry count to zero).
             <for items="2 3 4 5">
-                Take from <config/> the line number <item/>.
+                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/>`.
                 If <config/> is not empty, set <config><config/>, </config> (append comma).
@@ -93,7 +93,7 @@ Let the *user interactively choose* an answer.
 
             Start with <n>0</n> (set entry count to zero).
             <for items="2 3 4 5">
-                Take from <config/> the line number <item/>.
+                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/>`.
                 If <config/> is not empty, set <config><config/>, </config> (append comma).

package/plugin/meta/ase-getopt.md

@@ -20,13 +20,14 @@ set placeholders into the context as a side-effect.
     then just silently *SKIP* the following steps 3-7!
 
 3.  **MCP Call**:
-    Call the `ase_getopt(name: <getopt-skill/>, spec: <getopt-spec/>, args:
-    <getopt-args/>)` tool of the `ase` MCP server and set <text/> to the
-    `text` output field of this tool call. The `spec` syntax for each
-    option token is `--<long>[|-<short>][=<default>|=(<c1>|<c2>|...)]`,
-    where `=<default>` declares a value-taking option with a default,
-    and `=(<c1>|<c2>|...)` declares a value-taking option restricted to
-    the listed fixed choices (the first choice acts as the default).
+    Call the `ase_getopt(name: "<getopt-skill/>", spec:
+    "<getopt-spec/>", args: "<getopt-args/>")` tool of the `ase`
+    MCP server and set <text/> to the `text` output field of
+    this tool call. The `spec` syntax for each option token is
+    `--<long>[|-<short>][=<default>|=(<c1>|<c2>|...)]`, where
+    `=<default>` declares a value-taking option with a default, and
+    `=(<c1>|<c2>|...)` declares a value-taking option restricted to the
+    listed fixed choices (the first choice acts as the default).
 
 4.  **Short-Circuit for Error**:
     If <text/> starts with `ERROR:`:
@@ -47,14 +48,15 @@ set placeholders into the context as a side-effect.
     {
         "opts": { "<long1/>": <value1/>, "<long2/>": <value2/>, ... },
         "argv": [ "<arg1/>", "<arg2/>", ... ],
-        "args": "..."
+        "args": "...",
+        "info": "..."
     }
     ```
 
 6.  **Materializing into Context**:
-    For each *key* `<long/>` in <getopt-result/>`.opts`:
-    Set <getopt-option-<long/>/> to the corresponding value from
-    `<getopt-result/>.opts[<long/>]`.
+    For each *key* `<longN/>` in <getopt-result/>`.opts`:
+    Set <getopt-option-<longN/>/> to the corresponding value
+    `<getopt-result/>.opts[<longN/>]`.
     Set <getopt-arguments/> to the value of `<getopt-result/>.args`.
     Set <getopt-info/> to `<getopt-result/>.info`.
 

package/plugin/package.json

@@ -6,7 +6,7 @@
     "homepage":                             "http://github.com/rse/ase",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
     "bugs":                                 { "url": "http://github.com/rse/ase/issues" },
-    "version":                              "0.0.55",
+    "version":                              "0.0.56",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

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

@@ -131,12 +131,13 @@ 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:
-        [ <package-1/>, ..., <package-N/> ])` tool of the `ase` MCP
+    -   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
         metadata in maximum parallel and returns an array of objects `{
-        name, version, time, repository, stars, downloads }`. For each
+        name, version, created, updated, repository, stars, downloads,
+        rank }`. For each
         component <component-K/> (K=1-N) read from its corresponding
         entry: <version-K/> from `version`, <updated-K/> from `updated`,
         <created-K/> from `created`, <repository-K/> from `repository`,

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

@@ -61,7 +61,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         ">
         Set <ase-task-id><feature/></ase-task-id> (set task id to feature)
         and <feature></feature> (set feature empty), call the
-        `ase_task_id(id: <ase-task-id/>, session: <ase-session-id/>)` tool
+        `ase_task_id(id: "<ase-task-id/>", session: "<ase-session-id/>")` tool
         from the `ase` MCP server to switch the task, and then only
         output the following <template/>:
 
@@ -73,8 +73,8 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
     2.  If <feature/> has the format `<id/>: <text/>` where <id/> matches
         the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`, then set
         <feature><text/></feature> and <ase-task-id><id/></ase-task-id>
-        and call the `ase_task_id(id: <ase-task-id/>, session:
-        <ase-session-id/>)` tool from the `ase` MCP server to
+        and call the `ase_task_id(id: "<ase-task-id/>", session:
+        "<ase-session-id/>")` tool from the `ase` MCP server to
         implicitly switch the task. Do not output anything.
 
     3.  If <feature/> is empty,
@@ -91,8 +91,8 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         ">
         Set <ase-task-id/> to a unique task id, derived from <feature/>,
         which consists of two lower-case words concatenated with a
-        `-` character. Then call the `ase_task_id(id: <ase-task-id/>,
-        session: <ase-session-id/>)` tool from the `ase` MCP server to
+        `-` character. Then call the `ase_task_id(id: "<ase-task-id/>",
+        session: "<ase-session-id/>")` tool from the `ase` MCP server to
         implicitly switch the task. Do not output anything.
         </if>
 
@@ -279,7 +279,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         words <words/> of <content/>.
 
     3.  You *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: "<content/>")`.
 
     4.  Output a hint with the following <template/>:
 

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

@@ -61,7 +61,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         ">
         Set <ase-task-id><request/></ase-task-id> (set task id to request)
         and <request></request> (set request empty), call the
-        `ase_task_id(id: <ase-task-id/>, session: <ase-session-id/>)` tool
+        `ase_task_id(id: "<ase-task-id/>", session: "<ase-session-id/>")` tool
         from the `ase` MCP server to switch the task, and then only
         output the following <template/>:
 
@@ -73,8 +73,8 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
     2.  If <request/> has the format `<id/>: <text/>` where <id/> matches
         the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`, then set
         <request><text/></request> and <ase-task-id><id/></ase-task-id>
-        and call the `ase_task_id(id: <ase-task-id/>, session:
-        <ase-session-id/>)` tool from the `ase` MCP server to
+        and call the `ase_task_id(id: "<ase-task-id/>", session:
+        "<ase-session-id/>")` tool from the `ase` MCP server to
         implicitly switch the task. Do not output anything.
 
     3.  If <request/> is empty,
@@ -91,8 +91,8 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         ">
         Set <ase-task-id/> to a unique task id, derived from <request/>,
         which consists of two lower-case words concatenated with a
-        `-` character. Then call the `ase_task_id(id: <ase-task-id/>,
-        session: <ase-session-id/>)` tool from the `ase` MCP server to
+        `-` character. Then call the `ase_task_id(id: "<ase-task-id/>",
+        session: "<ase-session-id/>")` tool from the `ase` MCP server to
         implicitly switch the task. Do not output anything.
         </if>
 
@@ -270,7 +270,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         words <words/> of <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: "<content/>")`.
 
     4.  Output a hint with the following <template/>:
 

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

@@ -60,7 +60,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         identifier like `P1`, `P2`, `T1`, `T2`, ...),
         set <problem-id><problem/></problem-id> and
         <ase-task-id><problem/></ase-task-id>, call the `ase_task_id(id:
-        <ase-task-id/>, session: <ase-session-id/>)` tool from the
+        "<ase-task-id/>", session: "<ase-session-id/>")` tool from the
         `ase` MCP server to implicitly switch the task, and then
         call the `ase_kv_get(key: "ase-issue-<problem-id/>")` tool of
         the `ase` MCP server to retrieve the previously persisted
@@ -73,7 +73,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         ">
         Set <ase-task-id><problem/></ase-task-id> (set task id to problem)
         and <problem></problem> (set problem empty), call the
-        `ase_task_id(id: <ase-task-id/>, session: <ase-session-id/>)` tool
+        `ase_task_id(id: "<ase-task-id/>", session: "<ase-session-id/>")` tool
         from the `ase` MCP server to switch the task, and then only
         output the following <template/>:
 
@@ -85,8 +85,8 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
     3.  If <problem/> has the format `<id/>: <text/>` where <id/> matches
         the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`, then set
         <problem><text/></problem> and <ase-task-id><id/></ase-task-id>
-        and call the `ase_task_id(id: <ase-task-id/>, session:
-        <ase-session-id/>)` tool from the `ase` MCP server to
+        and call the `ase_task_id(id: "<ase-task-id/>", session:
+        "<ase-session-id/>")` tool from the `ase` MCP server to
         implicitly switch the task. Do not output anything.
 
     4.  If <problem/> is empty,
@@ -103,8 +103,8 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         ">
         Set <ase-task-id/> to a unique task id, derived from <problem/>,
         which consists of two lower-case words concatenated with a
-        `-` character. Then call the `ase_task_id(id: <ase-task-id/>,
-        session: <ase-session-id/>)` tool from the `ase` MCP server to
+        `-` character. Then call the `ase_task_id(id: "<ase-task-id/>",
+        session: "<ase-session-id/>")` tool from the `ase` MCP server to
         implicitly switch the task. Do not output anything.
         </if>
 
@@ -318,7 +318,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
         words <words/> of <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: "<content/>")`.
 
     4.  If <problem-id/> is set (i.e. the <problem/> was retrieved from
         `ase_kv_get` in STEP 1.3 via key `ase-issue-<problem-id/>`),

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

@@ -154,8 +154,8 @@ multi-*criteria* decision matrix.
 
     -   Then, calculate the ratings <rating-K/> (K=1-N) for all
         alternatives in a single call by invoking the `ase_decision_matrix(matrix:
-        [ [ <weight-1/>, <eval-1-1/>, ..., <eval-1-N/> ], ..., [ <weight-M/>,
-        <eval-M-1/>, ..., <eval-M-N/> ] ])` tool of the `ase` MCP server.
+        [ [ <weight-1/>, <eval-1-1/>, ..., <eval-N-1/> ], ..., [ <weight-M/>,
+        <eval-1-M/>, ..., <eval-N-M/> ] ])` tool of the `ase` MCP server.
         The tool returns an array of N numerical values, where the K-th
         entry is the product-sum of all weights <weight-L/> (L=1-M) and
         the evaluation <eval-K-L/> (L=1-M) for alternative <alternative-K/>.
@@ -173,9 +173,9 @@ multi-*criteria* decision matrix.
 
         | ⦿ *Criteria*  | ⚖ *Weight*  | ⚑ **<alternative-1/>** | [...alternatives 2-(N-1)...] | ⚑ **<alternative-N/>** |
         | :------------ | ----------: | ---------------------: | ---------------------------: | ---------------------: |
-        | <criteria-1/> | <weight-1/> | <eval-1-1/>            | [...evals 1-2..1-(N-1)...]   | <eval-1-N/>            |
+        | <criteria-1/> | <weight-1/> | <eval-1-1/>            | [...evals 2-1..(N-1)-1...]   | <eval-N-1/>            |
         [...criteria L=2-(M-1) for M>2...]
-        | <criteria-M/> | <weight-M/> | <eval-M-1/>            | [...evals M-2..M-(N-1)...]   | <eval-M-N/>            |
+        | <criteria-M/> | <weight-M/> | <eval-1-M/>            | [...evals 2-M..(N-1)-M...]   | <eval-N-M/>            |
         | **RATING**    |             | **<rating-1/>**        | [...ratings 2-(N-1)...]      | **<rating-N/>**        |
         </template>
     </step>

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

@@ -24,7 +24,7 @@ Persona Configuration
     Do not output anything.
 
 2.  <if condition="<request/> is empty">
-    1.  Call the `ase_persona(session: <ase-session-id/>)`
+    1.  Call the `ase_persona(session: "<ase-session-id/>")`
         tool from the `ase` MCP server and set
         <ase-persona-style/> to its `text` output.
         Do not output anything.
@@ -46,8 +46,8 @@ Persona Configuration
         </template>
 
     2.  Set <ase-persona-style><request/></ase-persona-style> and
-        call the `ase_persona(style: <ase-persona-style/>, session:
-        <ase-session-id/>)` tool from the `ase` MCP server. Do not
+        call the `ase_persona(style: "<ase-persona-style/>", session:
+        "<ase-session-id/>")` tool from the `ase` MCP server. Do not
         output anything.
 
     3.  Output the following <template/>:

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

@@ -36,7 +36,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
 1.  **Determine Task:**
 
-    1.  Set <id>$ARGUMENTS</id> initially.
+    1.  Set <id>$ARGUMENTS</id> initially, with any leading and trailing
+        whitespace stripped.
         Inherit the always existing <ase-task-id/> from the current context.
         Do not output anything.
 
@@ -45,9 +46,18 @@ explicitly requested by this procedure via outputs based on a <template/>!
         Do not output anything.
         </if>
 
+    3.  <if condition="<id/> does NOT match the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`">
+        Only output the following <template/> and then immediately
+        *STOP* processing the entire current skill:
+
+        <template>
+        ⧉ **ASE**: ☻ skill: **ase-task-delete**, ▶ ERROR: expected single `[<id>]` argument
+        </template>
+        </if>
+
 2.  **Perform Operation**:
 
-    1.  Call the `ase_task_delete(id: <id/>)` tool of the `ase` MCP
+    1.  Call the `ase_task_delete(id: "<id/>")` tool of the `ase` MCP
         server to delete the task plan content and set <text/> to the
         `text` output field of this `ase_task_delete` tool call. Do not
         output anything related to this MCP tool call.
@@ -68,7 +78,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
     2.  <if condition="<id/> is equal <ase-task-id/> AND <ase-task-id/> is not equal 'default'">
         Set <ase-task-id>default</ase-task-id>. Call the `ase_task_id(id:
-        <ase-task-id/>, session: <ase-session-id/>)` tool from the `ase`
+        "<ase-task-id/>", session: "<ase-session-id/>")` tool from the `ase`
         MCP server to switch the task to the default task. Only output
         the following <template/>:
 

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

@@ -56,6 +56,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
     1.  Set <instruction><getopt-arguments/></instruction> initially.
         Inherit the always existing <ase-task-id/> from the current context.
+        Inherit the always existing <ase-session-id/> from the current context.
         Do not output anything.
 
     2.  React on task and/or instruction:
@@ -65,8 +66,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
             ">
             Set <ase-task-id><instruction/></ase-task-id> (set task
             id to instruction) and <instruction></instruction> (set
-            instruction empty), call the `ase_task_id(id: <ase-task-id/>,
-            session: <ase-session-id/>)` tool from the `ase` MCP
+            instruction empty), call the `ase_task_id(id: "<ase-task-id/>",
+            session: "<ase-session-id/>")` tool from the `ase` MCP
             server to switch the task, and then only output the
             following <template/>:
 
@@ -82,8 +83,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
             ">
             Set <instruction></instruction> (set instruction to empty)
             and <ase-task-id><id/></ase-task-id> (set task id to
-            id) and call the `ase_task_id(id: <ase-task-id/>, session:
-            <ase-session-id/>)` tool from the `ase` MCP server to
+            id) and call the `ase_task_id(id: "<ase-task-id/>", session:
+            "<ase-session-id/>")` tool from the `ase` MCP server to
             switch the task, and then only output the following
             <template/>:
 
@@ -99,8 +100,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
             ">
             Set <instruction><text/></instruction> (set instruction to
             text) and <ase-task-id><id/></ase-task-id> (set task id
-            to id) and call the `ase_task_id(id: <ase-task-id/>, session:
-            <ase-session-id/>)` tool from the `ase` MCP server to
+            to id) and call the `ase_task_id(id: "<ase-task-id/>", session:
+            "<ase-session-id/>")` tool from the `ase` MCP server to
             switch the task, and then only output the following
             <template/>:
 
@@ -133,7 +134,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
 2.  **Determine Plan:**
 
-    1.  Call the `ase_task_load(id: <ase-task-id/>)` tool of the `ase` MCP
+    1.  Call the `ase_task_load(id: "<ase-task-id/>")` tool of the `ase` MCP
         server to load any existing plan content and set <text/> to
         the `text` output field of this `ase_task_load` tool call.
         Do not output anything related to this MCP tool call.
@@ -235,6 +236,28 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
             Only output the following <template/> and continue processing:
 
+            <template>
+            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **plan refined**
+            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ⇌ instruction: **<instruction/>**, ▶ status: **instruction given**
+            </template>
+
+        -   If <result/> matches `OTHER: <text/>`:
+
+            Set <instruction><instruction/> <text/></instruction> (append
+            the user's free-text hint to the existing instruction).
+
+            Treat the <instruction/> as a *refinement instruction* for
+            the plan, and update <content/> in-place by *applying* the
+            requested <instruction/> to the *plan*. When refining the
+            plan this way, preserve the overall structure of the plan
+            and only modify what the user actually requested. Do *not*
+            rewrite unrelated sections of the plan.
+
+            Calculate the number of words <words/> of <content/>.
+            Set <content-dirty>true</content-dirty>.
+
+            Only output the following <template/> and continue processing:
+
             <template>
             ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **plan refined**
             ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ⇌ instruction: **<instruction/>**, ▶ status: **instruction given**
@@ -273,9 +296,9 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
 3.  **Iterative Plan Refinement Loop:**
 
-    *REPEAT* the following steps 3.1 to 3.4 in a *LOOP* until
-    the user selects `DONE`, `IMPLEMENT`, or `PREFLIGHT`, or
-    declines/cancels in the dialog of step 3.4:
+    *REPEAT* the following steps from 3.1 up to and including 3.4 in a
+    *LOOP* until the user selects `DONE`, `IMPLEMENT`, or `PREFLIGHT`,
+    or declines/cancels in the dialog of step 3.4:
 
     1.  *Update timestamp*:
         <if condition="<content/> contains '✎ modified:' AND <content-dirty/> is 'true'">
@@ -289,7 +312,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
     2.  *Persist plan*:
         <if condition="<content-dirty/> is 'true'">
-        Call the `ase_task_save(id: <ase-task-id/>, text: <content/>)` tool
+        Call the `ase_task_save(id: "<ase-task-id/>", text: "<content/>")` tool
         of the `ase` MCP server to persist the current plan, and then
         set <content-dirty>false</content-dirty> again. Calculate the
         number of words <words/> of <content/>. Do not output anything
@@ -301,11 +324,12 @@ explicitly requested by this procedure via outputs based on a <template/>!
         </if>
 
     3.  *Render plan*: Only output the following <template/>, so the user
-        can read the plan and react to it. If <content/> is longer than
-        90 lines and a `※ IMPLEMENTATION DRAFT` section exists, replace
-        the entire content of the `※ IMPLEMENTATION DRAFT` section with
-        `[...]`. Else, do *not* truncate, summarize, or partially show
-        the plan. Use the following <template/>:
+        can read the plan and react to it. If <content/> is longer
+        than 90 lines and a `※ IMPLEMENTATION DRAFT` section (from the
+        companion skill `ase-task-preflight`) exists, replace the entire
+        content of the `※ IMPLEMENTATION DRAFT` section with `[...]`.
+        Else, do *not* truncate, summarize, or partially show the plan.
+        Use the following <template/>:
 
         <template>
         ⧉ **ASE**: ┈┈┈┈┈┈┈┈────────━━━━━━━━**(** `TASK-PLAN-BEGIN` **)**━━━━━━━━────────┈┈┈┈┈┈┈┈
@@ -318,8 +342,17 @@ explicitly requested by this procedure via outputs based on a <template/>!
         -   If <getopt-option-next/> matches the regex `^(DONE|IMPLEMENT|PREFLIGHT|REFINE)$`:
             Honor the pre-selection what to do as the next step.
             Set <result><getopt-option-next/></result>.
-            Then *clear* <getopt-option-next/> by setting <getopt-option-next>none</getopt-option-next>
-            so that subsequent loop iterations fall back to the interactive dialog.
+
+            Then *clear* <getopt-option-next/> by setting
+            <getopt-option-next>none</getopt-option-next> so that
+            subsequent loop iterations fall back to the interactive
+            dialog.
+
+            Set <instruction></instruction> (clear the instruction, as
+            any instruction carried in via the arguments was already
+            applied to the plan in step 2 before this loop), so that a
+            pre-selected `REFINE` correctly asks the user for a *fresh*
+            refinement instruction below.
 
         -   If <getopt-option-next/> is equal to `none`:
             Let the *user interactively choose* what to do as the next step.
@@ -367,9 +400,9 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
         -   If <result/> is `REFINE`:
 
-            Ask the user interactively, without a special tool, for
-            the refinement instruction with a single question `**What
-            is your instruction for refining the plan?**`. Then set
+            Ask the user interactively, without a special tool, for the
+            refinement instruction with a single question `**What is
+            your instruction for further refining the plan?**`. Then set
             <instruction/> to the response of the user.
 
             Treat the <instruction/> as a *refinement instruction* for
@@ -389,7 +422,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
         -   If <result/> matches `OTHER: <text/>`:
 
-            Set <instruction><text/></instruction>.
+            Set <instruction><text/></instruction> (replace existing instruction).
 
             Treat the <instruction/> as a *refinement instruction* for
             the plan, and update <content/> in-place by *applying* the

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

@@ -24,7 +24,7 @@ Configure Task Id
     <request>$ARGUMENTS</request>
 
 2.  <if condition="<request/> is empty">
-    -   Call the `ase_task_id(session: <ase-session-id/>)`
+    -   Call the `ase_task_id(session: "<ase-session-id/>")`
         tool from the `ase` MCP server and set
         <ase-task-id/> to its `text` output.
 
@@ -36,7 +36,7 @@ Configure Task Id
 
 3.  <if condition="<request/> is NOT empty">
     -   Set <ase-task-id><request/></ase-task-id> and
-        call the `ase_task_id(id: <ase-task-id/>, session: <ase-session-id/>)`
+        call the `ase_task_id(id: "<ase-task-id/>", session: "<ase-session-id/>")`
         tool from the `ase` MCP server.
 
     -   Output:

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

@@ -59,8 +59,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
             ">
             Set <ase-task-id><instruction/></ase-task-id> (set task
             id to instruction) and <instruction></instruction> (set
-            instruction empty), call the `ase_task_id(id: <ase-task-id/>,
-            session: <ase-session-id/>)` tool from the `ase` MCP
+            instruction empty), call the `ase_task_id(id: "<ase-task-id/>",
+            session: "<ase-session-id/>")` tool from the `ase` MCP
             server to switch the task, and then only output the
             following <template/>:
 
@@ -76,8 +76,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
             ">
             Set <instruction></instruction> (set instruction to empty)
             and <ase-task-id><id/></ase-task-id> (set task id to
-            id) and call the `ase_task_id(id: <ase-task-id/>, session:
-            <ase-session-id/>)` tool from the `ase` MCP server to
+            id) and call the `ase_task_id(id: "<ase-task-id/>", session:
+            "<ase-session-id/>")` tool from the `ase` MCP server to
             switch the task, and then only output the following
             <template/>:
 
@@ -86,13 +86,30 @@ explicitly requested by this procedure via outputs based on a <template/>!
             </template>
             </if>
 
+        3.  else <if condition="<instruction/> is NOT empty">
+            The argument is neither empty nor a valid task id. As this
+            skill only accepts an optional `[<id>]` argument and *never*
+            a free-text instruction, only output the following <template/>
+            and then immediately *STOP* processing the entire current skill:
+
+            <template>
+            ⧉ **ASE**: ☻ skill: **ase-task-implement**, ▶ ERROR: expected single `[<id>]` argument
+            </template>
+            </if>
+
 2.  **Determine Operation**:
 
-    1.  Call the `ase_task_load(id: <ase-task-id/>)` tool of the `ase` MCP
-        server to load the current task plan content and set <content/> to
+    1.  Call the `ase_task_load(id: "<ase-task-id/>")` tool of the `ase` MCP
+        server to load the current task plan content and set <text/> to
         the `text` output field of the `ase_task_load` tool call.
 
-        Calculate the number of words <words/> of <content/>.
+        -   If <text/> starts with `ERROR:` or `WARNING:`:
+            Set <content></content> (set content to empty).
+            Set <words/> to "0".
+
+        -   If <text/> starts NOT with `ERROR:` and NOT with `WARNING:`:
+            Set <content><text/></content> (set content to text).
+            Calculate the number of words <words/> of <content/>.
 
         Only output the following <template/>:
 

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

@@ -26,7 +26,7 @@ List Task Plans
     $ARGUMENTS
 </expand>
 
-1.  Call the `ase_task_list(verbose: <getopt-option-verbose/>)` tool from
+1.  Call the `ase_task_list(verbose: "<getopt-option-verbose/>")` tool from
     the `ase` MCP server. The result is a structured object with a
     `tasks` array where each entry has an `id` field, and -- if
     <getopt-option-verbose/> is `true` -- additionally an `mtime` field

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

@@ -59,8 +59,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
             ">
             Set <ase-task-id><instruction/></ase-task-id> (set task
             id to instruction) and <instruction></instruction> (set
-            instruction empty), call the `ase_task_id(id: <ase-task-id/>,
-            session: <ase-session-id/>)` tool from the `ase` MCP
+            instruction empty), call the `ase_task_id(id: "<ase-task-id/>",
+            session: "<ase-session-id/>")` tool from the `ase` MCP
             server to switch the task, and then only output the
             following <template/>:
 
@@ -76,8 +76,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
             ">
             Set <instruction></instruction> (set instruction to empty)
             and <ase-task-id><id/></ase-task-id> (set task id to
-            id) and call the `ase_task_id(id: <ase-task-id/>, session:
-            <ase-session-id/>)` tool from the `ase` MCP server to
+            id) and call the `ase_task_id(id: "<ase-task-id/>", session:
+            "<ase-session-id/>")` tool from the `ase` MCP server to
             switch the task, and then only output the following
             <template/>:
 
@@ -86,13 +86,30 @@ explicitly requested by this procedure via outputs based on a <template/>!
             </template>
             </if>
 
+        3.  else <if condition="<instruction/> is NOT empty">
+            The argument is neither empty nor a valid task id. As this
+            skill only accepts an optional `[<id>]` argument and *never*
+            a free-text instruction, only output the following <template/>
+            and then immediately *STOP* processing the entire current skill:
+
+            <template>
+            ⧉ **ASE**: ☻ skill: **ase-task-preflight**, ▶ ERROR: expected single `[<id>]` argument
+            </template>
+            </if>
+
 2.  **Determine Operation:**
 
-    1.  Call the `ase_task_load(id: <ase-task-id/>)` tool of the `ase` MCP
-        server to load the current task plan content and set <content/> to
+    1.  Call the `ase_task_load(id: "<ase-task-id/>")` tool of the `ase` MCP
+        server to load the current task plan content and set <text/> to
         the `text` output field of the `ase_task_load` tool call.
 
-        Calculate the number of words <words/> of <content/>.
+        -   If <text/> starts with `ERROR:` or `WARNING:`:
+            Set <content></content> (set content to empty).
+            Set <words/> to "0".
+
+        -   If <text/> starts NOT with `ERROR:` and NOT with `WARNING:`:
+            Set <content><text/></content> (set content to text).
+            Calculate the number of words <words/> of <content/>.
 
         Only output the following <template/>:
 
@@ -136,8 +153,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
         Do not output anything.
         </if>
 
-    4.  Finally, call the `ase_task_save(id: <ase-task-id/>,
-        text: <content/>)` of the `ase` MCP server to save the updated
+    4.  Finally, call the `ase_task_save(id: "<ase-task-id/>",
+        text: "<content/>")` of the `ase` MCP server to save the updated
         task plan content. Calculate the number of words <words/> of
         <content/>. Do not output anything related to this MCP tool call
         except the following <template/>:

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

@@ -56,28 +56,45 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
     2.  React on task id:
 
-        <if condition="
-            <instruction/> matches the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`
-        ">
-        Set <ase-task-id><instruction/></ase-task-id> (set task
-        id to instruction) and <instruction></instruction> (set
-        instruction empty), call the `ase_task_id(id: <ase-task-id/>,
-        session: <ase-session-id/>)` tool from the `ase` MCP
-        server to switch the task, and then only output the
-        following <template/>:
+        1.  <if condition="
+                <instruction/> matches the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`
+            ">
+            Set <ase-task-id><instruction/></ase-task-id> (set task
+            id to instruction) and <instruction></instruction> (set
+            instruction empty), call the `ase_task_id(id: "<ase-task-id/>",
+            session: "<ase-session-id/>")` tool from the `ase` MCP
+            server to switch the task, and then only output the
+            following <template/>:
 
-        <template>
-        ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **task given**
-        </template>
-        </if>
+            <template>
+            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **task given**
+            </template>
+            </if>
+
+        2.  else <if condition="<instruction/> is NOT empty">
+            The argument is neither empty nor a valid task id. As this
+            skill only accepts an optional `[<id>]` argument and *never*
+            a free-text instruction, only output the following <template/>
+            and then immediately *STOP* processing the entire current skill:
+
+            <template>
+            ⧉ **ASE**: ☻ skill: **ase-task-reboot**, ▶ ERROR: expected single `[<id>]` argument
+            </template>
+            </if>
 
 2.  **Determine Operation:**
 
-    1.  Call the `ase_task_load(id: <ase-task-id/>)` tool of the `ase` MCP
-        server to load the current task plan content and set <content/> to
+    1.  Call the `ase_task_load(id: "<ase-task-id/>")` tool of the `ase` MCP
+        server to load the current task plan content and set <text/> to
         the `text` output field of the `ase_task_load` tool call.
 
-        Calculate the number of words <words/> of <content/>.
+        -   If <text/> starts with `ERROR:` or `WARNING:`:
+            Set <content></content> (set content to empty).
+            Set <words/> to "0".
+
+        -   If <text/> starts NOT with `ERROR:` and NOT with `WARNING:`:
+            Set <content><text/></content> (set content to text).
+            Calculate the number of words <words/> of <content/>.
 
         Only output the following <template/>:
 
@@ -104,35 +121,39 @@ explicitly requested by this procedure via outputs based on a <template/>!
         Set <instruction><text/></instruction> (set instruction to extracted text).
         </if>
 
-    4.  <if condition="<content/> contains '- **WHY**: <text/>'">
+    4.  <if condition="<content/> contains '- **WHY**: <text/>' and <instruction/> is empty">
+        Set <instruction><text/></instruction> (set instruction to extracted text).
+        </if>
+
+    5.  else <if condition="<content/> contains '- **WHY**: <text/>' and <instruction/> is NOT empty">
         Set <instruction><instruction/>, BECAUSE <text/></instruction>
         (append extracted text to instruction).
         </if>
 
-    5.  <if condition="<content/> contains 'created: **<text/>**'">
+    6.  <if condition="<content/> contains 'created: **<text/>**'">
         Set <timestamp-created><text/></timestamp-created> (set
         timestamp-created to extracted text)
         </if>
 
-    6.  Create a new plan from scratch and store the result as
+    7.  Create a new plan from scratch and store the result as
         <content/> by closely following the defined plan format
         <format/> and injecting into it all the information from
         the <instruction/> and all decisions you derived from the
         <instruction/>.
 
-    7.  Call the `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of the
+    8.  Call the `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of the
         `ase` MCP server and use the `text` field of its response for
         <timestamp-modified/> information. Then insert the current
         <ase-task-id/>, previous <timestamp-created/>, and refreshed
         <timestamp-modified/> information and calculate the number of
         words <words/> of <content/>.
 
-    8.  Call the `ase_task_save(id: <ase-task-id/>,
-        text: <content/>)` of the `ase` MCP server to save the updated
+    9.  Call the `ase_task_save(id: "<ase-task-id/>",
+        text: "<content/>")` of the `ase` MCP server to save the updated
         task plan content. Do not output anything related to this MCP
         call.
 
-    9.  Only output the following <template/> and continue processing:
+    10. Only output the following <template/> and continue processing:
 
         <template>
         ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **plan rebooted**

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

@@ -64,7 +64,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
 2.  **Perform Operation**:
 
-    1.  Call the `ase_task_rename(old: <old/>, new: <new/>)` tool of the
+    1.  Call the `ase_task_rename(old: "<old/>", new: "<new/>")` tool of the
         `ase` MCP server to rename the task plan and set <text/> to the
         `text` output field of this `ase_task_rename` tool call. Do not
         output anything related to this MCP tool call.
@@ -85,7 +85,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
     2.  <if condition="<old/> is equal <ase-task-id/>">
         Set <ase-task-id><new/></ase-task-id>. Call the `ase_task_id(id:
-        <ase-task-id/>, session: <ase-session-id/>)` tool from the `ase`
+        "<ase-task-id/>", session: "<ase-session-id/>")` tool from the `ase`
         MCP server to switch the task to the renamed task. Only output
         the following <template/>:
 

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

@@ -36,7 +36,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
 1.  **Determine Task:**
 
-    1.  Set <id>$ARGUMENTS</id> initially.
+    1.  Set <id>$ARGUMENTS</id> initially, with any leading and trailing
+        whitespace stripped.
         Inherit the always existing <ase-task-id/> from the current context.
         Do not output anything.
 
@@ -45,9 +46,18 @@ explicitly requested by this procedure via outputs based on a <template/>!
         Do not output anything.
         </if>
 
+    3.  <if condition="<id/> does NOT match the regexp `^[a-zA-Z][a-zA-Z0-9_-]*$`">
+        Only output the following <template/> and then immediately
+        *STOP* processing the entire current skill:
+
+        <template>
+        ⧉ **ASE**: ☻ skill: **ase-task-view**, ▶ ERROR: expected single `[<id>]` argument
+        </template>
+        </if>
+
 2.  **Perform Operation**:
 
-    1.  Call the `ase_task_load(id: <id/>)` tool of the `ase` MCP
+    1.  Call the `ase_task_load(id: "<id/>")` tool of the `ase` MCP
         server to load the task plan content and set <text/> to the
         `text` output field of this `ase_task_load` tool call. Do not
         output anything related to this MCP tool call.