@rse/ase 0.9.7 → 0.9.8

package/plugin/skills/ase-docs-distill/help.md

@@ -32,15 +32,15 @@ one block per point, each showing its *LOCATION*, *EVIDENCE*,
 ranking is *auditable* rather than an opaque ordering.
 
 The `--top`/`-t` *N* option is a *length dial* that bounds the list to at
-most *N* points (default *10*). It is an *upper bound only*: when the
+most *N* points (default *5*). It is an *upper bound only*: when the
 document has fewer salient points than *N*, the skill emits only the
 points it found and *never pads* the list with filler; a `0`, negative, or
-non-numeric value falls back to the default *10*.
+non-numeric value falls back to the default *5*.
 
 ##  ARGUMENTS
 
 `--top`, `-t` *N*:
-    Bound the ranked list to at most *N* key points (default *10*). The
+    Bound the ranked list to at most *N* key points (default *5*). The
     bound is a *cap*, never a *quota* - fewer points are emitted when the
     document does not contain *N* salient ones, and an invalid or
     non-positive *N* reverts to the default.

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

@@ -116,8 +116,8 @@ Analyze documents for spelling, punctuation, or grammar errors
 
         3.  <if condition="<getopt-option-auto/> is not 'true'">
 
-            Render the proposed correction as a *unified diff* with *one*
-            line of context in a fenced block based on the following <template/>:
+            Render the proposed correction as a *unified diff* with *up to
+            two* lines of context in a fenced block based on the following <template/>:
 
             <template>
 
@@ -126,7 +126,7 @@ Analyze documents for spelling, punctuation, or grammar errors
             ```diff
             --- <file/> (original)
             +++ <file/> (corrected)
-            @@ -<line/>,<n/> +<line/>,<m/> @@
+            @@ -<old-start/>,<n/> +<new-start/>,<m/> @@
              <context-before/>
             -<old-text/>
             +<new-text/>
@@ -136,8 +136,16 @@ Analyze documents for spelling, punctuation, or grammar errors
             </template>
 
             Hints:
-            -   The <n/> is the number of lines in <old-text/>.
-            -   The <m/> is the number of lines in <new-text/>.
+            -   The <old-start/> is the line of the first hunk line, i.e.,
+                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 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 number of lines in <context-before/>, <new-text/>, and
+                <context-after/> combined.
 
             </if>
 
@@ -153,20 +161,21 @@ Analyze documents for spelling, punctuation, or grammar errors
 
             </if>
 
-            <if condition="<getopt-option-auto/> is 'true'">
+            <else>
 
             Set <result>ACCEPT</result>.
 
-            </if>
+            </else>
 
         5.  Check <result/> and dispatch accordingly:
 
             -   <if condition="<result/> is 'ACCEPT'">
 
-                Invoke the `Edit` tool to apply the change exactly as shown
-                in the diff. The operation will be auto-approved because of
-                the active proofread marker, so *no* interactive permission
-                prompt will appear. Then continue with the next <item/>.
+                Invoke the `Edit` tool to apply the change by replacing
+                <old-text/> with <new-text/> at <file/>:<line/>. The operation
+                will be auto-approved because of the active proofread marker,
+                so *no* interactive permission prompt will appear. Then
+                continue with the next <item/>.
 
                 </if>
 
@@ -174,8 +183,8 @@ Analyze documents for spelling, punctuation, or grammar errors
 
                 Generate a *new* proposal for the *same* <item/>,
                 incorporating the user's free-text hint from <result/>
-                after the "OTHER:" prefix, and loop back to substep 2 of
-                this iteration. There is *no* cap on refinement rounds -
+                after the "OTHER:" prefix, and *go back* to substep 2 of
+                this `for`-iteration. There is *no* cap on refinement rounds -
                 keep refining until the user picks `ACCEPT` or `REJECT`.
 
                 </if>

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

@@ -113,15 +113,15 @@ Honor the following tenets throughout the brainstorming:
             <ase-tpl-bullet-signal/> FACET <M/>/<m/>: **<facet-M/>**, QUESTION: **<question-M/>**
             </template>
 
-        2.  Determine *up to 4* grounded candidate answers
+        2.  Determine *2 to 4* grounded candidate answers
             <answer-M-K/> (K={1,2,3,4}) from the code base, the documented
             context, and your world knowledge.
 
         3.  Use an interactive user dialog with header <facet-M/> and
             question <question-M/>, and let the user select the
-            <answer-M/> out of the candidate answers <answer-M-K/> (just
-            leave out all answers in case you have determined less than
-            4 potential answers)
+            <answer-M/> out of the candidate answers <answer-M-K/> (leave
+            out the answer lines of those candidate answers you have
+            not determined)
 
             <expand name="user-dialog">
                 <facet-M/>: <question-M/>
@@ -131,7 +131,26 @@ Honor the following tenets throughout the brainstorming:
                 <answer-M-4/>: (fourth grounded candidate answer)
             </expand>
 
-        4.  Output the following <template/>:
+        4.  Dispatch on the dialog <result/>:
+
+            -   If <result/> is `CANCEL`:
+                Skip the remaining sub-steps of this iteration cycle and
+                continue directly with sub-step 2 below (cancellation handling).
+
+            -   If <result/> starts with `ERROR:`:
+                Ask the user interactively, without a special tool, the
+                question <question-M/> directly and set <answer-M/> to the
+                response of the user.
+
+            -   If <result/> matches `OTHER: <text/>`:
+                Set <answer-M><text/></answer-M> (take the user's free-text answer).
+
+            -   Otherwise:
+                Set <answer-M><result/></answer-M> (take the selected candidate answer).
+
+            Do not output anything in this sub-step.
+
+        5.  Output the following <template/>:
 
             <template>
             <ase-tpl-bullet-normal/> FACET <M/>/<m/>: **<facet-M/>**, ANSWER: **<answer-M/>**
@@ -182,7 +201,7 @@ Honor the following tenets throughout the brainstorming:
     set and finally into a recommendation.
 
     1.  *Cluster*: group the candidate ideas into <c/> coherent clusters
-        <cluster-C/> (a short 1-4 word label, C=1...</c>), collapsing
+        <cluster-C/> (a short 1-4 word label, C=1...<c/>), collapsing
         near-duplicates and discarding ideas pruned by *You Aren't Gonna
         Need It (YAGNI)* (speculative, out-of-scope, or contradicting
         documented context).

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

@@ -7,10 +7,10 @@
 
 `ase-meta-brainstorm`
     [`--help`|`-h`]
-    [`--max-clarify=3`]
+    [`--max-clarify`|`-c=3`]
     [`--min-ideas`|`-i=12`]
-    [`--min-rank=7`]
-    [`--max-shortlist=4`]
+    [`--min-rank`|`-r=7`]
+    [`--max-shortlist`|`-s=4`]
     *topic*
 
 ##  DESCRIPTION
@@ -33,13 +33,9 @@ default 7, or higher). Finally it distills a *shortlist* of the top
 wherever possible - and derives a single *RECOMMENDATION*, being either
 the highest-ranked option or a principled synthesis of the shortlist.
 
-On completion the skill offers a *next step*: stop, or hand the
-recommended direction off to the `ase-task-edit`, `ase-code-craft`, or
-`ase-task-preflight` skills.
-
 ##  OPTIONS
 
-`--max-clarify=3`:
+`--max-clarify`|`-c=3`:
     The *maximum* number of essential-unknown clarification questions
     asked in the *clarify intent* phase (default: 3). Lower it for a
     faster, leaner intake, raise it for more upfront grounding.
@@ -49,12 +45,12 @@ recommended direction off to the `ase-task-edit`, `ase-code-craft`, or
     phase before converging (default: 12). Raise it for a broader idea
     space, lower it for a quicker, narrower session.
 
-`--min-rank=7`:
+`--min-rank`|`-r=7`:
     The *minimum* 0-10 fit rank an idea must score to survive the
     *converge* phase (default: 7). Raise it for a stricter filter, lower
     it to retain more ideas.
 
-`--max-shortlist=4`:
+`--max-shortlist`|`-s=4`:
     The *maximum* number of distilled options on the final *shortlist*
     (default: 4). Lower it for a sharper focus, raise it for more
     finalists.

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

@@ -11,9 +11,9 @@ disable-model-invocation: false
 effort: high
 allowed-tools:
     - "Bash(git diff *)"
-    - "Bash(git grep:*)"
-    - "Bash(git ls-files:*)"
-    - "Bash(grep:*)"
+    - "Bash(git grep *)"
+    - "Bash(git ls-files *)"
+    - "Bash(grep *)"
     - "Agent"
 ---
 
@@ -98,7 +98,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
             </template>
 
-        2.  Render a *two-column table* with one row per discovered
+        2.  Render a *three-column table* with one row per discovered
             *intent group* present in the <diff/>. Output the following
             table header <template/>:
 
@@ -205,6 +205,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
         | **<deviation/>** | <location/> | <reason/>                         |
 
         </template>
+        </if>
     </step>
 
 4.  <step id="STEP 4: Score Against Risk Rubric"

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

@@ -17,24 +17,23 @@ The `ase-meta-diff` skill turns a raw Git diff into a *concise*,
 *human-readable* narrative of what changed and why, *grouped by
 intent* (such as *Feature*, *Improvement*, *Bugfix*, *Update*,
 *Cleanup*, or *Refactor*) rather than by file. It inspects the
-*staged* changes (`git diff --cached HEAD`). The result is a short
-bullet list, one bullet per intent group, each naming the affected
-files with their per-file `[+N/-M]` line counts - giving you the
-essence of the changes at a glance.
+*staged* changes (`git diff --cached HEAD`). The result is a compact
+table, one row per intent group, each naming the affected files
+with their per-file `[+N/-M]` line counts - giving you the essence
+of the changes at a glance.
 
 With `--coherence`, the skill additionally *reconstructs the single
 intended change* the diff is trying to accomplish - phrased as one crisp
 *thesis* sentence - and then walks *every* hunk to *flag those that do
 not serve it*: **scope creep** (an unrelated feature or drive-by refactor
-riding along), **stray debug** (leftover prints, commented-out code, or
-disabled tests), and **ripple** (mechanical fallout edits forced by the
-core change). It emits an overall **COHERENT** / **INCOHERENT** verdict
+riding along) and **stray debug** (leftover prints, commented-out code, or
+disabled tests). It emits an overall **COHERENT** / **INCOHERENT** verdict
 plus a table of the flagged hunks with what to do with each - keeping the
 diff to a *single logical and coherent change* before it is committed.
 
 With `--risk`, the skill additionally *scores* the same diff against a
 four-axis **coupling-criticality-coverage-reversibility** rubric and
-emits a *graded risk report* - one bullet per axis (each scored *1*-*5*
+emits a *graded risk report* - one table row per axis (each scored *1*-*5*
 with a one-line evidence justification drawn from the actual hunks), an
 overall risk band (**LOW**, **MODERATE**, **HIGH**, or **CRITICAL**),
 and one actionable *mitigation* per high-risk axis. The axes combine
@@ -57,9 +56,9 @@ giving a visual sense of *what a diff endangers* before a deeper review.
 `--coherence`, `-c`:
     In addition to the intent-grouped summary, reconstruct the diff's
     *single intended change* as one crisp *thesis* sentence and flag
-    *every* hunk that does *not* serve it - *scope creep*, *stray debug*,
-    or *ripple* fallout - then emit an overall **COHERENT** /
-    **INCOHERENT** verdict with a table of the flagged hunks.
+    *every* hunk that does *not* serve it - *scope creep* or *stray
+    debug* - then emit an overall **COHERENT** / **INCOHERENT** verdict
+    with a table of the flagged hunks.
 
 `--risk`, `-r`:
     In addition to the intent-grouped summary, score the diff against

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

@@ -193,15 +193,16 @@ multi-*criteria* decision matrix.
 
     -   Determine rating distance percentage <percentage/> between
         <alternative-K/> and <alternative-X/> from their *raw,
-        unrounded* ratings by calculating: <percentage/> = <distance/> /
-        abs(<rating-K/>). Do not output anything.
-
-    -   If <rating-K/> is exactly zero, skip the division entirely
-        and treat <percentage/> as if it were equal to <distance/>
-        (so a true zero tie with <distance/> = 0 falls into the
-        *MULTIPLE BEST* branch below, and a non-zero gap with zero
-        best falls into the *small distance* branch below).
-        Do not output anything.
+        unrounded* ratings as follows. If <rating-K/> is exactly zero,
+        skip the division entirely and treat <percentage/> as if it
+        were equal to <distance/> (so a true zero tie with <distance/>
+        = 0 falls into the *MULTIPLE BEST* branch below, while a non-zero
+        gap with zero best is routed by the magnitude of <distance/>
+        through the same thresholds as <percentage/> otherwise). Do not
+        output anything.
+
+    -   Otherwise (<rating-K/> is non-zero), calculate: <percentage/> =
+        <distance/> / abs(<rating-K/>). Do not output anything.
 
     -   By construction, <rating-K/> is the maximum rating across
         all alternatives, so <distance/> >= 0 always holds; using

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

@@ -62,9 +62,19 @@ by querying *multiple* AIs for an *optimal consensus*.
 
     The user-selectable foreign models are restricted by the
     `--models`/`-m` option, parsed into <getopt-option-models/>
-    as a comma-separated list of model tokens. The default is
-    the single token `all`. If <getopt-option-models/> contains
-    the token `all`, you *MUST* treat it as the full list
+    as a comma-separated list of model tokens. The getopt parser
+    validates only the *first* token, so you *MUST* validate each
+    remaining token yourself against the allowed set `all`, `chatgpt`,
+    `gemini`, `deepseek`, `grok`, `glm`, `qwen`. If any token is *not*
+    in this set, only output the following <template/> and then
+    immediately *STOP* processing the entire current skill:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-quorum**, ▶ ERROR: invalid `--models` token: **<token/>**
+    </template>
+
+    The default is the single token `all`. If <getopt-option-models/>
+    contains the token `all`, you *MUST* treat it as the full list
     `chatgpt,gemini,deepseek,grok,glm,qwen` (all models). Anthropic
     Claude (yourself) is *always* included, independent of this option.
 
@@ -142,8 +152,8 @@ by querying *multiple* AIs for an *optimal consensus*.
 5.  <step id="STEP 5: Show Results">
 
     Finally show the summary, the consensus and the complete and
-    unmodified responses of yourself and each of the MCP servers, based
-    on the following output <template/>:
+    unmodified responses of yourself and each of the queried foreign
+    AIs, based on the following output <template/>:
 
     <template>
     **QUESTION**:

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

@@ -107,8 +107,8 @@ explicitly requested by this procedure via outputs based on a <template/>!
     <verdict/> to `REJECT - DEMANDS CHANGES` if *any* finding in
     <findings/> has a `severity` field of `HIGH`; otherwise set
     <verdict/> to `APPROVE`. The verdict is derived *before* the
-    severity floor below, so a suppressed `HIGH` finding still drives the
-    verdict.
+    severity floor below, so the floor only affects which findings are
+    *rendered*, never the verdict.
 
     Then *apply the severity floor* selected via <getopt-option-severity/>
     (default `LOW`): define the ordinal rank `LOW`=1, `MEDIUM`=2,
@@ -135,7 +135,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
         </template>
 
-        You *MUST* *NOT* output anything else in this STEP 3.
+        You *MUST* *NOT* output anything else in this STEP 3.1.
 
     2.  <if condition="<findings/> is empty">
         Only output the following <template/> and then *SKIP* the

package/plugin/skills/ase-meta-review/help.md

@@ -59,9 +59,9 @@ before it is committed.
     Set the *severity floor* (default `LOW`): findings below the chosen
     threshold are silently suppressed, ordered `LOW` < `MEDIUM` <
     `HIGH`. The default `LOW` keeps all findings; `ACCEPTED` findings are
-    never suppressed. The floor only affects the rendered findings table;
-    the overall *verdict* is still derived from all findings, so a
-    suppressed `HIGH` finding still yields a *REJECT* verdict.
+    never suppressed. The floor only affects the rendered findings table,
+    not the overall *verdict*, which is always derived from all findings
+    before the floor is applied.
 
 ##  ARGUMENTS
 

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

@@ -41,8 +41,8 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
     <define name="agent">
     ```text
         Agent(
-            name:          "ase-meta-search",
-            description:   "Query Web Search Service",
+            name:          "ase-meta-search-<arg1/>",
+            description:   "Query Web Search Service: <arg1/>",
             subagent_type: "ase:ase-meta-search",
             prompt:        <content/>
         )
@@ -53,8 +53,9 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
     *backend tokens*. The getopt parser validates only the *first*
     token, so you *MUST* validate each remaining token yourself against
     the allowed set `all`, `perplexity`, `brave`, `exa`, `websearch`. If
-    any token is *not* in this set, only output the following <template/>
-    and then immediately *STOP* processing the entire current skill:
+    any token is *not* in this set, bind <token/> to that offending
+    token, then only output the following <template/> and then
+    immediately *STOP* processing the entire current skill:
 
     <template>
     ⧉ **ASE**: ✪ skill: **ase-meta-search**, ▶ ERROR: invalid `--services` token: **<token/>**
@@ -66,7 +67,7 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
     If the `perplexity` backend is *selected* and the MCP tool
     `perplexity_search` from the MCP server `search-perplexity` is available:
 
-    <expand name="agent">
+    <expand name="agent" arg1="perplexity">
         Call the MCP tool `perplexity_search(query: "<query/>")`
         from the MCP server `search-perplexity`.
     </expand>
@@ -74,7 +75,7 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
     If the `brave` backend is *selected* and the MCP tool
     `brave_web_search` from the MCP server `search-brave` is available:
 
-    <expand name="agent">
+    <expand name="agent" arg1="brave">
         Call the MCP tool `brave_web_search(query: "<query/>")`
         from the MCP server `search-brave`.
     </expand>
@@ -82,14 +83,14 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
     If the `exa` backend is *selected* and the MCP tool
     `web_search_exa` from the MCP server `search-exa` is available:
 
-    <expand name="agent">
+    <expand name="agent" arg1="exa">
         Call the MCP tool `web_search_exa(query: "<query/>")`
         from the MCP server `search-exa`.
     </expand>
 
     If the `websearch` backend is *selected*:
 
-    <expand name="agent">
+    <expand name="agent" arg1="websearch">
         Call the tool `WebSearch(query: "<query/>")`.
     </expand>
 

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

@@ -197,7 +197,7 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
     Carry the result forward to the next round: set
     <thesis><fortification/></thesis> (the fortification becomes the
     thesis to be strengthened next), set <i/> to <i/> + 1 (increment the
-    round counter), and then *CONTINUE* the *LOOP* at **STEP 1**!
+    round counter), and then *REPEAT* the operation at **STEP 1**!
     </if>
 
     <if condition="<i/> is greater than or equal to <rounds/>">

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

@@ -106,13 +106,15 @@ addressing surface-level symptoms.
 
             Ask <question/> and surface up to <width/> *distinct*,
             *non-overlapping* candidate sub-causes, each documented in <answer-k/>.
+            Let <count/> be the number of candidates you actually surfaced
+            (at least one, at most <width/>).
             Don't stop at symptoms, keep digging for systemic issues.
             Explore *different* candidates -- technical, domain-specific,
             process-related, or organizational causes -- and avoid restating
             the same cause in different words.
 
             Start with <k>1</k> (set candidate counter to one).
-            <while condition="<k/> is less than or equal to <width/>">
+            <while condition="<k/> is less than or equal to <count/>">
                 <template>
                 <ase-tpl-bullet-secondary/> **WHY <n/>.<k/>**: <answer-k/>
                 </template>
@@ -150,15 +152,19 @@ addressing surface-level symptoms.
     whole chain up to the original <problem/>).
 
     When <width/> is *greater than 1* and this backward validation *fails* at
-    some level -- i.e. the chosen sub-cause does *not* adequately explain the
-    fact above it -- *backtrack*: discard the chosen sub-cause from that level
-    downward, pick the next-best candidate from that level's <fallbacks/>, set
-    <question/> to it, and re-run the STEP 2 widened descent from there. Repeat
-    until a chain survives backward validation or that level's <fallbacks/> are
-    exhausted (then report the strongest chain found and note that no candidate
-    fully validated). This is the payoff of <width/> *greater than 1*: the
-    enumerated alternatives let the analysis *recover* from a wrong turn instead
-    of committing to a mis-rooted chain.
+    some level <m/> -- i.e. the chosen sub-cause does *not* adequately explain
+    the fact above it -- *backtrack*: discard the chosen sub-cause (and every
+    chosen sub-cause below it) from level <m/> downward, pick the next-best
+    candidate from level <m/>'s <fallbacks/>, and resume the STEP 2 widened
+    descent: set <n/> to <m/> (reset the iteration counter to the failed level),
+    set <question/> to the picked candidate, and re-enter STEP 2's
+    <while condition="<n/> is less than or equal to <depth/>"/> loop at that
+    level -- so the original <depth/> budget is honored from <m/> downward.
+    Repeat until a chain survives backward validation or level <m/>'s
+    <fallbacks/> are exhausted (then report the strongest chain found and note
+    that no candidate fully validated). This is the payoff of <width/> *greater
+    than 1*: the enumerated alternatives let the analysis *recover* from a wrong
+    turn instead of committing to a mis-rooted chain.
 
     Propose a solution that addresses and solves the validated root-cause.
     For the proposed solution, optionally directly propose corresponding source code changes.

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

@@ -65,7 +65,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
             </template>
             </if>
 
-        2.  else <if condition="<instruction/> is NOT empty">
+        2.  <elseif 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/>
@@ -74,7 +74,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
             <template>
             ⧉ **ASE**: ☻ skill: **ase-task-condense**, ▶ ERROR: expected single `[<id>]` argument
             </template>
-            </if>
+            </elseif>
 
 2.  **Determine Operation:**
 
@@ -114,9 +114,9 @@ explicitly requested by this procedure via outputs based on a <template/>!
         and unchanged*. Honor the following ruleset *strictly*:
 
         1.  *Preserve-exactly (never alter)*: the plan <format/>
-            structure (the headings `#`/`##`, the `※`/`◉`/`✪` markers,
-            all three `## ※ CONTEXT`, `## ※ CHANGES`, and `## ※
-            VERIFICATION` sections, the `created:`/`modified:` line, and
+            structure (the headings `#`/`##`, all three `##  CONTEXT`,
+            `##  CHANGES`, and `##  VERIFICATION` sections, the
+            `Created:`/`Modified:` lines, and
             the `- **<aspect/>**:` bullet labels), all *code spans* and
             code blocks, technical terms, file paths, identifiers,
             numbers, severities (`LOW`/`MEDIUM`/`HIGH`/`ACCEPTED`), and
@@ -223,13 +223,15 @@ explicitly requested by this procedure via outputs based on a <template/>!
             </template>
 
         -   If <result/> is `EDIT`:
-            Set <args></args> (empty).
+            Set <args></args> (set args to empty).
+            <if condition="the condensed plan was saved via `ase_task_save` in step 3">
+                Set <args>--int-reuse-task</args>.
+            </if>
             <if condition="<getopt-option-next/> is not equal `none`">
-            Set <args>--next <getopt-option-next/></args> (forward
-            remaining list tokens to the downstream skill).
+                Set <args><args/> --next <getopt-option-next/></args>
             </if>
             Only output the following <template/> and then call the
-            tool `Skill(skill: "ase:ase-task-edit", args: <args/>)`
+            tool `Skill(skill: "ase:ase-task-edit", args: "<args/>")`
             to invoke the `ase:ase-task-edit` skill in order to *edit*
             the condensed plan. Immediately stop processing the current
             skill once the `Skill` tool was used.
@@ -239,13 +241,15 @@ explicitly requested by this procedure via outputs based on a <template/>!
             </template>
 
         -   If <result/> is `IMPLEMENT`:
-            Set <args></args> (empty).
+            Set <args></args> (set args to empty).
+            <if condition="the condensed plan was saved via `ase_task_save` in step 3">
+                Set <args>--int-reuse-task</args>.
+            </if>
             <if condition="<getopt-option-next/> is not equal `none`">
-            Set <args>--next <getopt-option-next/></args> (forward
-            remaining list tokens to the downstream skill).
+                Set <args><args/> --next <getopt-option-next/></args>
             </if>
             Only output the following <template/> and then call the
-            `Skill(skill: "ase:ase-task-implement", args: <args/>)` tool
+            `Skill(skill: "ase:ase-task-implement", args: "<args/>")` tool
             to *apply* the plan.
 
             <template>
@@ -253,15 +257,26 @@ explicitly requested by this procedure via outputs based on a <template/>!
             </template>
 
         -   If <result/> is `PREFLIGHT`:
-            Set <args></args> (empty).
+            Set <args></args> (set args to empty).
+            <if condition="the condensed plan was saved via `ase_task_save` in step 3">
+                Set <args>--int-reuse-task</args>.
+            </if>
             <if condition="<getopt-option-next/> is not equal `none`">
-            Set <args>--next <getopt-option-next/></args> (forward
-            remaining list tokens to the downstream skill).
+                Set <args><args/> --next <getopt-option-next/></args>
             </if>
             Only output the following <template/> and then call the
-            `Skill(skill: "ase:ase-task-preflight", args: <args/>)` tool
+            `Skill(skill: "ase:ase-task-preflight", args: "<args/>")` tool
             to *apply* the plan.
 
             <template>
             ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **plan condensed -- hand-off to pre-flight**
             </template>
+
+        -   If <result/> matches `OTHER: <text/>` or is any other
+            unrecognized value:
+            Treat it as `DONE` (the condensed plan is already saved):
+            only output the following <template/> and then *STOP*.
+
+            <template>
+            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **plan condensed -- done**
+            </template>

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

@@ -30,7 +30,7 @@ telegrapher-like even under the `writer` persona.
 
 The plan is saved *only* when condensing actually makes it smaller; if no
 further reduction is possible, the plan is left untouched (including its
-`✎ modified:` timestamp) and reported as *already condensed*.
+`⚙   Modified:` timestamp) and reported as *already condensed*.
 
 After condensing, the user is asked whether to stop or hand off to
 `ase-task-edit`, `ase-task-implement`, or `ase-task-preflight`, unless

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

@@ -35,6 +35,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
     1.  Set <id>$ARGUMENTS</id> initially, with any leading and trailing
         whitespace stripped.
         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.  <if condition="<id/> is empty">
@@ -59,20 +60,22 @@ explicitly requested by this procedure via outputs based on a <template/>!
         output anything related to this MCP tool call.
 
         -   If <text/> starts with `ERROR:` or `WARNING:`:
-            Only output the following <template/>:
+            Set <deleted>false</deleted> and only output the following
+            <template/>:
 
             <template>
             ⧉ **ASE**: ◉ task: **<id/>**, ▶ status: **<text/>**
             </template>
 
         -   If <text/> starts NOT with `ERROR:` and NOT with `WARNING:`:
-            Only output the following <template/>:
+            Set <deleted>true</deleted> and only output the following
+            <template/>:
 
             <template>
             ⧉ **ASE**: ◉ task: **<id/>**, ▶ status: **task deleted**
             </template>
 
-    2.  <if condition="<id/> is equal <ase-task-id/> AND <ase-task-id/> is not equal 'default'">
+    2.  <if condition="<deleted/> is equal 'true' AND <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`
         MCP server to switch the task to the default task. Only output