@rse/ase 0.9.55 → 0.9.57

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

@@ -78,6 +78,15 @@ Honor the following tenets throughout the brainstorming:
 
 1.  <step id="STEP 1: Restate Topic">
 
+    <if condition="<topic/> is empty">
+    Only output the following <template/> and then immediately *STOP*
+    processing the entire current skill:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-brainstorm**, ▶ ERROR: expected a `<topic>` argument
+    </template>
+    </if>
+
     Restate the topic to be brainstormed by outputting the following <template/>:
 
     <template>
@@ -99,7 +108,7 @@ Honor the following tenets throughout the brainstorming:
     1..<getopt-option-max-clarify/> unknowns, as too much upfront intent
     clarification kills the brainstorming of ideas later. So, you *MUST*
     reduce the clarifications of the unknowns to the absolute minimum in
-    general and cap it at <getopt-option-max-clarify/>!
+    general and cap them at <getopt-option-max-clarify/>!
 
     For each essential unknown to clarify, derive a short 1-3 word facet
     <facet-M/> and a corresponding question <question-M/> whose answer
@@ -185,7 +194,7 @@ Honor the following tenets throughout the brainstorming:
     the unconventional/wildcard angle - because variety in origin yields
     variety in outcome.
 
-    Do still *not* judge, rank, or prune ideas in this step. Generate
+    Still do *not* judge, rank, or prune ideas in this step. Generate
     ideas until you either reach at least <getopt-option-min-ideas/> distinct
     candidate ideas or have clearly exhausted the meaningfully distinct
     space.

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

@@ -11,6 +11,7 @@ allowed-tools:
     - "Bash(git diff *)"
     - "Bash(git show *)"
     - "Bash(git tag --list *)"
+    - "Read"
     - "Write"
     - "Edit"
 ---
@@ -106,14 +107,18 @@ Processing
     correct baseline Git tag. Take the `N.M.K` from the *first* (most
     recent) level-2 header in the *ChangeLog* file and check whether a
     corresponding Git tag already exists with the command `git tag --list
-    N.M.K`. If this command produces *no* output, the first section is
-    still in-progress/untagged, so use the `N.M.K` from the *second*
-    level-2 header as the baseline tag instead. If *no* second level-2
-    header exists (very first, still untagged release), skip the baseline
-    tag and check *all* Git commits with the command `git log HEAD
-    --numstat --pretty=format:'%h: %s'` instead. If this command *does*
-    produce output, the first section is already released/tagged, so use
-    the `N.M.K` from the *first* level-2 header as the baseline tag. Then
+    N.M.K`. If this command *does* produce output, the first section is
+    already released/tagged, so use the `N.M.K` from the *first* level-2
+    header as the baseline tag and *insert* a new, still-unreleased
+    level-2 section (next patch version, current date) *above* it, which
+    then becomes the *first* (most recent) section all subsequent steps
+    operate on - the already released section *MUST* *NOT* be modified.
+    If this command produces *no* output, the
+    first section is still in-progress/untagged, so use the `N.M.K` from
+    the *second* level-2 header as the baseline tag instead. If *no*
+    second level-2 header exists (very first, still untagged release),
+    skip the baseline tag and check *all* Git commits with the command
+    `git log HEAD --numstat --pretty=format:'%h: %s'` instead. Then
     check all Git commits between `HEAD` and this baseline tag with the
     command `git log N.M.K..HEAD --numstat --pretty=format:'%h: %s'`.
 

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

@@ -28,6 +28,15 @@ Query Foreign LLM for Chat
 Query foreign LLM for: <query><getopt-arguments/></query>
 </objective>
 
+<if condition="<query/> is empty">
+Only output the following <template/> and then immediately *STOP*
+processing the entire current skill:
+
+<template>
+⧉ **ASE**: ✪ skill: **ase-meta-chat**, ▶ ERROR: expected a `<query>` argument
+</template>
+</if>
+
 1.  You *MUST* *NOT* output anything in this step.
     Just call the underlying agent with the following tool:
 

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

@@ -8,6 +8,7 @@ disable-model-invocation: false
 effort: medium
 allowed-tools:
     - "Bash(git diff *)"
+    - "Bash(git ls-files *)"
 ---
 
 @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
@@ -32,10 +33,19 @@ currently staged Git changes.
 1.  <step id="STEP 1: Find out staged changes">
 
     Run the following command to find out details of what changes are
-    currently staged in the Git *index* for commit:
+    currently staged in the Git *index* for commit, capturing its output
+    into <diff/>:
 
     `git diff --cached`
 
+    <if condition="<diff/> is empty">
+    Only output the following <template/> and then *STOP* immediately:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-commit**, ▶ status: **no changes to commit**
+    </template>
+    </if>
+
     </step>
 
 2.  <step id="STEP 2: Craft a consolidated commit message">

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

@@ -34,8 +34,8 @@ on -- *control flow*, *XML placeholders*, *regex matching*, and
 *arithmetic* -- and report an overall **0%…100% compatibility** rating.
 
 This skill is unusual: it is both the *test definition* and the *system
-under test*. Each *probe* is a pure ASE construct that you execute and
-record its *actual* result. You *MUST NOT* compare against any expected
+under test*. Each *probe* is a pure ASE construct that you execute,
+recording its *actual* result. You *MUST NOT* compare against any expected
 value until STEP 6. Do not fabricate passes: a probe whose actual result
 differs from its expected result *MUST* be recorded as a *fail*.
 

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

@@ -41,7 +41,7 @@ of the decorative, eloquent, and explaining `writer`, the concise,
 factual, and accurate `engineer` (the default), the layered,
 pyramid-structured `journalist`, the brief, factual, and abbreviating
 `telegrapher`, or the terse, rough, and stuttering `caveman`;
-`agent.guidance` selects the amount of unsolicited hints and is one of
+`agent.guidance` selects the number of unsolicited hints and is one of
 `none`, `minimal`, `normal` (the default), or `verbose`; and
 `project.boxing` selects the artifact transparency and is one of `white`,
 `grey`, or `black`. Setting `agent.persona`, `agent.guidance`, or
@@ -78,7 +78,8 @@ preset-bootstrapping operation that stays a shell concern next to
     `user`, `project`, `task:`*id*, and/or `session:`*id* terms, in any
     order and at most one term per kind. The `user` term is always
     implicitly added at the bottom of the chain, and `project` is
-    implicitly added whenever a project context exists. If the option is
+    implicitly added whenever a project context exists, but never above
+    the strongest explicitly requested term. If the option is
     omitted, the chain of the *current session* (`session:`*id*) is used,
     so that reads see the full `user` -> `project` -> `session` cascade
     and writes -- including those to the session-only keys `agent.task`

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

@@ -37,6 +37,15 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
 
 1.  <step id="STEP 1: Restate Thesis">
 
+    <if condition="<thesis/> is empty">
+    Only output the following <template/> and then immediately *STOP*
+    processing the entire current skill:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-diaboli**, ▶ ERROR: expected a `<thesis>` argument
+    </template>
+    </if>
+
     Output the thesis with the following <template/>:
 
     <template>
@@ -112,10 +121,10 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
         just a contrarian.
 
     -   **Pre-Mortem Thinking**:
-        Imagine failure scenarios of the thesis, because better to
-        prevent them in advance than having to resolve them later.
+        Imagine failure scenarios of the thesis, because it is better to
+        prevent them in advance than to have to resolve them later.
 
-    For each Anti-Thesis or Counter-Argument rank it on a Likert scale
+    For each Anti-Thesis or Counter-Argument, rank it on a Likert scale
     of 0 (weak) to 10 (strong). Repeat the process of finding more
     Anti-Theses or Counter-Arguments until you EITHER have found at
     least <count/> Anti-Theses or Counter-Arguments with at least a rank

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

@@ -52,13 +52,13 @@ Procedure
         (taken exactly as given) and capturing the full diff output into
         <diff/> for the subsequent analysis:
 
-        `git diff --cached HEAD`
+        `git diff --cached`
 
     2.  Determine the *diff statistics* by running the corresponding command
         (taken exactly as given) and capturing the full stat output into
         <stat/> for the subsequent analysis:
 
-        `git diff --cached --numstat HEAD`
+        `git diff --cached --numstat`
 
     </step>
 
@@ -112,7 +112,7 @@ Procedure
             | **<intent/>** | <changes/> | <files/>: <description/> |
             </template>
 
-            In the <files/> part of the second column, markup all file
+            In the <files/> part of the second column, mark up all file
             references as code (with backticks), prepend them with `▢ `,
             append ` [+N/-M]` (based on the information in <stat/>) to them,
             and separate them with `, ` (a comma and space). Do *not* repeat
@@ -174,7 +174,7 @@ Procedure
             logging, `TODO`/`FIXME` scaffolding, disabled tests), which
             should be just removed and not part of any commit.
 
-    3.  A hunk that *serves* <thesis/> will be *not* reported. Only hunks that
+    3.  A hunk that *serves* <thesis/> will *not* be reported. Only hunks that
         do *not* serve it will be reported. If *every* hunk serves the thesis,
         the diff is *coherent* and you report *no* flagged hunks.
 
@@ -203,7 +203,7 @@ Procedure
         the hunk does not serve <thesis/> and what to do with it (e.g.
         split into its own commit, drop the debug residue).
 
-        In the <location/> column, markup all file references as code
+        In the <location/> column, mark up all file references as code
         (with backticks), prepend them with `▢ ` and append ` [+N/-M]`
         (based on the information in <stat/>) to them.
 
@@ -212,7 +212,7 @@ Procedure
 
         <template>
 
-        | Deviation        | Location    | Why it does not serve the thesis? |
+        | Deviation        | Location    | Why does it not serve the thesis? |
         | ---------------- | ----------- | --------------------------------- |
         | **<deviation/>** | <location/> | <reason/>                         |
 
@@ -278,7 +278,7 @@ Procedure
         and <mitigation/> texts *concise* and *ultra brief*. Do *not*
         output any further explanation.
 
-        In <evidence/> markup all file references as code (with
+        In <evidence/> mark up all file references as code (with
         backticks), prepend them with `▢ ` and append ` [+N/-M]` (based
         on the information in <stat/>) to them.
 
@@ -297,7 +297,7 @@ Procedure
 
     1.  From the *same* captured <diff/> and <stat/>, *extract the
         touched modules* - the distinct changed source files (or their
-        enclosing modules/ packages, according to the language idiom).
+        enclosing modules/packages, according to the language idiom).
 
     2.  Then, for each touched module, *scan its reverse dependencies*
         - the other first-party files that *import* or *reference* it
@@ -322,14 +322,14 @@ Procedure
             calling the tool `Agent(description: "Diagram Rendering",
             subagent_type: "ase:ase-meta-diagram", prompt:
             "<mermaid-spec/>", run_in_background: false)` and capture
-            its returned `text` field as <diagram/>.
+            its returned *fenced code block* verbatim as <diagram/>.
 
     4.  Then emit the following <template/>, showing <diagram/> and
         appending a *brief impact summary* of bullets, where each
         <module/> is a *touched* module and <impact/> is a one-sentence
         note on *what depends on it* and *how far the blast reaches*.
 
-        In <module/> and <impact/>, markup all file references as code
+        In <module/> and <impact/>, mark up all file references as code
         (with backticks), prepend them with `▢ ` and append ` [+N/-M]`
         (based on the information in <stat/>) to them.
 
@@ -341,9 +341,7 @@ Procedure
 
         <ase-tpl-bullet-signal/> **CHANGE BLAST RADIUS MAP**:
 
-        ```text
         <diagram/>
-        ```
 
         <ase-tpl-bullet-signal/> **BLAST**: ⚑ **<module/>**: <impact/>
 
@@ -351,7 +349,7 @@ Procedure
 
         [...]
 
-        <ase-tpl-foot/>
+        <ase-tpl-foot title="CHANGE BLAST RADIUS"/>
         </template>
 
     </step>

package/plugin/skills/ase-meta-eli5/SKILL.md

@@ -29,7 +29,7 @@ Explain a Topic Like I'm 5
 
 <objective>
 *Explain* the following topic in "Explain Like I'm 5" (ELI5) style,
-so that even a five year old child could understand it:
+so that even a five-year-old child could understand it:
 <topic><getopt-arguments/></topic>
 </objective>
 
@@ -46,7 +46,7 @@ so that even a five year old child could understand it:
     </template>
     </if>
 
-    Set <facts></facts> (set to empty)
+    Set <facts></facts> (set to empty).
 
     </step>
 
@@ -80,7 +80,7 @@ so that even a five year old child could understand it:
 3.  <step id="STEP 3: Explain Topic">
 
     Explain the <topic/> in "Explain Like I'm 5" (ELI5) style: use
-    *simple*, *jargon-free* wording a five year old child could
+    *simple*, *jargon-free* wording a five-year-old child could
     understand -- short sentences, everyday words, and familiar images.
     Do *not* use technical terms without immediately putting them into
     child-friendly words.

package/plugin/skills/ase-meta-eli5/help.md

@@ -13,7 +13,7 @@
 ##  DESCRIPTION
 
 The `ase-meta-eli5` skill explains the supplied *topic* in "Explain
-Like I'm 5" (ELI5) style, so that even a five year old child could
+Like I'm 5" (ELI5) style, so that even a five-year-old child could
 understand it. The explanation uses simple, jargon-free wording --
 short sentences, everyday words, and familiar images -- and is
 structured into three labeled blocks: *WHAT* (a plain-words summary),

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

@@ -114,12 +114,12 @@ multi-*criteria* decision matrix.
 
     -   For each criterion <criteria-L/> (L=1-M), decide on its <weight-L/>
         from the value set { 4.00, 2.00, 1.00, 0.50, 0.25 } (from most
-        important, over normal, to less important). Do not output anything.
+        important, via normal, to less important). Do not output anything.
 
     -   Ensure the final number of criteria is always within the range of
         minimum 8 and maximum 12: if fewer than 8 criteria were requested,
         use the set of alternatives to decide on additional criteria
-        which potentially allow best to triage the alternatives, take the
+        which potentially best allow triaging the alternatives, take the
         <reason/> into account, and use the `ase-meta-search` skill (drawing from
         the *skill-wide shared budget* of at most 8 `ase-meta-search` invocations
         in total across STEP 2 and STEP 3 combined) to find out about the
@@ -145,7 +145,7 @@ multi-*criteria* decision matrix.
     -   For each alternative <alternative-K/> (K=1-N) and each criterion
         <criteria-L/> (L=1-M), decide on the evaluation <eval-K-L/>, which
         means how well the alternative meets the criterion on a Likert-scale
-        from { -2, -1, 0, +1, +2 } (from worst, over neutral, to best). Do
+        from { -2, -1, 0, +1, +2 } (from worst, via neutral, to best). Do
         not output anything.
 
     -   Then, calculate the ratings <rating-K/> (K=1-N) for all

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

@@ -38,6 +38,21 @@ by querying *multiple* AIs for an *optimal consensus*.
 
 1.  <step id="STEP 1: Preview Own Answer">
 
+    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 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`, `claude`, `codex`,
+    `copilot`. If 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-quorum**, ▶ ERROR: invalid `--models` token: **<token/>**
+    </template>
+
     Prepare the LLM query by setting <query/> to the following <template/>:
 
     <template>
@@ -64,21 +79,6 @@ by querying *multiple* AIs for an *optimal consensus*.
 
 2.  <step id="STEP 2: Query Foreign AIs">
 
-    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 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`, `claude`, `codex`,
-    `copilot`. If 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-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 API-based models). The
@@ -143,7 +143,7 @@ by querying *multiple* AIs for an *optimal consensus*.
     Agents which returned a response with an `ERROR:` prefix are
     silently skipped and are treated as not available.
 
-    Summarize all responses, of both yourself and all available agents
+    Summarize all responses, of both yourself and all available agents,
     with just 1 to 7 corresponding bullet points and with short
     sentences.
 
@@ -178,7 +178,7 @@ 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
+    Finally, show the summary, the consensus, and the complete and
     unmodified responses of yourself and each of the queried foreign
     AIs, based on the following output <template/>:
 

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

@@ -185,7 +185,7 @@ Find Quotes on a Topic
         -   ` *(unverified)*` if the exact wording or the attribution of
             the quote could not be established with confidence -- but
             omit this marker for a quote whose wording and attribution
-            the Internet/Web search of STEP 2.2 confirmed -- including
+            the Internet/Web search of STEP 2.2 confirmed, including
             its re-application for a neighborhood topic in STEP 3.
 
         Render the single line `○   (none)` for a quadrant without any

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

@@ -150,14 +150,16 @@ Procedure
         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
-        remainder of this STEP 3 (an empty finding list implies the
-        `APPROVE` verdict, so the closing hint of substep 4 would expand
+        Only output the following <template/> - with <note/> set to `the
+        change was not reviewed` if <verdict/> starts with `SKIPPED` and
+        to `the change is clean` otherwise - and then *SKIP* the
+        remainder of this STEP 3 (an empty finding list never yields the
+        `REJECT` verdict, so the closing hint of substep 4 would expand
         into nothing anyway):
 
         <template>
 
-        <ase-tpl-bullet-normal/> **NO FINDINGS**: the change is clean, nothing to flag.
+        <ase-tpl-bullet-normal/> **NO FINDINGS**: <note/>, nothing to flag.
 
         </template>
         </if>
@@ -173,7 +175,7 @@ Procedure
         <dimension/> to its `dimension` field, set <location/> to its
         `location` field, and set <finding/> to its `finding` field.
 
-        In the <location/> column, markup the `file:line` reference
+        In the <location/> column, mark up the `file:line` reference
         as code (with backticks) and prepend it with `▢ ` - keep the
         sub-agent's own `:N` / `:N-M` line citation intact and do *not*
         append any further line-count decoration.

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

@@ -45,12 +45,12 @@ sub-agent so that the silent reading and read-only repository probing
 never leak into the transcript; only the structured verdict and findings
 are rendered.
 
-The skill *complements* rather than duplicates its neighbours:
+The skill *complements* rather than duplicates its neighbors:
 `ase-code-lint` flags *mechanical* code-quality issues, `ase-code-analyze`
 inspects *logic and semantics*, `ase-meta-diff` narrates *what changed*
 (with optional coherence, risk, and blast-radius reports), and
 `ase-meta-diaboli` *adversarially challenges a thesis* - whereas
-`ase-meta-review` renders a *reviewer's judgement* on a concrete diff
+`ase-meta-review` renders a *reviewer's judgment* on a concrete diff
 before it is committed.
 
 ##  OPTIONS

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

@@ -38,6 +38,15 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
 
 1.  <step id="STEP 1: Query Search Services">
 
+    <if condition="<query/> is empty">
+    Only output the following <template/> and then immediately *STOP*
+    processing the entire current skill:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-search**, ▶ ERROR: expected a `<query>` argument
+    </template>
+    </if>
+
     <define name="agent">
     ```text
         Agent(
@@ -105,6 +114,15 @@ Your objective is to *search* the *Internet*/*Web* for the following query:
         Call the tool `web_search(query: "<query/>")`.
     </expand>
 
+    If *none* of the selected backends could be invoked - because no
+    corresponding tool is available - only output the following
+    <template/> and then immediately *STOP* processing the entire current
+    skill:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-search**, ▶ ERROR: no search backend available: **<getopt-option-services/>**
+    </template>
+
     </step>
 
 2.  <step id="STEP 2: Consolidate Search Answers">

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

@@ -41,6 +41,15 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
 
 1.  <step id="STEP 1: Restate Thesis">
 
+    <if condition="<thesis/> is empty">
+    Only output the following <template/> and then immediately *STOP*
+    processing the entire current skill:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-steelman**, ▶ ERROR: expected a `<thesis>` argument
+    </template>
+    </if>
+
     Begin a *round* of fortification and consolidating reasoning. On
     the first visit, set <i>1</i> (set round counter to one); on each
     subsequent visit (via the jump back in the last step), <i/> has
@@ -125,7 +134,7 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
 
     -   **Argue in Good Faith**:
         Make clear you are building the best honest case, not
-        overselling, because the goal of the objective is a better
+        overselling, because the goal is a better
         final decision, not a sales pitch.
 
     -   **Concede the Real Weaknesses**:
@@ -137,7 +146,7 @@ to <getopt-option-count/>; if <getopt-option-count/> is *non-numeric* or
         Imagine success scenarios of the thesis, because envisioning
         how it wins clarifies the conditions worth securing in advance.
 
-    For each Pro-Thesis or Supporting-Argument rank it on a Likert
+    For each Pro-Thesis or Supporting-Argument, rank it on a Likert
     scale of 0 (weak) to 10 (strong). Repeat the process of finding
     more Pro-Theses or Supporting-Arguments until you EITHER have found
     at least <count/> Pro-Theses or Supporting-Arguments with at least a

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

@@ -37,6 +37,15 @@ addressing surface-level symptoms.
 
 1.  <step id="STEP 1: Restate Problem">
 
+    <if condition="<getopt-arguments/> is empty">
+    Only output the following <template/> and then immediately *STOP*
+    processing the entire current skill:
+
+    <template>
+    ⧉ **ASE**: ✪ skill: **ase-meta-why**, ▶ ERROR: expected a `<fact>` argument
+    </template>
+    </if>
+
     State the problem statement.
 
     <template>
@@ -67,16 +76,16 @@ addressing surface-level symptoms.
         <while condition="<n/> is less than or equal to <depth/>">
 
             Ask <question/> and document the answer in <answer/> with the following template.
-            Don't stop at symptoms, keep digging for systemic issues.
+            Don't stop at symptoms; keep digging for systemic issues.
             Consider technical, domain-specific, process-related, or organizational causes.
 
             <template>
             <ase-tpl-bullet-secondary/> **WHY <n/>**: <answer/>
             </template>
 
-            Then, for the next iteration set <question/> now to be the last <answer/>.
-            The magic is NOT in exactly <depth/> "Why" -- you can <break/>
-            the iteration when you already reached the root-cause.
+            Then, for the next iteration, set <question/> now to be the last <answer/>.
+            The magic is NOT in exactly <depth/> "Whys" -- you can <break/>
+            the iteration when you have already reached the root-cause.
             Finally, set <n/> to <n/> + 1 (increment iteration counter).
 
         </while>
@@ -108,7 +117,7 @@ addressing surface-level symptoms.
             *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.
+            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.
@@ -136,7 +145,7 @@ addressing surface-level symptoms.
 
             Record the remaining candidates as <fallbacks/> for level <n/>.
             Then, for the next iteration, set <question/> to the chosen candidate.
-            You can <break/> the iteration when the chosen candidate already
+            You can <break/> the iteration when the chosen candidate has already
             reached its root-cause.
             Finally, set <n/> to <n/> + 1 (increment iteration counter).
 

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

@@ -44,9 +44,9 @@ source code changes.
     candidate sub-causes, descends into the single most significant one
     (justifying the choice), and retains the rest as *fallbacks*. During
     backward validation a mis-rooted choice is *backtracked* into a fallback
-    and re-descended, so the widening actively improves which root-cause is
+    and re-descended, so the widening actively improves which root cause is
     reached rather than merely listing alternatives. The result is still a
-    single, but better-justified, root-cause. A non-numeric or non-positive
+    single, but better-justified, root cause. A non-numeric or non-positive
     value falls back to the default.
 
 ##  ARGUMENTS
@@ -71,7 +71,7 @@ Drill down deeper with a tunable chain length of seven:
 ```
 
 Weigh several candidate sub-causes per level (with backtracking) to avoid
-committing early to the wrong root-cause:
+committing early to the wrong root cause:
 
 ```text
 ❯ /ase-meta-why -w 3 the release was delayed by two weeks

package/plugin/skills/ase-sync-export/SKILL.md

@@ -10,7 +10,8 @@ user-invocable: true
 disable-model-invocation: false
 effort: xhigh
 allowed-tools:
-    - Write
+    - "Read"
+    - "Write"
 ---
 
 @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md

package/plugin/skills/ase-sync-export/help.md

@@ -73,4 +73,4 @@ Export only the data-model artifact:
 ##  SEE ALSO
 
 [`ase-sync-reconcile`](../ase-sync-reconcile/help.md),
-[`ase-sync-import`](../ase-sync-import/help.md)
+[`ase-sync-import`](../ase-sync-import/help.md).