@rse/ase 0.0.60 → 0.0.62

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

@@ -36,7 +36,7 @@ Analyze documents for spelling, punctuation, or grammar errors
     First, use the following <template/> to give a hint on this step:
 
     <template>
-    &#x26AA; **PROOFREADING INVESTIGATION**
+    <ase-tpl-bullet-secondary/> **PROOFREADING INVESTIGATION**
     </template>
 
     Dispatch the investigation to a *sub-agent* via the `Agent`
@@ -69,7 +69,7 @@ Analyze documents for spelling, punctuation, or grammar errors
     problems in <problems/>:
 
     <template>
-    &#x26AA; **PROOFREADING SUMMARY**:
+    <ase-tpl-bullet-secondary/> **PROOFREADING SUMMARY**:
 
     | *Proofread Type* | *Proofread Result*      |
     | ---------------- | ----------------------- |
@@ -109,7 +109,7 @@ Analyze documents for spelling, punctuation, or grammar errors
         2.  Report the problem with the following <template/>:
 
             <template>
-            &#x1F7E0; **<type/> PROBLEM**: `<file/>`:<line/>:
+            <ase-tpl-bullet-signal/> **<type/> PROBLEM**: `<file/>`:<line/>:
 
             <description/>
             </template>
@@ -121,7 +121,7 @@ Analyze documents for spelling, punctuation, or grammar errors
 
             <template>
 
-            &#x1F535; **<type/> CORRECTION**:
+            <ase-tpl-bullet-normal/> **<type/> CORRECTION**:
 
             ```diff
             --- <file/> (original)
@@ -201,7 +201,7 @@ Analyze documents for spelling, punctuation, or grammar errors
         following final <template/>:
 
         <template>
-        &#x26AA; **PROOFREAD FINISHED**
+        <ase-tpl-bullet-secondary/> **PROOFREAD FINISHED**
         </template>
 
     </step>

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

@@ -51,4 +51,4 @@ Proofread an entire documentation directory automatically:
 
 ##  SEE ALSO
 
-`ase-code-lint`, `ase-meta-changes`.
+`ase-code-lint`, `ase-meta-changelog`.

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

@@ -0,0 +1,220 @@
+---
+name: ase-meta-brainstorm
+argument-hint: "[--help|-h] <topic>"
+description: >
+    Collaboratively brainstorm a topic by diverging on ideas, converging
+    through clustering and scoring, and distilling a shortlist with
+    a recommended direction. Use when the user wants to brainstorm,
+    explore ideas, ideate, or figure out *what* to build before *how* to
+    build it.
+user-invocable: true
+disable-model-invocation: false
+effort: high
+---
+
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
+@${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
+@${CLAUDE_SKILL_DIR}/../../meta/ase-dialog.md
+
+<skill name="ase-meta-brainstorm">
+Collaboratively Brainstorm a Topic
+</skill>
+
+<objective>
+Collaboratively brainstorm the topic <topic>$ARGUMENTS</topic> by first
+*diverging* into a broad space of candidate ideas, then *converging*
+through clustering and scoring, and finally distilling a *shortlist*
+with a single recommended direction.
+</objective>
+
+Guiding Tenets
+--------------
+
+Honor the following tenets throughout the brainstorming:
+
+-   **No Assumption of Simplicity**:
+    Every topic goes through the full process — a one-line config
+    change as much as a new subsystem — because the simplest-looking
+    topics often hide the most harmful assumptions.
+
+-   **Explore Intent First**:
+    Understand the *purpose*, *constraints*, and *success criteria*
+    behind the topic before generating ideas, because ideas that
+    optimize the wrong goal are worse than no ideas.
+
+-   **Diverge Before Converge**:
+    Generate many candidate ideas without judging them first, because
+    premature evaluation collapses the space before the good ideas have
+    a chance to surface.
+
+-   **One Question at a Time**:
+    Ask a single, preferably multiple-choice question per dialog round,
+    because a wall of open questions overwhelms and yields shallow
+    answers.
+
+-   **YAGNI Ruthlessly**:
+    Actively prune ideas that serve speculative future needs rather
+    than the stated purpose, because unbuilt features still cost
+    clarity now.
+
+-   **Ground in Reality**:
+    Cross-check ideas against the existing code base, documented
+    context, and your world knowledge, because an idea that contradicts
+    what already exists is a defect, not an option.
+
+-   **Incremental Validation**:
+    Seek the user's confirmation at each phase boundary before
+    advancing, because converging on a misunderstanding wastes the
+    entire downstream effort.
+
+<flow>
+
+1.  <step id="STEP 1: Restate Topic">
+
+    Restate the topic to be brainstormed by output the following <template/>:
+
+    <template>
+    <ase-tpl-bullet-secondary/> **TOPIC**: <topic/>
+    </template>
+
+    </step>
+
+2.  <step id="STEP 2: Clarify Intent">
+
+    Before generating any ideas, *explore the project context* (review
+    relevant existing files, documentation, and recent changes) and
+    determine the <m/> *essential unknowns* about the topic — the
+    purpose, constraints, scope boundaries, and success criteria that
+    must be pinned down for the brainstorming to be reasonably grounded.
+
+    For each essential unknown, derive a short 1-3 word facet <facet-M/>
+    and a corresponding question <question-M/> whose answer materially
+    changes which ideas make sense at all.
+
+    1.  For each <question-M/> in the iteration cycle <M/> (<M/>=1...<m/>):
+
+        1.  Output the following <template/>:
+
+            <template>
+            <ase-tpl-bullet-signal/> FACET <M/>/<m/>: **<facet-M/>**, QUESTION: **<question-M/>**
+            </template>
+
+        2.  Determine *up 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)
+
+            <expand name="user-dialog">
+                <facet-M/>: <question-M/>
+                <answer-M-1/>: (first grounded candidate answer)
+                <answer-M-2/>: (second grounded candidate answer)
+                <answer-M-3/>: (third grounded candidate answer)
+                <answer-M-4/>: (forth grounded candidate answer)
+            </expand>
+
+        4.  Output the following <template/>:
+
+            <template>
+            <ase-tpl-bullet-normal/> FACET <M/>/<m/>: **<facet-M/>**, ANSWER: **<answer-M/>**
+            </template>
+
+    2.  If at any point <result/> is `CANCEL`:
+        Only output the following <template/> and then immediately *STOP*
+        processing the entire current skill:
+
+        <template>
+        ⧉ **ASE**: ✪ skill: **ase-meta-brainstorm**, ▶ status: **brainstorm cancelled**
+        </template>
+
+    </step>
+
+3.  <step id="STEP 3: Diverge Idea Space">
+
+    Generate a *broad* space of candidate ideas that address the
+    <topic/> within the constraints established by the answers
+    <answer-M/>.
+
+    Deliberately pursue *diverse angles* — e.g. the minimal/MVP-first
+    angle, the robustness/risk-first angle, the user-experience-first
+    angle, the reuse-existing-machinery angle, the coolness angle, and
+    the unconventional/wildcard angle — because variety in origin yields
+    variety in outcome.
+
+    Do still *not* judge, rank, or prune ideas in this step. Generate
+    ideas until you either reach at least 12 distinct candidate ideas or
+    have clearly exhausted the meaningfully distinct space.
+
+    Store each candidate idea in <idea-N/> with the format
+    `**<idea-name-N/>**: <idea-statement-N/>` (where <idea-name-N/> is a
+    short 1-4 word summary and <idea-statement-N/> is a single-sentence
+    statement of not more than 40 words), and output the following
+    <template/>:
+
+    <template>
+    <ase-tpl-bullet-normal/> **IDEA <N/>**: <idea-N/>
+    </template>
+
+    </step>
+
+4.  <step id="STEP 4: Converge Idea Space">
+
+    Converge the candidate ideas <idea-N/> into a smaller, structured
+    sets 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
+        near-duplicates and discarding ideas pruned by *You Aren't Gonna
+        Need It (YAGNI)* (speculative, out-of-scope, or contradicting
+        documented context).
+
+        For each cluster and its contained retained ideas, output the
+        following <template/> (<cluster-summary-C/> is a single-sentence
+        statement of not more than 40 words):
+
+        <template>
+        <ase-tpl-bullet-secondary/> **IDEA CLUSTER <C/>/<c/>**: <cluster-C/> — <cluster-summary-C/>,
+        **IDEAS**: <N/>, <M/>[, ...]
+        </template>
+
+    2.  *Score*: for each retained idea <idea-N/> in the clusters, rank its *fit* against the
+        purpose and constraints on a Likert scale of 0 (poor) to 10
+        (excellent), considering *value*, *uniqueness*, *risk*, and
+        *alignment with the existing code base*. Keep only ideas in the
+        clusters with a rank of at least 7.
+
+    3.  From the scored ideas <idea-N/>, distill a *shortlist* of the top
+        3-4 options, sorted by rank from highest to lowest.
+
+        For this, draw the shortlist from *distinct* clusters <cluster-C/>
+        wherever possible — prefer a diverse shortlist spanning different
+        clusters over several high-ranked variations of the same cluster,
+        unless one cluster clearly dominates on rank.
+
+        Store each distilled option in <option-N/> with the format
+        `**<option-name-N/>** (rank: <option-rank-N/>/10, cluster:
+        <option-cluster-N/>): <option-statement-N/>` (where the statement is
+        a single sentence of not more than 40 words capturing the direction
+        and its primary trade-off), and output the following <template/>:
+
+        <template>
+        <ase-tpl-bullet-normal/> **DISTILLED IDEA <N/>**: <option-N/>
+        </template>
+
+    4.  Finally, derive a single *recommended idea* — the highest-ranked
+        option, or a principled synthesis of the option shortlist that preserves
+        what is strongest in each — store its one-sentence rationale (not
+        more than 40 words) in <recommendation/>, and output the following
+        <template/>:
+
+        <template>
+        <ase-tpl-bullet-signal/> **RECOMMENDED IDEA**: <recommendation/>
+        </template>
+
+    </step>
+
+</flow>

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

@@ -0,0 +1,51 @@
+
+##  NAME
+
+`ase-meta-brainstorm` - Collaboratively Brainstorm a Topic
+
+##  SYNOPSIS
+
+`ase-meta-brainstorm`
+    [`--help`|`-h`]
+    *topic*
+
+##  DESCRIPTION
+
+The `ase-meta-brainstorm` skill guides a collaborative ideation
+session on a *topic* *before* any implementation begins. It first
+*clarifies intent* by exploring the project context and interviewing
+the user — one grounded, multiple-choice question at a time — about
+purpose, constraints, scope, and success criteria. It then *diverges*
+into a broad space of candidate ideas pursued from deliberately diverse
+angles (MVP-first, risk-first, UX-first, reuse-first, and wildcard),
+without judging them.
+
+Next it *converges* by clustering the ideas into coherent themes,
+pruning speculative or out-of-scope ones via *YAGNI*, and scoring the
+survivors on a 0-10 fit scale (keeping only those ranked 7 or higher).
+Finally it distills a *shortlist* of the top 3-4 directions — drawn from
+distinct clusters 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.
+
+##  ARGUMENTS
+
+*topic*:
+    The subject to brainstorm — a feature, component, behavior, or
+    design question to explore *what* to build before *how*.
+
+##  EXAMPLES
+
+Brainstorm an approach for a new feature:
+
+```text
+❯ /ase-meta-brainstorm an offline-first sync layer for the mobile app
+```
+
+##  SEE ALSO
+
+`ase-meta-evaluate`, `ase-meta-quorum`, `ase-meta-diaboli`

package/plugin/skills/{ase-meta-changes → ase-meta-changelog}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: ase-meta-changes
+name: ase-meta-changelog
 argument-hint: "[--help|-h]"
 description: >
     Update changes entries in CHANGELOG.md files
@@ -17,7 +17,7 @@ allowed-tools:
 @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 
-<skill name="ase-meta-changes">
+<skill name="ase-meta-changelog">
 Update ChangeLog Entries
 </skill>
 
@@ -63,7 +63,7 @@ Processing
     following <template/>:
 
     <template>
-    &#x1F535; **CHANGELOG FILE:** `<filename/>`
+    <ase-tpl-bullet-normal/> **CHANGELOG FILE:** `<filename/>`
     </template>
 
     </step>
@@ -74,7 +74,7 @@ Processing
     operation with an output based on the following <template/>:
 
     <template>
-    &#x1F535; **DETERMINE ARTIFACT CHANGES:**
+    <ase-tpl-bullet-normal/> **DETERMINE ARTIFACT CHANGES:**
     </template>
 
     To update to entries of the most recent *ChangeLog* section, consult
@@ -102,7 +102,7 @@ Processing
     operation with an output based on the following <template/>:
 
     <template>
-    &#x1F535; **COMPLETE ENTRIES:**
+    <ase-tpl-bullet-normal/> **COMPLETE ENTRIES:**
     </template>
 
     Without immediately modifying the `CHANGELOG.md` file, *complete*
@@ -127,7 +127,7 @@ Processing
     operation with an output based on the following <template/>:
 
     <template>
-    &#x1F535; **CONSOLIDATE ENTRIES:**
+    <ase-tpl-bullet-normal/> **CONSOLIDATE ENTRIES:**
     </template>
 
     Without immediately modifying the `CHANGELOG.md` file, *consolidate*
@@ -147,7 +147,7 @@ Processing
     operation with an output based on the following <template/>:
 
     <template>
-    &#x1F7E0; **UPDATING CHANGELOG:**
+    <ase-tpl-bullet-signal/> **UPDATING CHANGELOG:**
     </template>
 
     Finally, *update* the `CHANGELOG.md` file with the completed,

package/plugin/skills/{ase-meta-changes → ase-meta-changelog}/help.md

@@ -1,16 +1,16 @@
 
 ##  NAME
 
-`ase-meta-changes` - Update ChangeLog Entries
+`ase-meta-changelog` - Update ChangeLog Entries
 
 ##  SYNOPSIS
 
-`ase-meta-changes`
+`ase-meta-changelog`
     [`--help`|`-h`]
 
 ##  DESCRIPTION
 
-The `ase-meta-changes` skill helps to *complete*, *consolidate*, and
+The `ase-meta-changelog` skill helps to *complete*, *consolidate*, and
 *sort* the entries of the most recent section of a `CHANGELOG.md`
 file, based on the underlying *Git* commits and the currently staged
 changes in the Git *index*.
@@ -25,7 +25,7 @@ date in the section header is also updated to the current date.
 Update the most recent ChangeLog section:
 
 ```text
-❯ /ase-meta-changes
+❯ /ase-meta-changelog
 ```
 
 ##  SEE ALSO

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

@@ -28,4 +28,4 @@ Craft a commit message for the currently staged changes:
 
 ##  SEE ALSO
 
-`ase-meta-changes`.
+`ase-meta-changelog`.

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

@@ -27,7 +27,7 @@ effort: xhigh
     Output the thesis with the following <template/>:
 
     <template>
-    &#x26AA; **THESIS**: <thesis/>
+    <ase-tpl-bullet-secondary/> **THESIS**: <thesis/>
     </template>
 
 2.  **Determine Anti-Thesis**:
@@ -117,7 +117,7 @@ effort: xhigh
     <template/>:
 
     <template>
-    &#x1F7E0; **ANTITHESIS**: <antithesis-N/>
+    <ase-tpl-bullet-signal/> **ANTITHESIS**: <antithesis-N/>
     </template>
 
 3.  **Dialectical Reasoning**:
@@ -147,6 +147,6 @@ effort: xhigh
     in <synthesis/>, and then finally output the following <template/>:
 
     <template>
-    &#x1F535; **SYNTHESIS**: <synthesis/>
+    <ase-tpl-bullet-normal/> **SYNTHESIS**: <synthesis/>
     </template>