@rse/ase 0.9.48 → 0.9.50

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

@@ -1,84 +0,0 @@
----
-name: ase-meta-persona
-argument-hint: "[--help|-h] [<persona>]"
-description: >
-    Adjust communication style in five intensity levels of token usage.
-    The <persona> can be either the decorative, eloquent, and explaining "writer",
-    the concise, factual, and accurate "engineer" (default),
-    the layered, pyramid-structured "journalist",
-    the brief, factual, and abbreviating "telegrapher",
-    or the terse, rough, and stuttering "caveman".
-    Use when user says "persona <persona>" or "be <persona>".
-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-getopt.md
-
-<skill name="ase-meta-persona">
-Persona Configuration
-</skill>
-
-<expand name="getopt" arg1="ase-meta-persona">
-    $ARGUMENTS
-</expand>
-
-<objective>
-*Configure* the *persona style* of the agent to adjust the communication
-style and token usage intensity.
-</objective>
-
-1.  Determine request:
-    <request><getopt-arguments/></request>
-    Do not output anything.
-
-2.  <if condition="<request/> is empty">
-    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.
-
-    2.  Output the following <template/>:
-
-        <template>
-        ⧉ **ASE**: ☯ persona: **<ase-persona-style/>**
-        </template>
-    </if>
-
-3.  <if condition="<request/> is NOT empty">
-    1.  If <request/> is NEITHER 'writer', 'engineer', 'journalist',
-        'telegrapher', NOR 'caveman', report this with the following
-        <template/> and then *STOP* immediately:
-
-        <template>
-        ⧉ **ASE**: **ERROR:** invalid persona: "<request/>" (expected `writer`, `engineer`, `journalist`, `telegrapher`, or `caveman`)
-        </template>
-
-    2.  If <request/> is equal <ase-persona-style/> report this with the
-        following <template/> and then *STOP* immediately:
-
-        <template>
-        ⧉ **ASE**: ☯ persona: **<ase-persona-style/>** (*unchanged*)
-        </template>
-
-    3.  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.
-
-        Then you *MUST* re-evaluate and internalize the conditional
-        rules provided under `Persona Communication Style` in the
-        constitution in order to immediately honor the changed
-        communication style in all following outputs!
-
-        Do not output anything.
-
-    4.  Output the following <template/>:
-
-        <template>
-        ⧉ **ASE**: ☯ persona: **<ase-persona-style/>** (*updated*)
-        </template>
-    </if>
-

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

@@ -1,60 +0,0 @@
-
-##  NAME
-
-`ase-meta-persona` - Persona Configuration
-
-##  SYNOPSIS
-
-`ase-meta-persona`
-    [`--help`|`-h`]
-    [*persona*]
-
-##  DESCRIPTION
-
-The `ase-meta-persona` skill gets or sets the active *communication
-style* (persona) of the assistant. Five intensity levels of token
-usage are supported, from most verbose to most terse:
-
--   `writer`: decorative, eloquent, and explaining; full prose
-    sentences bundled into paragraphs separated by blank lines
--   `engineer`: concise, factual, and accurate (default); prefers
-    bullet point lists with one aspect per bullet
--   `journalist`: layered, pyramid-structured; every aspect a single-line
-    bullet following `**<title>**: <core> ▶ **<keywords>**: <details>.`,
-    with a one-to-two word title, a terse core, one-to-four keywords, and
-    a one-to-four sentence detail
--   `telegrapher`: brief, factual, and abbreviating; every aspect a
-    single-line bullet following `**<title>**: <core>.`, with a one-to-two
-    word title and a terse, arrow/em-dash-joined core
--   `caveman`: terse, rough, and stuttering; every aspect a single-line
-    bullet with a very terse core of one-word fields or a one-to-two word
-    expression
-
-Without arguments, the skill reports the currently active persona.
-With a *persona* argument, it switches to that persona via the
-`ase_persona` MCP tool.
-
-##  ARGUMENTS
-
-*persona*:
-    The persona to activate; one of `writer`, `engineer`, `journalist`,
-    `telegrapher`, or `caveman`. If omitted, the currently active
-    persona is reported.
-
-##  EXAMPLES
-
-Show the currently active persona:
-
-```text
-❯ /ase-meta-persona
-```
-
-Switch to the telegrapher persona:
-
-```text
-❯ /ase-meta-persona telegrapher
-```
-
-##  SEE ALSO
-
-[`ase-task-id`](../ase-task-id/help.md).