@rse/ase 0.9.51 → 0.9.52

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

@@ -0,0 +1,117 @@
+
+##  NAME
+
+`ase-meta-workflow` - Generate a Workflow Skill
+
+##  SYNOPSIS
+
+`ase-meta-workflow`
+    [`--help`|`-h`]
+    [`--scope`|`-s` `local`|`user`]
+    [`--force`|`-f`]
+    *skill-name*
+    *workflow-description*
+
+##  DESCRIPTION
+
+The `ase-meta-workflow` skill *generates* a new, regular skill of the
+currently used *agent tool* -- written in the style of *ASE* skills --
+which orchestrates the workflow given as *workflow-description*.
+
+The *workflow-description* is treated as a combination of *sequential*
+actions, *concurrent* actions, *sub-agent* invocations, *skill*
+invocations, and arbitrary other action statements. The skill maps them
+onto the ASE control constructs: top-level sequential actions become
+numbered `<step>` items inside a single `<flow>`, concurrent actions
+become a `<parallel>` block, sub-agent invocations become `<agent>`
+elements, and skill invocations become `<skill>` elements. Whenever a
+`<parallel>` block contains at least one `<agent isolation="worktree">`,
+a dedicated consolidation step holding `<agent-consolidation/>` is
+appended right after it, so the Git WorkTrees of the concurrent
+sub-agents are merged and removed again. Every top-level `<skill>`
+invocation is additionally enclosed in its own `<agent>` element --
+without `isolation` and with `run_in_background=false` -- so the
+`TaskCreate` and `TaskUpdate` tool calls of the called skill cannot
+interfere with the task tracking of the generated workflow skill itself.
+
+To keep the emitted `<skill>` invocations correct, the skill consults the
+accumulated manual pages of all ASE skills and takes every option and
+argument verbatim from them. To keep the emitted flow meaningful, it
+consults the *ASE workflow graph* -- a list of `<from> -> <to>`
+transitions between ASE skills and logical states such as `START`,
+`SKETCH`, `TASK`, `ARTIFACT`, and `END`. That graph *guides* the
+derivation but never restricts it: arbitrary non-ASE actions and
+unlisted transitions stay allowed.
+
+The generated skill is *independent* of the ASE plugin installation path:
+it loads the ASE meta definitions through the `ase meta` command instead
+of plugin-relative includes.
+
+The skill is *portable* across the supported agent tools, because
+*Anthropic Claude Code*, *GitHub Copilot*, and *OpenAI Codex* differ in
+three relevant ways, each of which is dispatched on the currently used
+agent tool:
+
+-   the *target directory*, because every agent tool discovers its skills
+    in its own locations,
+
+-   the *frontmatter fields*, because every agent tool accepts its own
+    field set and its own `allowed-tools` permission grammar, and
+
+-   the *preamble*, because only *Anthropic Claude Code* expands the
+    ``!`...`` construct before the skill content reaches the model. The
+    other agent tools receive it verbatim and would silently leave it
+    unexpanded, so they instead get an explicit instruction to run
+    `ase meta ...` themselves before anything else.
+
+##  OPTIONS
+
+`--scope`|`-s` `local`|`user`:
+    Where the generated skill is stored. With `local` (the default),
+    it is written into the current project, where it can be committed
+    and reviewed alongside the code. With `user`, it is written into the
+    personal skill directory, where it is available across all projects.
+    The concrete directory depends on the currently used agent tool:
+    `.claude/skills/` and `~/.claude/skills/` under *Anthropic Claude
+    Code*, `.github/skills/` and `~/.copilot/skills/` under *GitHub
+    Copilot*, and `.agents/skills/` and `~/.codex/skills/` under *OpenAI
+    Codex*.
+
+`--force`|`-f`:
+    Overwrite an already existing skill. Without this option, the skill
+    refuses with an error as soon as the target `SKILL.md` exists, so
+    hand-edited skills are never lost silently.
+
+##  ARGUMENTS
+
+*skill-name*:
+    Name of the skill to generate, matching `^[a-zA-Z][a-zA-Z0-9_-]*$`.
+    It is used as the directory name, as the frontmatter `name`, and as
+    the resulting `/`*skill-name* command (respectively the
+    `$`*skill-name* mention under *OpenAI Codex*).
+
+*workflow-description*:
+    Free-text description of the workflow the generated skill should
+    perform. Mentioning that actions run "in parallel", that they are
+    dispatched "in a sub-agent", or naming concrete `ase-xxx-xxx` skills
+    steers the derived structure accordingly.
+
+##  EXAMPLES
+
+Generate a project-local skill which analyzes the code and then resolves
+every finding concurrently in isolated worktrees:
+
+```text
+❯ /ase-meta-workflow optimizer run ase-code-analyze, then for each finding P<n> resolve, implement and delete it in a parallel isolated sub-agent
+```
+
+Generate a user-wide skill and overwrite a previous generation:
+
+```text
+❯ /ase-meta-workflow --scope user --force release lint the code, update the changelog, then propose a commit message
+```
+
+##  SEE ALSO
+
+[`ase-help-intent`](../ase-help-intent/help.md), [`ase-help-skill`](../ase-help-skill/help.md),
+[`ase-code-analyze`](../ase-code-analyze/help.md), [`ase-code-resolve`](../ase-code-resolve/help.md), [`ase-task-implement`](../ase-task-implement/help.md).

package/plugin/skills/ase-meta-workflow/sample.md

@@ -0,0 +1,70 @@
+---
+name: optimizer
+argument-hint: "[-i <id>] <context>"
+description: >
+    Resolve problems.
+user-invocable: true
+disable-model-invocation: false
+allowed-tools:
+    - "Bash(ase meta *)"
+---
+
+!`ase meta control skill getopt`
+
+<purpose name="optimizer">
+Analyze and Resolve Source Code Problems
+</purpose>
+
+<expand name="getopt"
+    arg1="optimizer"
+    arg2="--id|-i <id>=optimizer">
+    $ARGUMENTS
+</expand>
+
+<flow>
+
+1.  <step id="STEP 1: Analyze Code">
+
+    <agent description="Analyze Code"
+        subagent_type="general-purpose"
+        run_in_background=false>
+
+        Run <skill name="ase-code-analyze" args="--prefix <id/> <getopt-arguments/>"/>
+
+    </agent>
+
+    </step>
+
+2.  <step id="STEP 2: Resolve Code Problems">
+
+    <parallel>
+
+    For each `P<n/>` in the result set, in ascending order and strictly *one at a time*:
+
+    1.  Call the Agent:
+
+        <agent description="Reresolve P<n/>"
+            subagent_type="general-purpose"
+            isolation="worktree"
+            run_in_background=true>
+
+            1.  Run <skill name="ase:ase-code-resolve" args="-a <id/>-P<n/>"/>
+
+            2.  Run <skill name="ase:ase-task-implement" args="<id/>-P<n/>"/>
+
+            3.  Run <skill name="ase:ase-task-delete" args="<id/>-P<n/>"/>
+
+        </agent>
+
+    </parallel>
+
+    </step>
+
+3.  <step id="STEP 3: Result Consolidation">
+
+    <agent-consolidation/>
+
+    </step>
+
+</flow>
+

package/plugin/skills/ase-meta-workflow/workflow.txt

@@ -0,0 +1,97 @@
+START               -> ase-help-skill
+START               -> ase-meta-config
+START               -> ase-meta-why
+START               -> ase-meta-eli5
+START               -> ase-meta-evaluate
+START               -> ase-meta-diaboli
+START               -> ase-meta-steelman
+START               -> ase-meta-quorum
+START               -> ase-meta-chat
+START               -> ase-meta-search
+START               -> ase-meta-brainstorm
+START               -> ase-meta-compat
+START               -> ase-help-intent
+START               -> ase-arch-discover
+START               -> ase-code-insight
+START               -> ase-code-explain
+START               -> ase-code-lint
+START               -> ase-docs-distill
+START               -> ase-docs-proofread
+START               -> ase-meta-review
+START               -> ase-meta-diff
+START               -> ase-meta-changelog
+START               -> ase-meta-commit
+START               -> ase-meta-proximity
+START               -> ase-meta-workflow
+START               -> ase-code-dissect
+ase-help-skill      -> END
+ase-meta-config     -> END
+ase-meta-why        -> END
+ase-meta-eli5       -> END
+ase-meta-evaluate   -> END
+ase-meta-diaboli    -> END
+ase-meta-steelman   -> END
+ase-meta-quorum     -> END
+ase-meta-chat       -> END
+ase-meta-search     -> END
+ase-meta-brainstorm -> END
+ase-meta-compat     -> END
+ase-help-intent     -> END
+ase-arch-discover   -> END
+ase-code-insight    -> END
+ase-code-explain    -> END
+ase-code-lint       -> END
+ase-docs-distill    -> END
+ase-docs-proofread  -> END
+ase-meta-review     -> END
+ase-meta-diff       -> END
+ase-meta-changelog  -> END
+ase-meta-commit     -> END
+ase-meta-proximity  -> END
+ase-meta-workflow   -> END
+ase-code-dissect    -> END
+START               -> SKETCH
+START               -> TASK
+START               -> ase-sync-import
+START               -> ARTIFACT
+ARTIFACT            -> ase-arch-analyze
+ARTIFACT            -> ase-code-analyze
+ase-arch-analyze    -> SKETCH
+ase-code-analyze    -> SKETCH
+SKETCH              -> ase-code-craft
+SKETCH              -> ase-code-refactor
+SKETCH              -> ase-code-resolve
+ase-code-craft      -> APPROACHES
+ase-code-refactor   -> APPROACHES
+ase-code-resolve    -> APPROACHES
+APPROACHES          -> TASK
+TASK                -> ase-task-id
+ase-task-id         -> TASK
+TASK                -> ase-task-edit
+ase-task-edit       -> TASK
+TASK                -> ase-task-grill
+ase-task-grill      -> TASK
+TASK                -> ase-task-condense
+ase-task-condense   -> TASK
+TASK                -> ase-task-dissect
+ase-task-dissect    -> TASK
+TASK                -> ase-task-reboot
+ase-task-reboot     -> TASK
+TASK                -> ase-task-implement
+TASK                -> ase-task-preflight
+ase-task-preflight  -> TASK
+TASK                -> ase-task-view
+TASK                -> ase-task-list
+TASK                -> ase-task-rename
+TASK                -> ase-task-delete
+ase-task-implement  -> ARTIFACT
+ase-task-view       -> END
+ase-task-list       -> END
+ase-task-rename     -> END
+ase-task-delete     -> END
+ase-sync-import     -> ARTIFACT
+ARTIFACT            -> ase-sync-export
+ARTIFACT            -> ase-sync-reconcile
+ase-sync-reconcile  -> ARTIFACT
+TASK                -> END
+ARTIFACT            -> END

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

@@ -17,9 +17,9 @@ allowed-tools:
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
 
-<skill name="ase-sync-export">
+<purpose name="ase-sync-export">
 Export Artifact Set to Side-by-Side Files
-</skill>
+</purpose>
 
 <expand name="getopt"
     arg1="ase-sync-export"

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

@@ -16,9 +16,9 @@ effort: xhigh
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
 
-<skill name="ase-sync-import">
+<purpose name="ase-sync-import">
 Import Foreign Sources into Artifact Set
-</skill>
+</purpose>
 
 <expand name="getopt"
     arg1="ase-sync-import"

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

@@ -16,9 +16,9 @@ effort: xhigh
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
 
-<skill name="ase-sync-reconcile">
+<purpose name="ase-sync-reconcile">
 Reconcile Artifact Set to Artifact Set
-</skill>
+</purpose>
 
 <expand name="getopt"
     arg1="ase-sync-reconcile"

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

@@ -15,9 +15,9 @@ effort: high
 @${CLAUDE_SKILL_DIR}/../../meta/ase-dialog.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
 
-<skill name="ase-task-condense">
+<purpose name="ase-task-condense">
 Condense a Task Plan
-</skill>
+</purpose>
 
 <expand name="getopt"
     arg1="ase-task-condense"
@@ -142,17 +142,37 @@ Set <args></args> (set args to empty).
             -   *Drop* articles ("a", "an", "the") and *replace*
                 conjunctions with short separate clauses where this
                 shortens the text without introducing ambiguity.
-            -   *Re-wrap* the shortened free-text to the ~120-character-
-                per-line convention.
+            -   *Re-wrap* the shortened free-text to the ~100-character-
+                per-line convention of the plan <format/>, but *never*
+                break a line *inside* an inline code span.
             -   *Merge* genuinely-redundant bullets (the same aspect
                 restated) and *drop* pure duplication - but *only* when
                 truly redundant; *never* lose a distinct aspect.
 
-        3.  *Persona override*: this condense ruleset *always wins* for
+        3.  *Normalize the rendering artifacts*: the loaded
+            <task-content/> is the *rendering-prepared* variant of the
+            plan, whose artifacts *MUST NOT* be persisted back. Restore
+            the *authoring form* of the plan <format/> before saving:
+
+            -   A bullet point rendered as `◯   ` is written back as
+                `-   ` -- the condensed <task-content/> *MUST NOT*
+                contain a single `◯` marker.
+
+            -   An inline code span which the rendering split across two
+                physical lines into two spans (`` `<head/>` `` at a line
+                end and `` `<tail/>` `` at the next line start) is
+                written back as the *one* original span
+                `` `<head/> <tail/>` ``, and the line is then broken
+                *before* its opening backtick.
+
+            This normalization is *not* a semantic change and hence
+            *never* violates the preserve-exactly rule 1.
+
+        4.  *Persona override*: this condense ruleset *always wins* for
             the plan content. This ruleset-based compression is applied
             *regardless* of the currently active session persona style.
 
-        4.  *Hard guardrail - semantics preserved EXACTLY*: condensing
+        5.  *Hard guardrail - semantics preserved EXACTLY*: condensing
             *only* shortens wording. It *MUST NOT* drop, merge (except
             truly-redundant bullets per sub-item 2), reorder, or alter
             *any* factual claim, requirement, file path, rule, or

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

@@ -14,9 +14,9 @@ effort: high
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
 
-<skill name="ase-task-delete">
+<purpose name="ase-task-delete">
 Delete a Task Plan
-</skill>
+</purpose>
 
 <expand name="getopt" arg1="ase-task-delete">
     $ARGUMENTS