Skip to content

rse/ase / plugin/skills/ase-meta-workflow

ase-meta-workflow

Verified

Generate a new agent tool skill, written in the style of ASE skills, which orchestrates a workflow of sequential actions, parallel actions, sub-agent calls, and skill calls. Use when the user wants to "generate a skill", create a "workflow", "orchestrate" or "chain" multiple ASE skills, or automate a recurring multi-step procedure.

FileKindSize
SKILL.mdskill md15.2 KB
help.mdmarkdown5.4 KB
sample.mdmarkdown1.4 KB
workflow.txtmarkdown3.7 KB
---
name: optimizer
argument-hint: "[-i <id>] <context>"
description: >
    Resolve problems.
user-invocable: true
disable-model-invocation: false
allowed-tools:
    - "Bash(ase util meta *)"
---

!`ase util meta control skill getopt`

<purpose name="optimizer">
Analyze and Resolve Source Code Problems
</purpose>

<expand name="getopt"
    arg1="optimizer"
    arg2="--id|-i=optimizer">
    $ARGUMENTS
</expand>

Set <id><getopt-option-id/></id>.

<flow>

1.  <step id="STEP 1: Analyze Code">

    <agent description="Analyze Code"
        subagent_type="general-purpose"
        run_in_background=false>

        Run <skill name="ase: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:

    1.  Call the Agent:

        <agent description="Resolve P<n/>"
            subagent_type="general-purpose"
            isolation="worktree"
            run_in_background=true>

            1.  Run <skill name="ase:ase-task-edit" args="--next DONE <id/>-P<n/>: <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>

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall