electronick1/LLAssemblyCLI / common_skill_parts
llassembly-agentic-workflow
VerifiedOrchestrate agentic workflow to satisfy user request and goal. In the current session you run scripts/get_next_instruction.py and precisely follow the instructions in its output (stdout). Use for any multi-step task that benefits from planned, branching, verifiable orchestration.
references/prebuilt-skill.md
View on GitHub---
name: @@SKILL_NAME@@
description: Companion skill for llassembly-agentic-workflow. A compiled control-flow plan with pre-generated agents, executed by the llassembly-agentic-workflow skill. Use when directly asked for this skill.
---
# @@SKILL_NAME@@
Prebuilt llassembly workflow. The control-flow plan (`references/plan_llassembly.<ext>`)
and its sub-agents (`references/agents/`) are already generated. This skill is executed by
the **llassembly-agentic-workflow** skill's driver — it does not run on its own.
`references/agents/` holds the sub-agent definitions. `--init` copies them into the workflow
directory, and the driver prints each one's path beside its name when it is time to run it.
## How to run
Switch to llassembly-agentic-workflow skill, drive the workflow in the current session
with this skill's path:
python scripts/get_next_instruction.py --init "<path_to_this_skill>"
where `<path_to_this_skill>` is a folder path where @@SKILL_NAME@@ is located, then follow
the instructions it prints until it prints `Execution finished. Goal is achieved.`. Follow
the printed instructions literally, and re-run the llassembly-agentic-workflow
`scripts/get_next_instruction.py` driver. Never decide the next step yourself — the driver
decides. In case of failure or misbehaviour always re-run the driver. Always do exactly
what the latest execution printed, then re-run the driver. Stages can repeat, branch, or
arrive in a different order.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |