Skip to content

electronick1/LLAssemblyCLI / common_skill_parts

llassembly-agentic-workflow

Verified

Orchestrate 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/agent_generator_helpers/verification.md

View on GitHub
# Helper: verification

Helper for the `llassembly-generate-sub-agents` worker. Use it when the sub-agent being
defined decides whether the goal has actually been met — the sub-agent the control-flow
branches on to stop iterating. The rules that apply to every sub-agent live in
`references/workers/llassembly-generate-sub-agents.md` §5; this file adds only what is
specific to this role.

## When this role applies

The request implies a checkable outcome: code that must run, an endpoint that must
respond, a file that must contain something, a condition that must hold before the
workflow may exit.

## What the definition must specify

- Check the actual observable outcome implied by the goal (a file's contents, an endpoint
  responding, a value being correct) — not merely that an earlier step "ran".
- Be read-only: a verifier inspects and reports; it must not fix or mutate state.

## What to report

- A single decisive boolean the workflow exits on: `"true"` when every check passed,
  `"false"` otherwise. This is the value that lets the workflow take its exit branch, so it
  must always be set.
- A short reason on failure — a description of the first failing check — so a diagnosis
  sub-agent can act on it; on success, report what was checked instead.
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