Skip to content

chatfuel-lab/wizard / content/modules/flow-builder/skill

FileKindSize
SKILL.mdskill md2.7 KB
examples/operations.graphqlother78.9 KB
playbooks/customize.mdmarkdown1.5 KB
playbooks/embed.mdmarkdown824 B
references/guide.mdmarkdown19.2 KB
references/test-panel.mdmarkdown8.1 KB

playbooks/customize.md

View on GitHub
# Customizing this module

Shared ground rules (tokens, design system, adding operations) live in
`../chatfuel-core/playbooks/customize.md`. Module-specific ideas:

- Element editors are one file per family under `components/editors/` — restyle or trim freely; the never-crash fallback (`GenericElementView`) must stay.
- Auto-layout (`lib/layout.ts`) is pure BFS — swap in dagre/elkjs if you want prettier layouts.
- Creating a flow is two writes, not one: `createFlow` takes no name and answers with the Bot rather than the flow, so `hooks/useFlowsList.ts` works out which id is new by diffing the list it just got back (`lib/flowList.ts`) and then sends `updateFlowName`. A rename that fails leaves the flow — it is opened anyway, because losing a flow that is already on the server would be worse than an unnamed one.
- Rename and delete are on the rail row's own menu, and both go through `lib/flowList.ts` (`patchName`, `dropFlow`) so a flow inside a group is reached as surely as one in the flat lists. `deleteFlow` answers with ids only — not enough to rebuild the rail from, which is why the local state drops the id rather than adopting the response.
- The group CRUD (`createFlowGroup`, `updateFlowGroupName`, `deleteFlowGroup`, `moveFlowToGroup`, `removeFlowFromGroup`) and both sort mutations are generated in `examples/operations.graphql` and have no control yet — the rail is the place to put one.
- Read-only by API design: widget entry point, the switch-to-human elements (one per platform), WA template content beyond params, AI token counters.
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: 472kUpdated 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