Workflow-Scripts

Safely commit and push intended changes from a mixed or dirty worktree. Use when the user asks to push updates, commit current work, publish a fix, or handle git status with unrelated local changes, nested repositories, ignored generated files, or possible index.lock issues.

Execute an approved implementation plan end to end. Use when the user says Implement the plan, points to an execute-and-confirm workflow, asks to complete a named plan, or expects code changes plus verification, changelog/troubleshooting/docs updates, and accurate plan archival or status updates.

Triage saved runtime artifacts before editing code. Use when the user asks to inspect project/execution, project/errors, console.md, terminal.md, output.md, saved logs, warning output, large log-like files, or asks whether a warning/error needs a fix.

Debug and verify exported/rendered output parity across app view, HTML, Markdown, PDF, ZIP, and preview surfaces. Use when thumbnails, image links, rendered PDF, full export ZIPs, markdown previews, blog exports, or generated document styling differ from the app view or fail during export.

Launch or restart a local chat bot and verify real webhook health, auth, tunnel routing, and inbound/outbound delivery. Use when the user says launch my chatbot, restart after changes, verify health, run a real WhatsApp/Kapso/ngrok test, check what model/auth path is in use, or ensure home-env credentials are loaded.

Orchestrate multiple independent agents or model passes to produce a stronger implementation plan. Use when the user asks to launch multiple agents/models, use opencode in single-line mode, run independent parallel research/proposals, add an adversarial critique stage, or synthesize a coding-agent-ready handoff plan.

Verify current AI provider model names, capabilities, API contracts, and routing claims against live provider catalogs, official docs, or the current adapter code. Use when the user asks for a complete accurate provider/model list, whether a provider supports a capability, whether a model name is correct, or whether docs/plans/constants match current provider reality.

Trace a user-facing AI generation setting or provider behavior end to end through UI, state, request schemas, API routes, factories, adapters, and tests. Use when the user says a control must work for all providers, asks to pass parameters to API calls, reports provider selection being ignored, or needs direct vs research generation routes compared.

Synchronize repository changelog, troubleshooting, docs, and indexes after changes. Use after code changes, bug fixes, non-trivial debugging, policy/config updates, completed plans, docs requests, or when the user says update the logs, update docs, file a technical note, or keep changelog/troubleshooting in sync.

Review and harden public webhook or chat-bot systems before launch. Use when the user says a bot is going public, asks to lock things down, mentions denial of service, prompt injection, rapid-fire input, file attachments, NSFW/out-of-scope content, failure recovery, retry queues, dead letters, or operator controls.

Follow a repo bug-fix workflow from saved evidence to plan, implementation, verification, and logs. Use when the user names a bug-fix workflow, asks to inspect project/execution or project/errors first, says study this report then implement the plan, reports a persistent regression, asks to update both logs, or asks to file a completed bug plan.

Review, correct, and finalize repository implementation plans. Use when the user asks to use plan-review/finalise-plan/research-and-plan workflows, verify a plan against the live codebase, decide whether a plan is still relevant, append findings to a plan, create or update a dated active plan under project/plans, or update plan trackers.

Run or consume a workflow-driven code review and turn verified findings into a filed remediation plan. Use when the user asks for a code review report in project/research, asks to convert a review into a detailed implementation plan, or wants verified review findings prioritized before implementation.

Audit prompt systems for enforceable product and UI quality. Use when the user asks for a deep prompt review, prompt quality audit, UI-generation prompt hardening, or review of prompts for layering, shadows, glow, animation, app chrome, accessibility, responsive behavior, state coverage, or consistency across prompt files.