nextSuggest next actions after completing any task. Auto-invocation via Stop hook + UserPromptSubmit reactive backstop, owned by the `next-invocation-guard` plugin (local-only, ported from `resources/next-trigger.sh` + `resources/next-reactive-guard.sh`). Fires when assistant response contains completion keywords (locale patterns in `data/*.regex`). stall-detect - detect stalled follow-up steps and invoke /fix [stall-detect.md], ask-gates - recording-skip / decision-deferral forced-ask / TaskList primary-source / current-work confirmation gates [ask-gates.md], suggestion-patterns - per-context "After X" next-action option templates [suggestion-patterns.md]. Use when "next action", "what next", "stall", "stuck", "not progressing", "follow-up missing" is mentioned.
Install via ClawdBot CLI:
clawdbot install drumrobot/nextGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Sep 22, 2026
A software engineer runs an AI coding assistant in Claude Code or Antigravity. When a coding task finishes, the `next` skill auto-triggers via Stop hook and uses AskUserQuestion to propose relevant next actions such as running tests, opening a PR, or tackling stalled follow-up steps. The stall-detect topic file kicks in when /fix reveals pending work.
A platform team configures the `next` skill for their internal AI agent deployment so that after any completed task, the agent proactively offers cleanup, retrospective, or wrap-up options. The dependency-gated behaviors ensure cleanup suggestions only appear when a session-cleanup skill is actually present in the environment.
A support automation agent handles multi-turn troubleshooting. After resolving a ticket, `next` suggests follow-up options from per-context suggestion-patterns templates, detecting stalls when steps are skipped and invoking /fix to recover. Ask-gates enforce confirmation before deferring decisions or skipping recording.
A project manager's AI assistant uses fix_plan.md or checklist.md as the authoritative source of pending work. When those backing skills are available, the `next` skill mandatorily reads the tracker before composing next-action options, so suggestions reflect real outstanding items rather than generic advice.
An enterprise with strict data policies deploys the `next` skill's local-only Stop-hook and UserPromptSubmit reactive backstop, ported from shell resources, so no telemetry leaves the machine. Completion keywords from locale regex files trigger suggestions while analysis requests like `/next/fix analyze` are handled with a 5-Why report first.
Bundle the `next` skill as a value-add plugin for AI IDE environments like Claude Code and Antigravity. It reduces dead-end sessions by automatically proposing relevant follow-up actions, increasing session depth and developer retention.
Consultants integrate the skill into client agent pipelines, tuning stall-detect thresholds, ask-gates, and suggestion-patterns to match the client's workflow. The dependency-gated design prevents dead recommendations across heterogeneous environments.
Distribute the skill freely (author es6kr, v0.1.1) to drive adoption, then monetize through enterprise support for local-only deployments, custom regex locale patterns, and guaranteed compatibility with fix_plan/checklist trackers.
💬 Integration Tip
Always check the session's available-skills list before applying dependency-gated behaviors (session-cleanup, fix_plan/checklist) to avoid dead recommendations. In Antigravity environments, run Step 0-1's environment detection and context-usage gate before Step 0-0's audit to resolve the HARD STOP step-ordering conflict.
Scored Sep 22, 2026
Automate PCB design with KiCad. Create schematics, design boards, export Gerbers, order from PCBWay. Full design-to-manufacturing pipeline.
Full AI Chief Financial Officer — connects Mercury Banking + Stripe into real-time business intelligence. Daily cash position, automated P&L, revenue trackin...
Build and run automated QA bots to simulate user journeys, detect broken links, validate UI, run regressions, test responsiveness, and measure performance ac...
Operate an existing cron402 or agentcron.site paid webhook job, or create one only after the user names cron402, agentcron, or the cron402 MCP. Covers check_wallet, preview_schedule, create_cron, topup_cron, get_cron, list_crons, pause_cron, resume_cron, and delete_cron. Do not use for reminders, local timers, "run this later", "while I am away", or any schedule the user did not explicitly assign to cron402. Wallet secrets via abracadabra — never paste private keys in chat.
Webhook testing and debugging tool. Send test webhook payloads to any URL, simulate various webhook events (GitHub, Stripe, Slack), inspect responses, and lo...
Context-aware task scheduling with priority management