← Back to Skills Marketplace
drumrobot

next

by es6kr · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
81
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install next
Description
Suggest next actions after completing any task. Use automatically when a task is finished to recommend 2-3 logical follow-up actions the user might want to t...
Usage Guidance
This skill is a plausible 'next action' suggester, but its instructions require reading repository/PR/CI state and can invoke a /fix skill that executes missing steps. Before installing or enabling it: 1) Ask the author for the /fix skill's code and for explicit details about required credentials (GitHub tokens, CI tokens, git/cli access). 2) Ensure the skill will ask for explicit confirmation before performing destructive actions (push, run scripts, create PRs). 3) Limit tokens/permissions to least privilege and prefer read-only tokens for suggestion/detection. 4) Test in a safe repository or sandbox first. 5) If you cannot review the /fix skill, treat this as higher-risk and avoid granting broad repo/CI credentials.
Capability Analysis
Type: OpenClaw Skill Name: next Version: 0.1.0 The 'next' skill bundle is a workflow helper designed to suggest logical follow-up actions (e.g., testing, committing, documenting) after a task is completed. It includes a 'stall-detect' mechanism (stall-detect.md) that monitors for incomplete sub-steps and invokes a 'fix' skill if a workflow appears stuck. The logic is transparent, aligns with standard development practices, and contains no evidence of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description match a lightweight suggester, but the instructions require the agent to detect stalled workflows, inspect files (workflow.md, fix_plan.md), check PR/issue bodies and CI status, and then invoke /fix to execute missing steps. Those actions typically require repository access, CI API tokens, and the ability to run commands (git, CI CLI). The skill declares no required env vars, binaries, or config paths — a mismatch between claimed scope and the capabilities it expects to use.
Instruction Scope
SKILL.md instructs the agent to run a mandatory 'stall-detect' routine that checks project files, PR/issue checklists, workflow rules, and user responses, and to invoke the /fix skill when any stall is found. It also directs the agent to "Execute selected action" immediately. The instructions allow reading project artifacts and performing potentially destructive actions (git push, run scripts, create PRs) without clearly documented confirmation/limits.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install mechanism. There are no downloads or installs performed by the skill itself.
Credentials
The skill will need access to repository data, PR bodies, and CI status to implement its stall-detection and automatic fixes, which usually requires GitHub/Git/CI credentials and CLIs. But it declares no required environment variables or config paths. This omission is a proportionality mismatch — the skill asks for capabilities (read/change repo state, call /fix) without declaring the credentials or access it will need.
Persistence & Privilege
The skill is not always-enabled and is user-invocable (defaults). It will autonomously invoke the /fix skill when a stall is detected, and it instructs the agent to execute user-selected actions immediately. Autonomous invocation alone is normal, but combined with the other concerns (repo/CI access, automatic fixes) it increases the potential impact if the /fix skill or the agent has broad permissions.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install next
  3. After installation, invoke the skill by name or use /next
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release: next action suggester with stall detection
Metadata
Slug next
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is next?

Suggest next actions after completing any task. Use automatically when a task is finished to recommend 2-3 logical follow-up actions the user might want to t... It is an AI Agent Skill for Claude Code / OpenClaw, with 81 downloads so far.

How do I install next?

Run "/install next" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is next free?

Yes, next is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does next support?

next is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created next?

It is built and maintained by es6kr (@drumrobot); the current version is v0.1.0.

💬 Comments