Long-horizon agent skill for Claude Code / Cursor / Codex / Grok — multi-task ledger loop (related or not), host-portable (re-send the prompt to continue), clean-context supervisor, verified gates. Markdown library (loop-graph · quest), not a framework.
Skills
Skills is an open-source workflow skill for Claude Code and Codex, published by dream-num. Its author describes it as: “Univer Skill enables AI tools to work directly with spreadsheets, Excel workbooks, and CSV files. Powered by Univer CLI, it brings Git-style diffs, reviews, approvals, and rollbacks to spreadsheet workflows — making h…”. The project has 56 stars on GitHub and is available under the Apache-2.0 license. Add it to your setup with `git clone https://github.com/dream-num/skills ~/.claude/skills/skills`.
Installation
Add Skills to your agent with:
git clone https://github.com/dream-num/skills ~/.claude/skills/skillsAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
When to use it
Reach for Skills when you want workflow help from Claude Code without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear Apache-2.0 license — safe to read and adapt
- Declares compatibility with Claude Code, Codex
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does Skills do?
- Univer Skill enables AI tools to work directly with spreadsheets, Excel workbooks, and CSV files. Powered by Univer CLI, it brings Git-style diffs, reviews, approvals, and rollbacks to spreadsheet workflows — making human-AI collaboration structured, reviewable, and safe.
- How do I install Skills?
- Run git clone https://github.com/dream-num/skills ~/.claude/skills/skills in your agent, then reload your skills. Review the source at https://github.com/dream-num/skills before installing.
- Is Skills free to use?
- Yes. Skills is free and open source under the Apache-2.0 license, so you can read, run, and adapt it within that license's terms.
- Which agents does Skills work with?
- Skills declares compatibility with Claude Code and Codex. Agent Skills use a portable SKILL.md format, so other compatible clients can usually load it too.
Related skills
More Workflow →
Local control plane for governed AutoResearch in real repos: human-approved scope, live experiment tracking, evidence-backed results, and project memory for Claude Code and Codex.
Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.