Hot-reload Julia code changes using Revise.jl without restarting the session
Scanned 5/28/2026
Install via CLI
openskills install samtalki/AgentREPL.jl---
name: julia-revise
description: Hot-reload Julia code changes using Revise.jl without restarting the session
argument-hint: "[track <path>]"
allowed-tools:
- mcp__plugin_julia_julia-repl__revise
- mcp__plugin_julia_julia-repl__eval
- mcp__plugin_julia_julia-repl__pkg
---
# Julia Revise (Hot-Reload)
Hot-reload Julia code changes using Revise.jl — the key to maximizing REPL session lifespan.
## Arguments
- No argument: triggers `revise(action="revise")` to pick up all file changes
- `track <path>`: starts tracking a file with Revise
- `includet <path>`: includes a file with Revise tracking
- `status`: shows what Revise is tracking
## Instructions
1. Parse the user's argument to determine the action and optional path
2. Call `revise` with the appropriate action and path parameters
3. If Revise is not available, offer to install it:
- `pkg(action="add", packages="Revise")`
- Then `reset` to reload (Revise loads automatically on worker startup)
## Revise Workflow
Revise.jl enables iterative development without losing session state:
1. **Edit Julia source files** (using Claude's Edit/Write tools)
2. **Call `revise(action="revise")`** to pick up changes
3. **Continue working** — all variables, data, and packages are preserved
This eliminates the most common reason for using `reset`.
## When to Use Revise vs Reset
| Situation | Use Revise | Use Reset |
|-----------|-----------|-----------|
| Changed function body | Yes | No |
| Added new function | Yes | No |
| Modified method signature | Yes | No |
| Changed struct **layout** (Julia < 1.12) | No | Yes |
| Corrupted session state | No | Yes |
| Want clean slate | No | Yes |
| Changed const value | Sometimes | If needed |
## Tips
- Revise.jl is auto-loaded on worker startup if installed in the environment
- After `pkg(action="develop", packages="./MyPkg")`, Revise automatically tracks the package source
- Use `includet("file.jl")` (via eval) instead of `include("file.jl")` for standalone scripts — it enables hot-reloading
- Call `revise(action="status")` to see what files and packages Revise is watching
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...