freeze
Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally fixing unrelated code, or when scoping changes to one module. Use when: "freeze", "restrict edits", "only edit this folder", "lock down edits".
Best use case
freeze is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally fixing unrelated code, or when scoping changes to one module. Use when: "freeze", "restrict edits", "only edit this folder", "lock down edits".
Teams using freeze should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/freeze/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How freeze Compares
| Feature / Agent | freeze | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally fixing unrelated code, or when scoping changes to one module. Use when: "freeze", "restrict edits", "only edit this folder", "lock down edits".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
# Freeze — Restrict Edits to a Directory
Lock edits to a specific directory. Everything outside is read-only.
## How to Use
1. **Ask the user** which directory to lock to (or detect from context — e.g., the directory containing the bug).
2. **Announce:** "Edits restricted to `{dir}/`. Everything else is read-only. Say 'unfreeze' to remove."
3. **Enforce:** Before any Edit or Write, check that the target file is within the locked directory. If not, refuse and remind the user.
## Detection
After activating freeze, note the locked directory in your context. Every edit command should be checked:
- Target file starts with locked dir → proceed
- Target file is outside → "This file is outside the frozen scope (`{locked_dir}/`). Say 'unfreeze' to edit elsewhere."
## Auto-detect for Debugging
When invoked during debugging, auto-lock to the directory containing the affected files:
- If investigating `src/auth/login.ts` → freeze to `src/auth/`
- If the bug spans multiple directories → ask which one to lock
- If genuinely cross-cutting → skip the lock, note whyRelated Skills
unfreeze
Clear the freeze boundary set by freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when: "unfreeze", "unlock edits", "remove freeze", "allow all edits".
freezer-sample-locator
Track and retrieve sample locations in -80°C freezers with hierarchical storage organization. Trigger conditions: - User needs to record sample storage positions (freezer ID, level, rack, box, grid position) - User requests to search samples by name, project, date, or location - User requires sample inventory management and export functionality Input: Sample metadata (name, project, quantity) and storage coordinates Output: Structured sample location records with search and export capabilities Success criteria: - Accurate position recording without conflicts - Fast search and retrieval (<1 second for 1000+ samples) - Data integrity maintained across operations - Export in multiple formats (JSON, CSV) Risk level: MEDIUM (Script execution with file system access) Technical difficulty: INTERMEDIATE Version: v1.0 Owner: 研发部 Last updated: 2026-02-06
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.