@xelth/eck-snapshot 4.3.1 → 4.3.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of @xelth/eck-snapshot might be problematic. Click here for more details.

Files changed (2) hide show
  1. package/README.md +30 -22
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -32,29 +32,9 @@ npm install -g @xelth/eck-snapshot
32
32
 
33
33
  Once installed, you can run the tool using the `eck-snapshot` command from any directory.
34
34
 
35
- ## Workflow Options
35
+ ## Getting Started: Full Snapshot Workflow
36
36
 
37
- ### Option 1: Skeleton Workflow (Recommended for Large Projects)
38
-
39
- The skeleton workflow is optimized for web-based LLMs (Gemini, ChatGPT) with large context windows. It uses a three-step approach:
40
-
41
- 1. **Initial Context (Maximum Compression):** Create a lightweight map of your entire project where function/method bodies are hidden, showing only signatures and structure.
42
- ```bash
43
- eck-snapshot --skeleton
44
- ```
45
- This generates `.eck/snapshots/<name>_sk.md` - a compressed overview that fits even large monoliths into the context window.
46
-
47
- 2. **Lazy Loading (On-Demand Details):** When the AI needs implementation details, use the `show` command to display specific files:
48
- ```bash
49
- eck-snapshot show src/auth.js src/utils/hash.js
50
- ```
51
- Copy-paste the output back to your AI chat.
52
-
53
- 3. **Incremental Updates:** See the dedicated section below for details on the `update` command.
54
-
55
- ### Option 2: Full Snapshot Workflow
56
-
57
- Here's the traditional workflow for creating complete snapshots and focusing on specific features.
37
+ This is the primary workflow for creating complete snapshots of your project.
58
38
 
59
39
  #### Step 1: Create a Full Project Snapshot
60
40
 
@@ -126,6 +106,34 @@ A faster, non-AI method to reduce snapshot size. This command keeps only the top
126
106
  > eck-snapshot --max-lines-per-file 200
127
107
  > ```
128
108
 
109
+ ## Skeleton Workflow (Advanced for Large Projects)
110
+
111
+ The skeleton workflow is optimized for web-based LLMs (Gemini, ChatGPT) with large context windows. It uses a three-step approach for maximum compression:
112
+
113
+ ### 1. Initial Context (Maximum Compression)
114
+
115
+ Create a lightweight map of your entire project where function/method bodies are hidden, showing only signatures and structure.
116
+
117
+ ```bash
118
+ eck-snapshot --skeleton
119
+ ```
120
+
121
+ This generates `.eck/snapshots/<name>_sk.md` - a compressed overview that fits even large monoliths into the context window.
122
+
123
+ ### 2. Lazy Loading (On-Demand Details)
124
+
125
+ When the AI needs implementation details, use the `show` command to display specific files:
126
+
127
+ ```bash
128
+ eck-snapshot show src/auth.js src/utils/hash.js
129
+ ```
130
+
131
+ Copy-paste the output back to your AI chat.
132
+
133
+ ### 3. Incremental Updates
134
+
135
+ After making changes, use the `update` command (see section below) to send only what changed.
136
+
129
137
  ## Incremental Updates: The `update` Command
130
138
 
131
139
  The `update` command is a powerful feature that creates **delta snapshots** containing only the files that changed since your last full snapshot. This is essential for maintaining AI context efficiently during active development.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@xelth/eck-snapshot",
3
- "version": "4.3.1",
3
+ "version": "4.3.2",
4
4
  "description": "A powerful CLI tool to create and restore single-file text snapshots of Git repositories and directories. Optimized for AI context and LLM workflows.",
5
5
  "main": "index.js",
6
6
  "type": "module",