@caliber-ai/cli 0.4.1 → 0.5.0
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.
- package/README.md +14 -2
- package/dist/bin.js +410 -55
- package/dist/bin.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -17,7 +17,8 @@ caliber login
|
|
|
17
17
|
# Initialize your project
|
|
18
18
|
caliber init
|
|
19
19
|
|
|
20
|
-
#
|
|
20
|
+
# Check what's configured
|
|
21
|
+
caliber status
|
|
21
22
|
```
|
|
22
23
|
|
|
23
24
|
## Commands
|
|
@@ -28,6 +29,10 @@ caliber init
|
|
|
28
29
|
| `caliber update` | Re-analyze project and update setup | `--dry-run` |
|
|
29
30
|
| `caliber status` | Show current Caliber setup status | `--json` |
|
|
30
31
|
| `caliber undo` | Revert all config changes made by Caliber | |
|
|
32
|
+
| `caliber recommend` | Discover and manage skill recommendations | `--generate`, `--status <pending\|accepted\|dismissed>` |
|
|
33
|
+
| `caliber health` | Analyze context health and quality | `--fix`, `--json` |
|
|
34
|
+
| `caliber sync` | Sync local config with server state | `--platform <claude\|cursor\|both>`, `--dry-run` |
|
|
35
|
+
| `caliber diff` | Compare local config with server state | `--platform <claude\|cursor\|both>` |
|
|
31
36
|
| `caliber login` | Authenticate with Caliber | |
|
|
32
37
|
| `caliber logout` | Clear stored credentials | |
|
|
33
38
|
|
|
@@ -36,7 +41,14 @@ caliber init
|
|
|
36
41
|
1. **Login** — Authenticate with your Caliber account via the browser.
|
|
37
42
|
2. **Init** — Caliber analyzes your project structure, dependencies, and patterns, then generates tailored configuration files (e.g., `CLAUDE.md`, `.cursorrules`) for your chosen coding agent.
|
|
38
43
|
3. **Update** — Re-run the analysis when your project changes to keep agent configs up to date.
|
|
39
|
-
4. **
|
|
44
|
+
4. **Recommend** — Discover relevant skills from [skills.sh](https://skills.sh) based on your project's tech stack, scored by an LLM for relevance.
|
|
45
|
+
5. **Health** — Analyze the quality of your agent context configuration and get a score (A-F) with actionable recommendations. Use `--fix` to auto-remediate issues.
|
|
46
|
+
6. **Sync / Diff** — Compare your local agent config against the server state and sync missing or outdated items across platforms.
|
|
47
|
+
7. **Undo** — Cleanly revert all changes if you want to start fresh.
|
|
48
|
+
|
|
49
|
+
## CI/CD
|
|
50
|
+
|
|
51
|
+
Pushes to `main` automatically publish to npm with semantic versioning based on conventional commits. A Sentry release is created for each version.
|
|
40
52
|
|
|
41
53
|
## Requirements
|
|
42
54
|
|