@aiiware/aii 0.24.0 → 0.24.2
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.
- package/README.md +5 -2
- package/bin/aii +800 -793
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -305,6 +305,8 @@ aii persona status # check what's active
|
|
|
305
305
|
aii persona use --none # deactivate
|
|
306
306
|
```
|
|
307
307
|
|
|
308
|
+
Since v0.24.1, installing a persona shows what it will actually activate — soul, skills, hook commands, MCP servers, instructions and theme — and asks before writing anything. The counts describe what activation resolves, including surfaces the tree carries but `persona.json` never declares. In scripts, pass `--trust-source`.
|
|
309
|
+
|
|
308
310
|
**Official personas:** [github.com/aiiware/aii-personas](https://github.com/aiiware/aii-personas) — or create your own: a directory with a `persona.json` manifest and skill/soul files. In-session: `/persona use`, `/persona list`, `/persona status`.
|
|
309
311
|
|
|
310
312
|
### Theme System
|
|
@@ -329,7 +331,7 @@ Extensible instruction packages you can install and invoke:
|
|
|
329
331
|
/explain this function # Built-in: code explainer
|
|
330
332
|
```
|
|
331
333
|
|
|
332
|
-
Install accepts GitHub refs in any format — a bare `owner/repo` (Aii finds the skill, whether it's at the repo root or in a subdirectory, e.g. `aii skill install tt-a1i/archify`), explicit repo paths, blob URLs, and tree URLs. Every install pins the commit SHA, fetches binaries intact, and shows a trust preview (name, license, script payload) before anything is written — pass `--
|
|
334
|
+
Install accepts GitHub refs in any format — a bare `owner/repo` (Aii finds the skill, whether it's at the repo root or in a subdirectory, e.g. `aii skill install tt-a1i/archify`), explicit repo paths, blob URLs, and tree URLs. Every install pins the commit SHA, fetches binaries intact, and shows a trust preview (name, license, script payload) before anything is written. Since v0.24, `--yes` does **not** authorise installing third-party code — in scripts, pass `--trust-source` to confirm you trust the source. Create your own skills in `.aii/skills/<name>/SKILL.md` with YAML frontmatter. Skills in the cross-tool `~/.agents/skills/` directory are shown once before their first run, since other tools can write there.
|
|
333
335
|
|
|
334
336
|
### Project Instructions (AGENTS.md)
|
|
335
337
|
|
|
@@ -462,7 +464,8 @@ Run `aii help` for the full command list.
|
|
|
462
464
|
|------|-------------|
|
|
463
465
|
| `--model <name>` | Override model (e.g., `deepseek/deepseek-chat`) |
|
|
464
466
|
| `--auto` | Auto-approve all tool actions |
|
|
465
|
-
| `-y`, `--yes` | Auto-confirm prompts |
|
|
467
|
+
| `-y`, `--yes` | Auto-confirm shell prompts (does **not** authorise installs — see `--trust-source`) |
|
|
468
|
+
| `--trust-source` | Authorise installing third-party code (skills, plugins, personas) non-interactively |
|
|
466
469
|
| `-c`, `--continue-chat <id>` | Resume a specific session |
|
|
467
470
|
| `-n`, `--new-chat` | Force new session |
|
|
468
471
|
| `-i`, `--interactive` | Force interactive mode |
|