@duyquangnvx/create-agent-cli 0.20.0 → 0.22.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@duyquangnvx/create-agent-cli",
-  "version": "0.20.0",
+  "version": "0.22.0",
   "description": "Creates a new Agent CLI repository wired to @duyquangnvx/agent-cli.",
   "type": "module",
   "engines": {
@@ -21,7 +21,7 @@
     "access": "public"
   },
   "devDependencies": {
-    "@duyquangnvx/agent-cli": "0.20.0",
+    "@duyquangnvx/agent-cli": "0.22.0",
     "tsdown": "0.23.0",
     "zod": "4.6.7"
   },

package/partials/global/installSteps.md

@@ -1,6 +1,6 @@
 This installs the CLI. The user has installed this skill already.
 
-1. Run `node --version` and compare it with the range `npm view {{packageName}} engines.node` prints, which `doctor`'s `node` row also checks once the CLI is installed. Under nvm every Node version has its own global packages, so {{binName}} lands under the Node this shell runs. If that Node is too old, or is not the one the user's terminal runs, tell the user and let them choose before going on.
+1. Run `node --version` and compare it with the range `npm view {{packageName}} engines.node` prints, which `doctor`'s `node` row also checks once the CLI is installed. Under nvm every Node version has its own global packages, so {{binName}} lands under the Node this shell runs. If that Node is too old, or is not the one the user's terminal runs, tell the user and let them choose before going on. That is also why a {{binName}} the user installed can be missing from this shell: ask which Node their terminal runs before installing again.
 2. Hand the user the install line to type, as [Sandbox](#sandbox) says:
 
    `! npm install --global {{packageName}}@latest`

package/template/skills/{{binName}}/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   version: "0.0.0"
 ---
 
-<!-- A skeleton to rewrite around {{binName}}'s real Commands. Leave flags out: `--help` is generated from the code and stays in sync with it, this file does not. -->
+<!-- A skeleton to rewrite around {{binName}}'s real Commands. A line earns its place only when no `--help`, output, hint or `doctor` row tells the agent the same thing: write down what costs it turns to work out, such as a convention, a reason, a trap, or a step that needs the user's consent. Leave flags out: `--help` is generated from the code and stays in sync with it, this file does not. What {{binName}} is for, and the nearby tasks it is not for, go in the description, which the agent always sees. -->
 
 # {{binName}}
 
@@ -19,13 +19,6 @@ metadata:
 
 The line above should show 0.0.0, the version this skill describes. If it says {{binName}} is not installed or shows another version, read [setup](references/setup.md) before anything else.
 
-## When to use
-
-<!-- The tasks {{binName}} is for, and the nearby tasks it is not for. -->
-
-- Greeting someone by name.
-- Writing a greeting card to a file, in English for free or in another language at a cost.
-
 ## Workflows
 
 <!-- Each main task as steps naming the Commands it runs, in order. Move a long workflow to a file under references/ and link it. -->
@@ -43,11 +36,9 @@ The line above should show 0.0.0, the version this skill describes. If it says {
 
 To put a message under the greeting, pass `-` after the name and pipe the message in with a heredoc, so its quotes and newlines reach the card intact.
 
-Pass `--json` whenever you parse the output: stdout then holds only the data. A Command that changes something takes `--dry-run`, which prints its Plan, the files it writes and its cost, and changes nothing: run it first when unsure. A destructive Command also needs `--confirm=<target>`, and its error's Next step gives the exact command.
-
 ## Recovering from errors
 
-Errors go to stderr and end with a `hint:` line, then a `run:` line for each command to run next, in order. Under `--json`, every stderr line is one JSON object: `{"progress":"..."}` or `{"notice":"..."}` while it runs, then `{ errors: [{ code, message, hint, next }] }` as the last line, `next` holding those commands when there are any. Do what the hint says, except for a code below:
+Do what the error's hint says, except for a code below:
 
 | Code | What to do |
 |---|---|

package/template/skills/{{binName}}/references/setup.md

@@ -8,11 +8,9 @@ Work through a section in order and stop at a step that fails. Ask the user to d
 
 ## Check
 
-Run `{{runAs}} doctor --json`. It checks the setup without changing anything and prints `{ rows, next }`.
+Run `{{runAs}} doctor --json`, which changes nothing. Hand the user each line of its `next` to type with `!`, in order, then run `doctor` again.
 
-- Each row has a `check`, a `state` (`ok`, `problem` or `skipped`) and a `message` saying what it found. A row that has a `fix` names the command that fixes it.
-- `next` lists every fix in order. Hand the user each one to type with `!`, then run `doctor` again.
-- {{skillCheck}} If the session does not show it, ask the user to type `/reload-skills`, and failing that to restart Claude Code.
+{{skillCheck}} If the session does not show it, ask the user to type `/reload-skills`, and failing that to restart Claude Code.
 
 `{{runAs}} --version` names on its second line the `CHANGELOG.md` installed with the CLI. When the user asks what changed, read it from the top, newest first, down to the version in question.