@juicesharp/rpiv-args 1.1.3 → 1.1.5

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.
Files changed (2) hide show
  1. package/README.md +10 -10
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -11,7 +11,7 @@
11
11
  [![npm version](https://img.shields.io/npm/v/@juicesharp/rpiv-args.svg)](https://www.npmjs.com/package/@juicesharp/rpiv-args)
12
12
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
13
13
 
14
- Pass arguments to your skills like a shell command. `rpiv-args` adds `$1`, `$ARGUMENTS`, `$@`, `${@:N}`, and `${@:N:L}` placeholders to [Pi Agent](https://github.com/badlogic/pi-mono) skills write `/skill:deploy api production` and your skill body sees `$1` = `api`, `$2` = `production`. Skills without placeholders are untouched, so installing `rpiv-args` is safe for any existing skill collection.
14
+ Pass arguments to your skills like a shell command. `rpiv-args` adds `$1`, `$ARGUMENTS`, `$@`, `${@:N}`, and `${@:N:L}` placeholders to [Pi Agent](https://github.com/badlogic/pi-mono) skills - write `/skill:deploy api production` and your skill body sees `$1` = `api`, `$2` = `production`. Skills without placeholders are untouched, so installing `rpiv-args` is safe for any existing skill collection.
15
15
 
16
16
  ## Install
17
17
 
@@ -31,7 +31,7 @@ Or run `/rpiv-setup` if you have `@juicesharp/rpiv-pi` installed.
31
31
  | `${@:N}` | Arguments from position N onward | `/skill:foo a b c` → `${@:2}` = `b c` |
32
32
  | `${@:N:L}` | L arguments starting at position N | `/skill:foo a b c d` → `${@:2:2}` = `b c` |
33
33
 
34
- **Indexing is 1-based** `$1` is the first argument, `$2` is the second.
34
+ **Indexing is 1-based** - `$1` is the first argument, `$2` is the second.
35
35
  Out-of-range positions resolve to an empty string. For `${@:N[:L]}`, `N` is
36
36
  clamped to `≥ 1` and out-of-range slices yield an empty string.
37
37
 
@@ -51,14 +51,14 @@ expansion). When a skill body contains at least one placeholder, the extension:
51
51
  1. Parses arguments using shell-style quoting
52
52
  2. Substitutes all placeholders in the body
53
53
  3. Wraps the result in a `<skill>` block byte-identical to Pi's native format
54
- 4. Appends the raw arguments after the block matches Pi's standard output so any tool that parses `<skill>` blocks continues to work unchanged
54
+ 4. Appends the raw arguments after the block - matches Pi's standard output so any tool that parses `<skill>` blocks continues to work unchanged
55
55
 
56
56
  When no placeholders are found in the skill body, the output is byte-identical
57
- to Pi's built-in expansion zero behavioral change.
57
+ to Pi's built-in expansion - zero behavioral change.
58
58
 
59
59
  ## Writing skills with arguments
60
60
 
61
- ### `$ARGUMENTS` vs `$1` which to use
61
+ ### `$ARGUMENTS` vs `$1` - which to use
62
62
 
63
63
  Use **`$ARGUMENTS`** (or `$@`) when the input is freeform text the LLM should
64
64
  interpret naturally:
@@ -104,7 +104,7 @@ If a positional skill receives natural language input:
104
104
  /skill:migrate-component can you migrate the search bar please
105
105
  ```
106
106
 
107
- → `Migrate the can component from you to migrate.` **broken**.
107
+ → `Migrate the can component from you to migrate.` - **broken**.
108
108
 
109
109
  The LLM is good at interpreting `$ARGUMENTS` as a whole, but positional
110
110
  placeholders blindly split on spaces. Use `$ARGUMENTS` unless your skill has
@@ -130,17 +130,17 @@ argument-hint: [component] [from] [to]
130
130
  ---
131
131
  ```
132
132
 
133
- rpiv-args ignores this field substitution is triggered by placeholders in the body, not the hint.
133
+ rpiv-args ignores this field - substitution is triggered by placeholders in the body, not the hint.
134
134
 
135
135
  **Note**: Pi currently surfaces `argument-hint` in autocomplete for prompt
136
136
  templates (`commands/*.md`) but **not** for skills (`/skill:<name>`). The
137
137
  field is read by Pi but not displayed in the `/skill:` autocomplete UI at
138
- present treat it as documentation metadata until upstream Pi exposes it.
138
+ present - treat it as documentation metadata until upstream Pi exposes it.
139
139
 
140
140
  ### Full example
141
141
 
142
142
  <details>
143
- <summary>Deploy skill SKILL.md, invocation, and the exact text the LLM sees</summary>
143
+ <summary>Deploy skill - SKILL.md, invocation, and the exact text the LLM sees</summary>
144
144
 
145
145
  ```yaml
146
146
  ---
@@ -179,7 +179,7 @@ api production
179
179
  ```
180
180
 
181
181
  Note: the raw arguments (`api production`) are also appended after the
182
- `</skill>` block this is Pi's standard behavior and is preserved for
182
+ `</skill>` block - this is Pi's standard behavior and is preserved for
183
183
  backward compatibility.
184
184
 
185
185
  </details>
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@juicesharp/rpiv-args",
3
- "version": "1.1.3",
4
- "description": "Pi extension: pass shell-style $1 / $ARGUMENTS placeholders to your Pi skills",
3
+ "version": "1.1.5",
4
+ "description": "Pi extension. Shell-style $1 and $ARGUMENTS placeholders, expanded into your Pi skills at invocation.",
5
5
  "keywords": [
6
6
  "pi-package",
7
7
  "pi-extension",