@codegiveness/kernel-prompt 0.4.1 → 0.4.2

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/CHANGELOG.md CHANGED
@@ -1,5 +1,13 @@
1
1
  # Kernel Prompt
2
2
 
3
+ ## [0.4.2] - 2026-10-10
4
+
5
+ ### Changed
6
+
7
+ - Add a README badge row: CI status, npm version, npm monthly downloads, license, and Agent Skills compatibility.
8
+ - Replace the generic npm keywords `agent`, `skill`, and `kernel` with the repository topics (`agent-skills`, `agent-skill`, `skill-md`, `prompt-engineering`, `prompt-optimization`, `prompt-generator`, `meta-prompting`, `system-prompt`, `prompts`, `llm`, `ai-agents`), keeping `prompt`.
9
+ - Record GitHub access, the `main` branch ruleset, presentation metadata, and listing status for agents in `AGENTS.md`, and version the repository's social preview image at `.github/social-preview.png`.
10
+
3
11
  ## [0.4.1] - 2026-10-10
4
12
 
5
13
  ### Changed
package/README.md CHANGED
@@ -1,5 +1,7 @@
1
1
  # Kernel Prompt
2
2
 
3
+ [![CI](https://github.com/codegiveness/kernel-prompt/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/codegiveness/kernel-prompt/actions/workflows/ci.yml) [![npm](https://img.shields.io/npm/v/@codegiveness/kernel-prompt?logo=npm)](https://www.npmjs.com/package/@codegiveness/kernel-prompt) [![npm downloads](https://img.shields.io/npm/dm/@codegiveness/kernel-prompt?logo=npm)](https://www.npmjs.com/package/@codegiveness/kernel-prompt) [![License](https://img.shields.io/github/license/codegiveness/kernel-prompt)](LICENSE) [![Agent Skills: compatible](https://img.shields.io/badge/Agent%20Skills-compatible-6f42c1)](https://agentskills.io/specification)
4
+
3
5
  `kernel-prompt` is a small, harness-neutral prose skill that turns your message—a draft prompt or a task you want an AI agent to do—into an improved prompt for that agent. It asks one round of questions first, then writes the prompt while preserving your intent. It writes the instruction, never the task's result.
4
6
 
5
7
  Select it when you invoke it by name or ask to compose or improve an LLM prompt or an instruction for another AI. Reviewing documents or collaboration guidance—even with wording suggestions—is not by itself a match. Asking to turn that guidance into a system prompt is.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@codegiveness/kernel-prompt",
3
- "version": "0.4.1",
3
+ "version": "0.4.2",
4
4
  "description": "Agent skill that turns rough requests and drafts into clear prompts for other agents, asking only the decisions that change the result.",
5
5
  "license": "MIT",
6
6
  "author": "codegiveness",
@@ -13,12 +13,18 @@
13
13
  "url": "https://github.com/codegiveness/kernel-prompt/issues"
14
14
  },
15
15
  "keywords": [
16
+ "agent-skills",
17
+ "agent-skill",
18
+ "skill-md",
16
19
  "prompt-engineering",
20
+ "prompt-optimization",
21
+ "prompt-generator",
22
+ "meta-prompting",
23
+ "system-prompt",
17
24
  "prompt",
18
- "skill",
19
- "agent-skills",
20
- "agent",
21
- "kernel"
25
+ "prompts",
26
+ "llm",
27
+ "ai-agents"
22
28
  ],
23
29
  "publishConfig": {
24
30
  "access": "public",