@lorekit/cli 1.63.1 → 1.63.2

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.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/skill/lorekit-setup/SKILL.md +4 -2
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@lorekit/cli",
3
- "version": "1.63.1",
3
+ "version": "1.63.2",
4
4
  "description": "Install the LoreKit shared-memory skill and run health checks for the LoreKit MCP server.",
5
5
  "license": "MIT",
6
6
  "repository": {
package/skill/lorekit-setup/SKILL.md CHANGED
@@ -4,8 +4,10 @@ description: >
4
4
  Sets up a self-improvement loop for a skill, workflow, or agent using LoreKit,
5
5
  so a host gets better across runs by reading its own accumulated lessons at
6
6
  the start of every run and hardening the proven ones into permanent rules.
7
- Designs the two tiers (a fast episodic tier of LoreKit lessons, advisory-only;
8
- a slow procedural tier that promotes a recurring lesson into a host rule),
7
+ Designs the lessons loop (a fast episodic tier of LoreKit lessons, advisory-only;
8
+ a slow procedural tier that promotes a recurring lesson into a host rule; and,
9
+ for the rarer judgement-free, independently-checkable case, a third rung that
10
+ compiles a recurring lesson into a mechanically-enforced CI invariant instead),
9
11
  chooses the lesson bucket (tag + key namespace) and scopes, and installs the
10
12
  entrenchment guards that stop a learning loop from reinforcing its own
11
13
  mistakes. Also covers the non-LLM case: giving a deterministic job (a GitHub