Fix install commands and clone URL in docs, bump to 4.0.2

README.md

@@ -10,7 +10,7 @@ https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement
 ## Repository Layout
 
 The publishable skill package is the [`self-improving-agent/`](self-improving-agent/)
-subfolder — that is what ClawdHub installs and what you copy into
+subfolder — that is what ClawHub installs and what you copy into
 `~/.openclaw/skills/`. Repo-level files (this README, `.github/` CI) stay
 outside the package on purpose.
 
@@ -19,14 +19,24 @@ outside the package on purpose.
 
 ## Installation
 
+With OpenClaw's built-in skill installer — this installs into the active
+OpenClaw workspace:
+
+```bash
+openclaw skills install @pskoett/self-improving-agent
+```
+
+Or with the ClawHub CLI (`npm i -g clawhub`). Note this installs into
+`./skills` under the current working directory, not the workspace:
+
 ```bash
-clawdhub install self-improving-agent
+clawhub install @pskoett/self-improving-agent
 ```
 
 Or manually — copy the skill subfolder (not the repo root):
 
 ```bash
-git clone https://github.com/peterskoett/self-improving-agent.git /tmp/self-improving-agent-repo
+git clone https://github.com/pskoett/self-improving-agent.git /tmp/self-improving-agent-repo
 cp -r /tmp/self-improving-agent-repo/self-improving-agent ~/.openclaw/skills/self-improving-agent
 ```
 

self-improving-agent/CHANGELOG.md

@@ -17,6 +17,27 @@ Read this before upgrading. General upgrade rules:
 
 ## [Unreleased]
 
+## [4.0.2] - 2026-08-06
+
+> 4.0.1 is skipped: that version number was already used by a build
+> published to ClawHub, so it is not reusable here.
+
+### Fixed
+
+- **Install commands and clone URL in the docs were wrong** (#24). The
+  advertised `clawdhub install` command does not exist. The documented
+  commands are now `openclaw skills install @pskoett/self-improving-agent`
+  (built-in, installs into the active workspace) and
+  `clawhub install @pskoett/self-improving-agent` (ClawHub CLI,
+  `npm i -g clawhub`, installs into `./skills` under the current working
+  directory). Both take the `@owner/slug` form — a bare slug is only
+  accepted for already-installed or unambiguous skills. Fixed in
+  `README.md`, `SKILL.md`, and `references/openclaw-integration.md`.
+- The manual `git clone` URL used the wrong owner handle
+  (`peterskoett` → `pskoett`). The old handle only resolved via a web
+  redirect, which `git clone` does not follow, so manual installs failed on
+  a fresh machine.
+
 ### Added
 
 - GitHub Actions CI (`.github/workflows/ci.yml` at the repo root): runs the
@@ -26,7 +47,7 @@ Read this before upgrading. General upgrade rules:
 
 ### Changed
 
-- **Repo restructured for ClawdHub publishing**: the skill package now lives
+- **Repo restructured for ClawHub publishing**: the skill package now lives
   in the repo's `self-improving-agent/` subfolder (SKILL.md, assets, hooks,
   references, scripts, this changelog), keeping repo-level files (README,
   `.github/`) out of the published skill. Install by copying the subfolder,
@@ -37,6 +58,11 @@ Read this before upgrading. General upgrade rules:
   existing hook installs and `openclaw hooks enable self-improvement` are
   unaffected.
 
+### Upgrade notes (4.0.x → 4.0.2)
+
+Documentation only — no skill behavior, hook, or `.learnings/` changes. No
+action needed beyond reinstalling if you want the corrected install docs.
+
 ## [4.0.0] - 2026-07-04
 
 ### Removed

self-improving-agent/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: self-improving-agent
 description: "Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks."
-version: "4.0.0"
+version: "4.0.2"
 metadata:
 ---
 
@@ -48,15 +48,22 @@ OpenClaw uses workspace-based prompt injection with automatic skill loading.
 
 ### Installation
 
-**Via ClawdHub (recommended):**
+**Via OpenClaw's built-in installer (recommended)** — installs into the
+active OpenClaw workspace:
 ```bash
-clawdhub install self-improving-agent
+openclaw skills install @pskoett/self-improving-agent
+```
+
+**Via the ClawHub CLI** (`npm i -g clawhub`) — installs into `./skills`
+under the current working directory, not the workspace:
+```bash
+clawhub install @pskoett/self-improving-agent
 ```
 
 **Manual** (the skill lives in the repo's `self-improving-agent/` subfolder;
 copy that folder, not the repo root):
 ```bash
-git clone https://github.com/peterskoett/self-improving-agent.git /tmp/self-improving-agent-repo
+git clone https://github.com/pskoett/self-improving-agent.git /tmp/self-improving-agent-repo
 cp -r /tmp/self-improving-agent-repo/self-improving-agent ~/.openclaw/skills/self-improving-agent
 ```
 

self-improving-agent/references/openclaw-integration.md

@@ -31,14 +31,21 @@ OpenClaw uses workspace-based prompt injection combined with event-driven hooks.
 ### 1. Install the Skill
 
 ```bash
-clawdhub install self-improving-agent
+openclaw skills install @pskoett/self-improving-agent
+```
+
+Or with the ClawHub CLI (`npm i -g clawhub`) — note this installs into
+`./skills` under the current working directory, not the workspace:
+
+```bash
+clawhub install @pskoett/self-improving-agent
 ```
 
 Or copy manually — the skill package is the `self-improving-agent/`
 subfolder of the repo, not the repo root:
 
 ```bash
-git clone https://github.com/peterskoett/self-improving-agent.git /tmp/self-improving-agent-repo
+git clone https://github.com/pskoett/self-improving-agent.git /tmp/self-improving-agent-repo
 cp -r /tmp/self-improving-agent-repo/self-improving-agent ~/.openclaw/skills/self-improving-agent
 ```