@drunkcoding/agents-and-skills 0.0.27 → 0.0.28

package/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "tech-graph",
       "source": "./plugins/tech-graph",
       "description": "6-step wizard for technical diagrams (SVG/PNG) via fireworks-tech-graph",
-      "version": "0.0.27",
+      "version": "0.0.28",
       "category": "diagram",
       "keywords": [
         "diagram",
@@ -26,7 +26,7 @@
       "name": "html-effectiveness",
       "source": "./plugins/html-effectiveness",
       "description": "Generate self-contained interactive HTML reports from 20 upstream templates via a conversational agent.",
-      "version": "0.0.27",
+      "version": "0.0.28",
       "category": "reports",
       "keywords": [
         "html",
@@ -41,7 +41,7 @@
       "name": "plugin-validator",
       "source": "./plugins/plugin-validator",
       "description": "Orchestrated validator for Claude Code plugins — validates skills, agents, commands, and hooks across every plugin under plugins/**.",
-      "version": "0.0.27",
+      "version": "0.0.28",
       "category": "tooling",
       "keywords": [
         "validation",
@@ -57,7 +57,7 @@
       "name": "team-share",
       "source": "./plugins/team-share",
       "description": "Share Claude plugin settings with a team, scaffold CLAUDE.md when needed, refresh the Understand-Anything graph, and stage the onboarding artifacts for review.",
-      "version": "0.0.27",
+      "version": "0.0.28",
       "category": "tooling",
       "keywords": [
         "onboarding",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@drunkcoding/agents-and-skills",
-  "version": "0.0.27",
+  "version": "0.0.28",
   "description": "Personal collection of Claude Code skills and agents, installable via `npx skills`.",
   "keywords": [
     "claude-code",

package/plugins/html-effectiveness/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "html-effectiveness",
   "displayName": "HTML Effectiveness Reports",
-  "version": "0.0.27",
+  "version": "0.0.28",
   "description": "Generate self-contained interactive HTML reports from 20 upstream templates via a conversational agent.",
   "author": {
     "name": "Steven Hoang"

package/plugins/plugin-validator/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "plugin-validator",
   "displayName": "Plugin Validator",
-  "version": "0.0.27",
+  "version": "0.0.28",
   "description": "Orchestrated validator for Claude Code plugins — validates skills, agents, commands, and hooks across every plugin under plugins/**.",
   "author": {
     "name": "Steven Hoang"

package/plugins/team-share/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "team-share",
   "displayName": "Team Share",
-  "version": "0.0.27",
+  "version": "0.0.28",
   "description": "Share Claude plugin settings with a team, scaffold CLAUDE.md when needed, refresh the Understand-Anything graph, and stage the onboarding artifacts for review.",
   "author": {
     "name": "Steven Hoang"

package/plugins/team-share/agents/team-share.md

@@ -1,6 +1,6 @@
 ---
 name: team-share
-description: Share Claude plugin settings with the team, build or refresh the Understand-Anything knowledge graph with auto-update, and git-lfs track it before staging everything for review.
+description: Share Claude plugin settings with the team, build or refresh the Understand-Anything knowledge graph, initialize the docs wiki, and git-lfs track it before staging everything for review.
 argument-hint: "[--force] [--language <lang>] (passed through to /understand)"
 allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Skill
 ---
@@ -11,7 +11,8 @@ Make this repo onboarding-ready for the team in one pass:
 
 1. Generate a **shareable `.claude/settings.json`** (plugins + marketplaces) from the maintainer's live setup.
 2. Build/refresh the **Understand-Anything knowledge graph** with auto-update enabled.
-3. **git-lfs track** the graph and **stage** everything — leaving the commit to a human.
+3. Initialize the **docs wiki** for Understand-Anything under `docs/wiki`.
+4. **git-lfs track** the graph and **stage** everything — leaving the commit to a human.
 
 This command is **idempotent** — safe to re-run. It **never commits or pushes**; it only stages.
 `$ARGUMENTS` (e.g. `--force`, `--language zh`) is forwarded to `/understand`.
@@ -40,7 +41,7 @@ Goal: teammates who clone the repo get the **same plugins + marketplaces** the m
 
 ### 1a — Merge plugin + marketplace settings
 
-Copy **only** `enabledPlugins` and `extraKnownMarketplaces` from the maintainer's user settings into the repo settings. Do **NOT** copy `hooks`, `permissions`, `env`, or any key holding absolute paths or local tooling (those are per-machine and may expose private paths).
+Copy **only** `enabledPlugins` and `extraKnownMarketplaces` from the maintainer's user settings into the repo settings. Do **NOT** copy `hooks`, `permissions`, `env`, or any key holding absolute paths or machine-local secrets.
 
 ```bash
 USER_SETTINGS="$HOME/.claude/settings.json"
@@ -70,7 +71,7 @@ Notes:
 
 ### 1b — Scaffold `CLAUDE.md` if missing
 
-The `claude-code-setup` plugin (from the `claude-plugins-official` marketplace) generates a project-savvy `CLAUDE.md` when one does not yet exist. Running the install command is **idempotent** — if `CLAUDE.md` is already present it will **not** be overwritten.
+The `claude-code-setup` plugin (from the `claude-plugins-official` marketplace) generates a project-savvy `CLAUDE.md` when one does not yet exist. Running the install command is **idempotent** — if the file already exists, this step is skipped.
 
 ```bash
 # Only create CLAUDE.md when it does not already exist.
@@ -104,7 +105,7 @@ else
 
 ## Code research with Understand-Anything
 
-This project uses the [Understand-Anything](https://github.com/Egonex-AI/Understand-Anything) plugin to maintain an interactive knowledge graph of the codebase. **Always prefer these commands over raw grep/glob when researching code structure, relationships, or logic:**
+This project uses the [Understand-Anything](https://github.com/Egonex-AI/Understand-Anything) plugin to maintain an interactive knowledge graph of the codebase. **Always prefer these commands over raw file-by-file exploration when doing code research:**
 
 | Goal | Command |
 |------|---------|
@@ -115,8 +116,9 @@ This project uses the [Understand-Anything](https://github.com/Egonex-AI/Underst
 | Open the interactive visual dashboard | `/understand-dashboard` |
 | Extract business-domain knowledge (domains, flows, steps) | `/understand-domain` |
 | Generate an onboarding guide for new teammates | `/understand-onboard` |
+| Generate or refresh wiki knowledge under `docs/wiki` | `/understand-knowledge docs/wiki` |
 
-The knowledge graph lives in `.understand-anything/knowledge-graph.json` and is kept up-to-date automatically on every commit (auto-update is enabled). Re-run `/understand` after large refactors to force a full rebuild, or pass `--force` to rebuild from scratch.
+The knowledge graph lives in `.understand-anything/knowledge-graph.json` and is kept up-to-date automatically on every commit (auto-update is enabled). Re-run `/understand` after large refactors to force the graph to catch up, and re-run `/understand-knowledge docs/wiki` when you want to refresh the generated wiki content.
 EOF
   echo "✅ Understand-Anything code-research section appended to CLAUDE.md."
 fi
@@ -125,7 +127,7 @@ fi
 Notes:
 - The section is appended at the end of `CLAUDE.md` so it does not disturb existing content.
 - The marker string `## Code research with Understand-Anything` is used as the idempotency guard — do not rename the heading without updating the guard.
-- If `MIRRORS.md` / `AGENTS.md` or other agent-config files exist alongside `CLAUDE.md` (e.g. for non-Claude runtimes), apply the same append to them so all agent runtimes get the guidance. The loop below covers `AGENTS.md` and `MIRRORS.md` — add more filenames to the `for` list if the project uses additional agent-config files.
+- If `MIRRORS.md` / `AGENTS.md` or other agent-config files exist alongside `CLAUDE.md` (e.g. for non-Claude runtimes), apply the same append to them so all agent runtimes get the guidance. The loop below appends the same section only when missing.
 
 ```bash
 # Mirror to AGENTS.md / MIRRORS.md if they exist (non-Claude runtimes).
@@ -135,7 +137,7 @@ for f in AGENTS.md MIRRORS.md; do
 
 ## Code research with Understand-Anything
 
-This project uses the [Understand-Anything](https://github.com/Egonex-AI/Understand-Anything) plugin to maintain an interactive knowledge graph of the codebase. **Always prefer these commands over raw grep/glob when researching code structure, relationships, or logic:**
+This project uses the [Understand-Anything](https://github.com/Egonex-AI/Understand-Anything) plugin to maintain an interactive knowledge graph of the codebase. **Always prefer these commands over raw file-by-file exploration when doing code research:**
 
 | Goal | Command |
 |------|---------|
@@ -146,8 +148,9 @@ This project uses the [Understand-Anything](https://github.com/Egonex-AI/Underst
 | Open the interactive visual dashboard | `/understand-dashboard` |
 | Extract business-domain knowledge (domains, flows, steps) | `/understand-domain` |
 | Generate an onboarding guide for new teammates | `/understand-onboard` |
+| Generate or refresh wiki knowledge under `docs/wiki` | `/understand-knowledge docs/wiki` |
 
-The knowledge graph lives in `.understand-anything/knowledge-graph.json` and is kept up-to-date automatically on every commit (auto-update is enabled). Re-run `/understand` after large refactors to force a full rebuild, or pass `--force` to rebuild from scratch.
+The knowledge graph lives in `.understand-anything/knowledge-graph.json` and is kept up-to-date automatically on every commit (auto-update is enabled). Re-run `/understand` after large refactors to force the graph to catch up, and re-run `/understand-knowledge docs/wiki` when you want to refresh the generated wiki content.
 EOF
     echo "✅ Understand-Anything section also appended to $f."
   fi
@@ -164,13 +167,31 @@ Run the skill **in the main thread** (it dispatches its own analyzer subagents
 /understand --auto-update $ARGUMENTS
 ```
 
-- `--auto-update` writes `{"autoUpdate": true}` to `.understand-anything/config.json`. The plugin's bundled hook then incrementally patches the graph whenever a `git commit` is made (and on stale SessionStart), so each commit lands with a matching graph.
+- `--auto-update` writes `{"autoUpdate": true}` to `.understand-anything/config.json`. The plugin's bundled hook then incrementally patches the graph whenever a `git commit` is made (and on stale Session resume, depending on the plugin version).
 - If a graph already exists, `/understand` runs incrementally. Pass `--force` (via `$ARGUMENTS`) to rebuild from scratch.
 - After it finishes, confirm these exist: `.understand-anything/knowledge-graph.json`, `.understand-anything/meta.json`, `.understand-anything/config.json` (with `autoUpdate: true`).
 
 ---
 
-## Step 3 — Ignore scratch, git-lfs track the graph, and stage
+## Step 3 — Initialize the docs wiki from Understand-Anything
+
+Create the wiki folder if needed, then generate or refresh the wiki content in the main thread:
+
+```bash
+mkdir -p docs/wiki
+```
+
+```
+/understand-knowledge docs/wiki
+```
+
+- `mkdir -p docs/wiki` is idempotent and ensures the target directory exists before wiki generation.
+- Re-running `/understand-knowledge docs/wiki` should refresh the generated wiki content in place.
+- After it finishes, confirm `docs/wiki/` exists and contains generated wiki files before staging.
+
+---
+
+## Step 4 — Ignore scratch, git-lfs track the graph, and stage
 
 Scratch outputs must stay local (never committed):
 
@@ -185,7 +206,7 @@ git lfs install
 git lfs track ".understand-anything/*.json"
 
 # Stage — but DO NOT commit. A human reviews and commits.
-git add .gitattributes .gitignore .claude/settings.json .understand-anything/ CLAUDE.md
+git add .gitattributes .gitignore .claude/settings.json .understand-anything/ docs/wiki/ CLAUDE.md
 # Also stage AGENTS.md / MIRRORS.md if they were modified.
 for f in AGENTS.md MIRRORS.md; do [ -f "$f" ] && git add "$f"; done
 
@@ -202,5 +223,6 @@ Summarize for the user:
 - `CLAUDE.md` status: already existed vs created by `claude-code-setup`; Understand-Anything section added vs already present.
 - `AGENTS.md` status (if applicable): Understand-Anything section added vs already present / not found.
 - Graph status: created vs incrementally updated; `autoUpdate` on/off.
+- Wiki status: `docs/wiki` created vs already existed; `/understand-knowledge docs/wiki` run successfully vs failed.
 - What is staged and confirmed LFS-tracked.
-- Remind them: **review, then commit yourself** (e.g. `git commit -m "chore: share team onboarding (claude settings + CLAUDE.md + understand graph)"`). The auto-update hook keeps the graph fresh on every future commit.
+- Remind them: **review, then commit yourself** (e.g. `git commit -m "chore: share team onboarding (claude settings + CLAUDE.md + understand graph + wiki)"`). The auto-update hook keeps the graph fresh on every future commit, and the wiki can be refreshed by re-running `/understand-knowledge docs/wiki` whenever needed.

package/plugins/tech-graph/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "tech-graph",
-  "version": "0.0.27",
+  "version": "0.0.28",
   "description": "Step-by-step wizard for generating technical diagrams as SVG+PNG.",
   "author": {
     "name": "steven"