refactor: simplify CLAUDE.md, move detailed docs to docs/

CLAUDE.md reduced from 621 to 76 lines (↓88%). Detailed guidelines
moved to on-demand reference files under docs/.
This commit is contained in:
Jim Liu 宝玉
2026-03-11 21:01:59 -05:00
parent 3bba18c1fe
commit 270a9af804
6 changed files with 326 additions and 582 deletions
+27
View File
@@ -0,0 +1,27 @@
# Chrome Profile
All CDP skills share a single profile directory. Do NOT create per-skill profiles.
Override: `BAOYU_CHROME_PROFILE_DIR` env var (takes priority over all defaults).
| Platform | Default Path |
|----------|-------------|
| macOS | `~/Library/Application Support/baoyu-skills/chrome-profile` |
| Linux | `$XDG_DATA_HOME/baoyu-skills/chrome-profile` (fallback `~/.local/share/`) |
| Windows | `%APPDATA%/baoyu-skills/chrome-profile` |
| WSL | Windows home `/.local/share/baoyu-skills/chrome-profile` |
New skills: use `BAOYU_CHROME_PROFILE_DIR` only (not per-skill env vars like `X_BROWSER_PROFILE_DIR`).
## Implementation Pattern
```typescript
function getDefaultProfileDir(): string {
const override = process.env.BAOYU_CHROME_PROFILE_DIR?.trim();
if (override) return path.resolve(override);
const base = process.platform === 'darwin'
? path.join(os.homedir(), 'Library', 'Application Support')
: process.env.XDG_DATA_HOME || path.join(os.homedir(), '.local', 'share');
return path.join(base, 'baoyu-skills', 'chrome-profile');
}
```
+35
View File
@@ -0,0 +1,35 @@
# Style Maintenance (baoyu-comic)
## Adding a New Style
1. Create style definition: `skills/baoyu-comic/references/styles/<style-name>.md`
2. Update SKILL.md: add to `--style` options table + auto-selection entry
3. Generate showcase image:
```bash
${BUN_X} skills/baoyu-danger-gemini-web/scripts/main.ts \
--prompt "A single comic book page in <style-name> style showing [scene]. Features: [characteristics]. 3:4 portrait aspect ratio comic page." \
--image screenshots/comic-styles/<style-name>.png
```
4. Compress: `${BUN_X} skills/baoyu-compress-image/scripts/main.ts screenshots/comic-styles/<style-name>.png`
5. Update both READMEs (`README.md` + `README.zh.md`): add style to options, description table, preview grid
## Updating an Existing Style
1. Update style definition in `references/styles/`
2. Regenerate showcase image if visual characteristics changed (steps 3-4 above)
3. Update READMEs if description changed
## Deleting a Style
1. Delete style definition + showcase image (`.webp`)
2. Remove from SKILL.md `--style` options + auto-selection
3. Remove from both READMEs (options, description table, preview grid)
## Style Preview Grid Format
```markdown
| | | |
|:---:|:---:|:---:|
| ![style1](./screenshots/comic-styles/style1.webp) | ![style2](./screenshots/comic-styles/style2.webp) | ![style3](./screenshots/comic-styles/style3.webp) |
| style1 | style2 | style3 |
```
+135
View File
@@ -0,0 +1,135 @@
# Creating New Skills
**REQUIRED READING**: [Skill authoring best practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices)
## Key Requirements
| Requirement | Details |
|-------------|---------|
| **Prefix** | All skills MUST use `baoyu-` prefix |
| **name field** | Max 64 chars, lowercase letters/numbers/hyphens only, no "anthropic"/"claude" |
| **description** | Max 1024 chars, third person, include what + when to use |
| **SKILL.md body** | Keep under 500 lines; use `references/` for additional content |
| **References** | One level deep from SKILL.md; avoid nested references |
## SKILL.md Frontmatter Template
```yaml
---
name: baoyu-<name>
description: <Third-person description. What it does + when to use it.>
version: <semver matching marketplace.json>
metadata:
openclaw:
homepage: https://github.com/JimLiu/baoyu-skills#baoyu-<name>
requires: # include only if skill has scripts
anyBins:
- bun
- npx
---
```
## Steps
1. Create `skills/baoyu-<name>/SKILL.md` with YAML front matter
2. Add TypeScript in `skills/baoyu-<name>/scripts/` (if applicable)
3. Add prompt templates in `skills/baoyu-<name>/prompts/` if needed
4. Register in `marketplace.json` under appropriate category
5. Add Script Directory section to SKILL.md if skill has scripts
6. Add openclaw metadata to frontmatter
## Category Selection
| If your skill... | Use category |
|------------------|--------------|
| Generates visual content (images, slides, comics) | `content-skills` |
| Publishes to platforms (X, WeChat, Weibo) | `content-skills` |
| Provides AI generation backend | `ai-generation-skills` |
| Converts or processes content | `utility-skills` |
New category: add plugin object to `marketplace.json` with `name`, `description`, `skills[]`.
## Writing Descriptions
**MUST write in third person**:
```yaml
# Good
description: Generates Xiaohongshu infographic series from content. Use when user asks for "小红书图片", "XHS images".
# Bad
description: I can help you create Xiaohongshu images
```
## Script Directory Template
Every SKILL.md with scripts MUST include:
```markdown
## Script Directory
**Important**: All scripts are located in the `scripts/` subdirectory of this skill.
**Agent Execution Instructions**:
1. Determine this SKILL.md file's directory path as `{baseDir}`
2. Script path = `{baseDir}/scripts/<script-name>.ts`
3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
4. Replace all `{baseDir}` and `${BUN_X}` in this document with actual values
**Script Reference**:
| Script | Purpose |
|--------|---------|
| `scripts/main.ts` | Main entry point |
```
## Progressive Disclosure
For skills with extensive content:
```
skills/baoyu-example/
├── SKILL.md # Main instructions (<500 lines)
├── references/
│ ├── styles.md # Loaded as needed
│ └── examples.md # Loaded as needed
└── scripts/
└── main.ts
```
Link from SKILL.md (one level deep only):
```markdown
**Available styles**: See [references/styles.md](references/styles.md)
```
## Extension Support (EXTEND.md)
Every SKILL.md MUST include EXTEND.md loading. Add as Step 1.1 (workflow skills) or "Preferences" section (utility skills):
```markdown
**1.1 Load Preferences (EXTEND.md)**
Check EXTEND.md existence (priority order):
\`\`\`bash
test -f .baoyu-skills/<skill-name>/EXTEND.md && echo "project"
test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/<skill-name>/EXTEND.md" && echo "xdg"
test -f "$HOME/.baoyu-skills/<skill-name>/EXTEND.md" && echo "user"
\`\`\`
| Path | Location |
|------|----------|
| `.baoyu-skills/<skill-name>/EXTEND.md` | Project directory |
| `$XDG_CONFIG_HOME/baoyu-skills/<skill-name>/EXTEND.md` | XDG config (~/.config) |
| `$HOME/.baoyu-skills/<skill-name>/EXTEND.md` | User home (legacy) |
| Result | Action |
|--------|--------|
| Found | Read, parse, display summary |
| Not found | Ask user with AskUserQuestion |
```
End of SKILL.md should include:
```markdown
## Extension Support
Custom configurations via EXTEND.md. See **Step 1.1** for paths and supported options.
```
+53
View File
@@ -0,0 +1,53 @@
# Image Generation Guidelines
Skills that require image generation MUST delegate to available image generation skills.
## Skill Selection
**Default**: `skills/baoyu-image-gen/SKILL.md` (unless user specifies otherwise).
1. Read skill's SKILL.md for parameters and capabilities
2. If user requests different skill, check `skills/` for alternatives
3. Only ask user when multiple viable options exist
## Generation Flow Template
```markdown
### Step N: Generate Images
**Skill Selection**:
1. Check available skills (`baoyu-image-gen` default, or `baoyu-danger-gemini-web`)
2. Read selected skill's SKILL.md for parameters
3. If multiple skills available, ask user to choose
**Generation Flow**:
1. Call skill with prompt, output path, and skill-specific parameters
2. Generate sequentially by default (batch parallel only when user has multiple prompts)
3. Output progress: "Generated X/N"
4. On failure, auto-retry once before reporting error
```
**Batch Parallel** (`baoyu-image-gen` only): concurrent workers with per-provider throttling via `batch.max_workers` in EXTEND.md.
## Output Path Convention
**Output Directory**: `<skill-suffix>/<topic-slug>/`
- `<skill-suffix>`: e.g., `xhs-images`, `cover-image`, `slide-deck`, `comic`
- `<topic-slug>`: 2-4 words, kebab-case from content topic
- Conflict: append timestamp `<topic-slug>-YYYYMMDD-HHMMSS`
**Source Files**: Copy to output dir as `source-{slug}.{ext}`
## Image Naming Convention
**Format**: `NN-{type}-[slug].png`
- `NN`: Two-digit sequence (01, 02, ...)
- `{type}`: cover, content, page, slide, illustration, etc.
- `[slug]`: 2-5 word kebab-case descriptor, unique within directory
Examples:
```
01-cover-ai-future.png
02-content-key-benefits.png
03-slide-architecture-overview.png
```
+39
View File
@@ -0,0 +1,39 @@
# ClawHub / OpenClaw Publishing
## OpenClaw Metadata
Skills include `metadata.openclaw` in YAML front matter:
```yaml
metadata:
openclaw:
homepage: https://github.com/JimLiu/baoyu-skills#<skill-name>
requires: # only for skills with scripts
anyBins:
- bun
- npx
```
## Publishing Commands
```bash
bash scripts/sync-clawhub.sh # sync all skills
bash scripts/sync-clawhub.sh <skill> # sync one skill
```
Release-time artifact preparation is configured via `.releaserc.yml`. Keep registry/project-specific packaging in hook scripts.
## Shared Workspace Packages
`packages/` is the **only** source of truth. Never edit `skills/*/scripts/vendor/` directly.
Current package: `baoyu-chrome-cdp` (Chrome CDP utilities), consumed by 6 skills (`baoyu-danger-gemini-web`, `baoyu-danger-x-to-markdown`, `baoyu-post-to-wechat`, `baoyu-post-to-weibo`, `baoyu-post-to-x`, `baoyu-url-to-markdown`).
**How it works**: Sync script copies packages into each consuming skill's `vendor/` directory and rewrites dependency specs to `file:./vendor/<name>`. Vendor copies are committed to git, making skills self-contained.
**Update workflow**:
1. Edit package under `packages/`
2. Run `node scripts/sync-shared-skill-packages.mjs`
3. Commit synced `vendor/`, `package.json`, and `bun.lock` together
**Git hook**: Run `node scripts/install-git-hooks.mjs` once to enable the `pre-push` hook. It re-syncs and blocks push if vendor copies are stale (`--enforce-clean`).