vala_skillhub/skill-builder.xiaoxi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update: sync skill skill-builder 2026-04-01

Browse Source
This commit is contained in:
xiaoxi 2026-04-01 11:34:27 +08:00
commit aa3c61474d
6 changed files with 351 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.clawhub/origin.json Normal file
View File

@ -0,0 +1,7 @@
{
"version": 1,
"registry": "https://clawhub.ai",
"slug": "skill-builder",
"installedVersion": "1.0.5",
"installedAt": 1772328256596
}

104
SKILL.md Normal file
View File

@ -0,0 +1,104 @@
---
name: Skill Builder / Creator
slug: skill-builder
version: 1.0.5
homepage: https://clawic.com/skills/skill-builder
description: Create high-quality skills with modular structure, progressive disclosure, and token-efficient design.
changelog: Added description examples table, security checklist, and improved traps with fixes
metadata: {"clawdbot":{"emoji":"🛠️","requires":{"bins":[]},"os":["linux","darwin","win32"]}}
---
## Setup
On first use, read `setup.md` for integration guidelines.
## When to Use
User wants to create or improve a skill. Agent guides structure, reviews content, and ensures quality.
## Data Storage
If user wants project tracking, create folder in their home directory.
See `memory-template.md` for the template structure.
The agent does NOT create files automatically. Always ask user first.
## Architecture
Skills follow this structure:
```
skill-name/
├── SKILL.md # Core instructions (SHORT)
├── [topic].md # On-demand details
└── references/ # Heavy docs (optional)
```
## Quick Reference
| Topic | File |
|-------|------|
| Setup process | `setup.md` |
| Tracking projects | `memory-template.md` |
| Patterns and examples | `patterns.md` |
## Core Rules
### 1. SKILL.md Must Be Short
Target 30-50 lines, max 80. Move details to auxiliary files. Every line must justify its token cost.
### 2. Progressive Disclosure
```
Level 1: Metadata (name + description) — always loaded
Level 2: SKILL.md body — when skill triggers
Level 3: Auxiliary files — on demand
```
### 3. Descriptions Are Critical
One sentence, 15-25 words. Action verb first. Describes capabilities, not triggers.
| ❌ Wrong | ✅ Right |
|----------|----------|
| "Use when user needs PDFs" | "Process, merge, and extract PDF content" |
| "Helper for Docker" | "Build, deploy, and debug Docker containers" |
| "Git guide" | "Manage branches, resolve conflicts, and automate workflows" |
See `patterns.md` for more examples.
### 4. Required Structure
Every skill needs:
- Frontmatter: name, slug, version, description
- `## When to Use` — activation triggers
- `## Core Rules` — 3-7 numbered rules
### 5. Auxiliary Files Over Inline Content
If content exceeds 20 lines or is only needed sometimes, split to separate file. Reference from Quick Reference table.
### 6. No Redundancy
Information lives in ONE place. SKILL.md references files, doesn't duplicate content.
### 7. Test Before Publish
Read the skill as if you're an agent encountering it fresh. Is every instruction clear and necessary?
## Skill Building Traps
| Trap | Why it fails | Fix |
|------|--------------|-----|
| Explaining what X is | Models already know | Explain WHEN and HOW |
| "Use when..." in description | Wastes characters | Action verbs only |
| Keyword lists in description | Looks spammy | One clean sentence |
| Templates inline | Bloats SKILL.md | Separate file |
| Vague "observe" instructions | Gets flagged suspicious | Be specific about what data |
| Undeclared file creation | Security flag | Add Data Storage section |
## Related Skills
Install with `clawhub install <slug>` if user confirms:
- `skill-manager` — manage installed skills
- `skill-update` — update existing skills
- `skill-test` — test skills locally
## Feedback
- If useful: `clawhub star skill-builder`
- Stay updated: `clawhub sync`

6
_meta.json Normal file
View File

@ -0,0 +1,6 @@
{
"ownerId": "kn73vp5rarc3b14rc7wjcw8f8580t5d1",
"slug": "skill-builder",
"version": "1.0.5",
"publishedAt": 1772061099771
}

43
memory-template.md Normal file
View File

@ -0,0 +1,43 @@
# Memory Template — Skill Builder / Creator
**Optional:** If user wants to track projects, they can create `~/skill-builder/projects.md`.
Ask user before creating any files. Template:
```markdown
# Skill Projects
## Active
### [skill-name]
- status: drafting | reviewing | ready
- goal: [one sentence]
- files: SKILL.md, setup.md, [others]
- notes: [observations, decisions]
- last: YYYY-MM-DD
## Completed
### [skill-name]
- published: YYYY-MM-DD
- version: X.Y.Z
- lessons: [what worked, what to improve]
---
*Updated: YYYY-MM-DD*
```
## Status Values
| Value | Meaning |
|-------|---------|
| `drafting` | Writing initial content |
| `reviewing` | Checking structure, testing |
| `ready` | Ready to publish |
## Usage
- Add new project when user starts skill
- Update status as work progresses
- Move to Completed after publish
- Capture lessons for future skills

138
patterns.md Normal file
View File

@ -0,0 +1,138 @@
# Patterns — Skill Builder / Creator
Common patterns for different skill types.
## Pattern 1: Memory-Based Skills
Skills that learn and adapt to user preferences.
```
skill/
├── SKILL.md # Instructions + memory reference
├── setup.md # Integration process
├── memory-template.md # Memory structure
└── [domain].md # Domain details
```
**Key elements:**
- Memory structure with status tracking
- Rules for when to update memory
- Integration with user's main memory
## Pattern 2: Tool Integration Skills
Skills wrapping external tools or APIs.
```
skill/
├── SKILL.md # Workflow + commands
├── setup.md # Installation verification
├── reference.md # Command reference
└── scripts/ # Helper scripts
└── [tool].sh
```
**Key elements:**
- External Endpoints table (required)
- Security & Privacy section
- Script manifests
- Error handling guidance
## Pattern 3: Domain Expert Skills
Skills providing specialized knowledge.
```
skill/
├── SKILL.md # Overview + rules
├── setup.md # Minimal
├── memory-template.md # Minimal config
└── references/
├── [topic1].md
└── [topic2].md
```
**Key elements:**
- Progressive loading of references
- Clear triggers in description
- Core Rules capture expert judgment
## Pattern 4: Workflow Skills
Skills guiding multi-step processes.
```
skill/
├── SKILL.md # Process overview
├── setup.md # Prerequisites
├── memory-template.md # Progress tracking
├── phases/
│ ├── phase1.md
│ └── phase2.md
└── templates/ # Output templates
```
**Key elements:**
- Clear phase boundaries
- Progress tracking in memory
- Templates for outputs
## Description Examples
### Good Descriptions (copy these patterns)
| Domain | Description |
|--------|-------------|
| PDF | "Process, merge, and extract PDF content with page manipulation and text extraction." |
| Git | "Manage branches, resolve conflicts, and automate Git workflows with best practices." |
| Docker | "Build, deploy, and debug Docker containers with compose patterns and troubleshooting." |
| API | "Design, document, and test REST APIs with OpenAPI specs and mock servers." |
| Database | "Query, optimize, and migrate databases with schema design and performance tuning." |
### Bad Descriptions (avoid these)
| ❌ Bad | Why |
|--------|-----|
| "Use when you need to work with PDFs" | Starts with "Use when" |
| "PDF helper. Triggers: pdf, document, merge" | Multiple sentences, keyword list |
| "A comprehensive guide to Docker—including containers, images, and more" | Em-dash, vague "more" |
| "Helper for Git stuff" | Too vague, "stuff" |
### Formula
```
[Verb], [verb], and [verb] [technology] with [feature], [feature], and [feature].
```
15-25 words. One sentence. No em-dashes (—). No "Use when".
## Frontmatter Checklist
```yaml
---
name: Clear Name # What it is
slug: clear-name # Lowercase, hyphens
version: 1.0.0 # Semver
description: One sentence. # Action verbs. 15-25 words.
---
```
## Quality Checklist
Before publishing:
- [ ] SKILL.md under 80 lines?
- [ ] Description is one sentence, 15-25 words?
- [ ] All required sections present?
- [ ] No redundancy between files?
- [ ] Core Rules are actionable?
- [ ] Traps are real failure modes?
## Security Checklist
Avoid getting flagged as suspicious:
- [ ] No vague words: "silently", "secretly", "automatically"
- [ ] If creating files, add `## Data Storage` section
- [ ] If using APIs, add `## External Endpoints` table
- [ ] If using env vars, declare in metadata requires
- [ ] No "observe", "monitor", "track" without specifying WHAT exactly
- [ ] Always mention "ask user first" for file operations

53
setup.md Normal file
View File

@ -0,0 +1,53 @@
# Setup — Skill Builder / Creator
Reference this file when helping users create skills.
## Your Role
Help users create effective skills. Guide them through structure, naming, and best practices.
## Priority Order
### 1. Understand the Goal
Ask:
- "What should this skill help with?"
- "What tasks will it handle?"
Listen for: domain, triggers, audience (human using agent vs agent-to-agent).
### 2. Identify the Structure
Based on their goal, determine:
- Does it need memory? (tracks preferences, history, state)
- Does it call external APIs?
- Does it need scripts for deterministic tasks?
- How much auxiliary content?
### 3. Guide the Build
Walk them through:
1. Name and description (critical for discovery)
2. Core Rules (what the agent MUST do)
3. Traps (where models fail)
4. File structure
## Key Principles to Convey
**Concise over comprehensive:**
"Models are smart. Only add what they don't already know."
**Progressive disclosure:**
"Details go in separate files, loaded when needed."
**Description matters most:**
"This is what agents read to decide if your skill matches their query."
## When Done
You're ready when:
- Clear understanding of what the skill does
- Draft structure outlined
- User knows what files they need
Everything else builds iteratively.