opence-skill-creator
Learn how to create effective project skills following opence conventions.
Best use case
opence-skill-creator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Learn how to create effective project skills following opence conventions.
Teams using opence-skill-creator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/opence-skill-creator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How opence-skill-creator Compares
| Feature / Agent | opence-skill-creator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Learn how to create effective project skills following opence conventions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
<!-- OPENCE:START -->
# opence-skill-creator
Learn how to create effective project skills following opence conventions.
## When to Create a Skill
Create a skill during the **compound phase** when you identify:
- Repeatable workflows that can be encoded as instructions
- Recurring pitfalls or manual checks that need documentation
- Domain-specific knowledge that will be useful in future changes
Don't create a skill for one-off solutions or highly specific edge cases.
## Quick Start
Use the CLI to create skills (recommended):
```bash
# Create a new skill
opence skill add api-testing --description "Guidelines for testing API endpoints"
# List all skills
opence skill list
# Show skill details
opence skill show api-testing
```
The CLI automatically:
- Creates proper directory structure
- Generates correct frontmatter for each tool
- Validates naming conventions
- Creates references/ and scripts/ directories
## Skill Structure
```
.claude/skills/my-skill/
├── SKILL.md # Concise entry point (< 200 lines)
├── references/ # Detailed documentation
│ └── *.md # Extended guides, examples
└── scripts/ # Reusable code
└── *.sh, *.py # Helper scripts
```
**SKILL.md**: Keep concise. Include "When to use", key steps, and pointers to references/.
**references/**: Put detailed docs, long examples, API references here.
**scripts/**: Add reusable code that users can copy or execute.
## Naming Rules
- **Format**: kebab-case (e.g., `api-testing`, `deploy-prod`)
- **Reserved**: Don't use `opence-` prefix (reserved for native skills)
- **Unique**: Check with `opence skill list` to avoid duplicates
**Valid**: `api-testing`, `error-recovery`, `db-migration`
**Invalid**: `api testing` (spaces), `api_testing` (underscores), `opence-custom` (reserved)
## Writing Effective Descriptions
The `description` field determines when Claude automatically loads your skill. Write it carefully.
**Good description patterns:**
- Start with an action verb: Explains, Creates, Reviews, Validates, Deploys, Fixes
- Include keywords users naturally say
- List specific trigger scenarios
- Be specific but not overly narrow
**Examples of good descriptions:**
```
"Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks 'how does this work?'"
"Fix a GitHub issue following our coding standards. Use when working on issues or bugs."
"Research a topic thoroughly using multiple sources. Use for deep dives or comprehensive analysis."
```
**Anti-patterns to avoid:**
- Too abstract: `"Helps with development tasks"` — Claude can't decide when to use it
- Too specific: `"Fix the login button CSS on mobile Safari 15.4"` — Won't match future requests
- Missing scenarios: `"API testing utility"` — No trigger context
**Trigger phrase checklist:**
- [ ] Does it include words users would naturally say?
- [ ] Would Claude know when to load it automatically?
- [ ] Is it distinct from other skills' triggers?
## Next Steps
After creating a skill:
1. Edit SKILL.md to add instructions and examples
2. Add detailed docs to references/ if needed
3. Add helper scripts to scripts/ if applicable
4. Test the skill in actual usage
5. Commit to version control
See references/ for detailed guidance on:
- [Skill evaluation checklist](references/skill-evaluation-checklist.md) — Four-question framework and "is it worth creating" criteria
- Directory structure and sizing
- Frontmatter formats for different tools
- Best practices and anti-patterns
<!-- OPENCE:END -->Related Skills
og-creator-skill
Create or fix Open Graph metadata for any web project across stacks (React/Vue/Svelte/Next/Nuxt/SSR/SSG/static). Use when a user asks to add OG tags, fix social previews, or standardize OG/Twitter metadata, especially when react-helmet-async is required and og:image must be an absolute URL.
nav-skill-creator
Analyze codebase patterns and create custom skills for repetitive workflows. Use when project needs automation or pattern enforcement. Auto-invoke when user says "create a skill for...", "automate this workflow", or "we keep doing X manually".
modern-web-creator
Creates distinctive, human-quality websites using 2025 design philosophy—anti-design aesthetics, bold minimalism, organic shapes, and intentional imperfection. Specializes in React/TypeScript with Tailwind CSS, shadcn/ui, and custom micro-interactions. Prevents generic AI templates through specific constraints, asymmetric layouts, and brand-aligned creative direction. Use for portfolios, marketing sites, SaaS interfaces, or any project requiring unique visual identity beyond cookie-cutter designs.
ln-114-frontend-docs-creator
Creates design_guidelines.md for frontend projects. L3 Worker invoked CONDITIONALLY when hasFrontend detected.
interactive-component-creator
Build interactive web components and artifacts. Creates interactive UI elements, visualizations, and web-based applications.
fastmcp-creator
Build Model Context Protocol (MCP) servers - comprehensive coverage of generic MCP protocol AND FastMCP framework specialization. Use when creating any MCP server (Python FastMCP preferred, TypeScript/Node also covered). Includes agent-centric design principles, evaluation creation, Pydantic/Zod validation, async patterns, STDIO/HTTP/SSE transports, FastMCP Cloud deployment, .mcpb packaging, security patterns, and mid-2025+ community practices. Standalone skill with no external dependencies.
claude-md-creator
Use when creating CLAUDE.md files, updating existing CLAUDE.md, validating CLAUDE.md structure, or auto-fixing CLAUDE.md issues. Load for setting up project instructions, global guidelines, local overrides, or modular rules. Handles global (~/.claude/CLAUDE.md), project (.claude/CLAUDE.md), local (CLAUDE.local.md), and rules (.claude/rules/*.md) with smart project detection and template generation.
architecture-documentation-creator
Create comprehensive technical documentation for code systems including data flow diagrams, architecture overviews, algorithm documentation, cheat sheets, and multi-file documentation sets. Use when documenting pipelines, algorithms, system architecture, data flow, multi-stage processes, similarity algorithms, or creating developer onboarding materials. Covers Mermaid diagrams, progressive disclosure, critical patterns, JSON schemas, Pydantic models, and print-friendly reference materials.
architecture-diagram-creator
Create comprehensive HTML architecture diagrams showing data flows, business objectives, features, technical architecture, and deployment. Use when users request system architecture, project documentation, high-level overviews, or technical specifications.
adr-creator
Create Architecture Decision Records (ADRs) documenting significant technical decisions for the FF Analytics platform. This skill should be used when making architectural choices, evaluating alternatives for data models or infrastructure, documenting trade-offs, or when the user asks "should we use X or Y approach?" Guides through the ADR creation workflow from context gathering to documentation.
action-creator
Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use when user wants reusable actions for their specific workflows (send payment reminder to ACME Corp, forward bugs to engineering, archive old newsletters from specific sources).
ac-handoff-creator
Create handoff packages for session transitions. Use when ending sessions, preparing for continuation, saving session state, or creating resumable context.