fabric-pattern
Integrate Daniel Miessler's Fabric patterns into local workflows for structured prompting, text transformation, and retrieval-assisted processing.
Best use case
fabric-pattern is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Integrate Daniel Miessler's Fabric patterns into local workflows for structured prompting, text transformation, and retrieval-assisted processing.
Teams using fabric-pattern 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/fabric-pattern/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How fabric-pattern Compares
| Feature / Agent | fabric-pattern | 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?
Integrate Daniel Miessler's Fabric patterns into local workflows for structured prompting, text transformation, and retrieval-assisted processing.
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
## Description
Integration for the Fabric AI framework (https://github.com/danielmiessler/Fabric). This skill manages text processing by reading local pattern files directly, while utilizing the Fabric CLI for specific web, YouTube, and search retrieval tasks.
## Rules
### 1. Pattern Application (Text Processing)
**Constraint:** Do NOT use `fabric -p "pattern"` to process text.
Instead, you must manually apply the pattern using the following logic:
1. **Identify Pattern:** Determine the correct pattern name. If unsure, read `~/.config/fabric/patterns/pattern_explanations.md` to find the best fit.
2. **Read Instruction:** Read the content of the system prompt file located at:
`~/.config/fabric/patterns/"pattern_name"/system.md`
3. **Apply:** Use the content of that `system.md` file as your strict instruction/persona to process the user's text.
### 2. Fabric CLI Usage (Retrieval & Tools)
Only use the `fabric` command line tool for the following specific retrieval or maintenance tasks:
* **YouTube/Video:** Use `fabric -y "URL"`
* *Default behavior:* Returns the transcript.
* *Supported flags:*
* `--playlist` (Prefer playlist over video)
* `--transcript` (Default)
* `--transcript-with-timestamps`
* `--comments`
* `--metadata`
* `--yt-dlp-args="..."` (e.g., `--cookies-from-browser brave`)
* `--spotify="..."` (For Spotify podcast/episode metadata)
* **Web Scraping:** Use `fabric -u "URL"` to fetch page contents as Markdown.
* **Context Search:** Use `fabric -q "question"` to search using Jina AI.
* **Updates:** Use `fabric -U` to update the local patterns folder.
### 3. Integrations
* **Obsidian:** If the user asks to save, read, or interact with their Obsidian vault in relation to Fabric content (e.g., "save this summary to my vault"), utilize the `obsidian-cli` skill.
## Examples
**User:** "Summarize this website using the extract_wisdom pattern: https://example.com"
**Action:**
1. Run `fabric -u "https://example.com"` to get the raw text.
2. Read `~/.config/fabric/patterns/extract_wisdom/system.md`.
3. Process the raw text using the instructions found in `system.md`.
**User:** "Use fabric to get the transcript with timestamps for this video."
**Action:**
Run `fabric -y "VIDEO_URL" --transcript-with-timestamps`
**User:** "I need to use fabric to analyze this text but I don't know which pattern to use."
**Action:**
1. Read `~/.config/fabric/patterns/pattern_explanations.md`.
2. Select the most relevant pattern.
3. Read that pattern's `system.md` and apply it to the text.Related Skills
Testing Anti-Patterns
Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.
Meta-Pattern Recognition
Spot patterns appearing in 3+ domains to find universal principles
microservices-patterns
Comprehensive microservices patterns skill covering service mesh, traffic management, circuit breakers, resilience patterns, Istio, and production microservices architecture
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
architecture-patterns
Software architecture patterns and best practices
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices
agent-patterns
Format SPAWN REQUEST messages to launch parallel agents, generate structured agent status reports, and define communication protocols within the sprint system. Use when the user needs to coordinate multiple agents, format spawn requests, produce agent reports, or establish inter-agent communication patterns.
wemp-operator
> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装
zsxq-smart-publish
Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
ziliu-publisher
字流(Ziliu) - AI驱动的多平台内容分发工具。用于一次创作、智能适配排版、一键分发到16+平台(公众号/知乎/小红书/B站/抖音/微博/X等)。当用户需要多平台发布、内容排版、格式适配时使用。触发词:字流、ziliu、多平台发布、一键分发、内容分发、排版发布。