extract-component skillA
extract-component is agent-read markdown (skill) from dropfan/claude-code-plugins: This skill should be used when the user asks to "extract skill", "extract command", "extract agent", "extract pattern", "save as skill", "save as command", "save as agent", "turn this into a skill", "make this a command", "save this workflow", "提取技能", "提取命令", "提取 agent", "保存为技能", "提取可复用模式", or wants to extract reusable components (skills, commands, agents) from the current conversation history..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Extract Component ## Overview Analyze the current conversation history and extract reusable patterns into Claude Code components — Skills, Commands, or Agents. This skill identifies valuable methodology, operation sequences, and decision workflows from the conversation and generates properly formatted component files. ## Intent Classification When the user triggers this skill, determine the extraction intent: 1. **Explicit type** — User specifies what they want (e.g., "extract a skill", "make this a command") 2. **Auto-detect** — User wants extraction but hasn't specified the type (e.g., "extract pattern", "save this workflow") ### Component Type Guidelines - **Skill** — A methodology, technique, or approach for solving a category of problems. Skills describe *how to think about* a problem, with progressive disclosure of details. Best for: debugging strategies, review processes, design methodologies, domain-specific expertise. - **Command** — A concrete sequence of operations that can be executed with parameters. Commands are action-oriented with clear inputs and outputs. Best for: build workflows, deployment steps, data processing pipelines, repetitive multi-step tasks. …
Read the whole file at its exact version.
How to install
mdr add dropfan/claude-code-plugins/extract-component@git:20260705.f29e110mdr add dropfan/claude-code-plugins/extract-component@sha256:f5187aaa530cd31ePin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_qowugyn5iesvueah)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260705.f29e110 latest | 2026-07-05 | f29e110 | 2,282 B | A | view · diff |
| git:20260318.0aaf04d | 2026-03-18 | 0aaf04d | 2,282 B | A | view · diff |
| v0.1.0 | 2026-02-09 | 145b0d8 | 2,663 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2282 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
dropfan/claude-code-plugins · 8 stars · license MIT · pushed 2026-09-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_qowugyn5iesvueah GET https://markdownregistry.com/api/v1/resolve?ref=dropfan/claude-code-plugins/extract-component GET https://markdownregistry.com/api/v1/blob/f5187aaa530cd31ed5e293b63a0c4144a3260affd0e8760417ad16758aa5b994
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.