菜单
Customize or personalize a Codex plugin for a specific organization's tools and workflows by replacing placeholders and configuring MCP servers.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/vamseeachanta/workspace-hub --skill cowork-plugin-customizer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
基于 SOC 职业分类
正在显示 SKILL.md
| name | cowork-plugin-customizer |
| description | Customize or personalize a Codex plugin for a specific organization's tools and workflows by replacing placeholders and configuring MCP servers. |
| type | reference |
| version | 1.0.0 |
| category | development |
| last_updated | "2026-02-03T00:00:00.000Z" |
| source | https://github.com/anthropics/knowledge-work-plugins |
| related_skills | [] |
| capabilities | [] |
| requires | [] |
| see_also | [] |
| tags | [] |
Adapt a generic plugin template to a specific organization by replacing customization points with actual tool names, configuring MCP servers, and applying organization-specific customizations.
Finding the plugin: To find the plugin's source files, run
find mnt/.local-plugins mnt/.plugins -type d -name "*<plugin-name>*"to locate the plugin directory, then read its files to understand its structure before making changes. If you cannot find the plugin directory, the user is likely running this conversation in a remote container. Abort and let them know: "Customizing plugins is currently only available in the desktop app's Cowork mode."
Generic plugins mark customization points with a ~~ prefix. Any line or value starting with ~~ is a placeholder that should be replaced during customization (e.g., ~~Jira -> Asana, ~~your-team-channel -> #engineering). To find all customization points in a plugin, use:
grep -rn '~~\w' /path/to/plugin --include='*.md' --include='*.json'
Important: Never change the name of the plugin or skill being customized. Only replace
~~-prefixed placeholder values and update content -- do not rename directories, files, or the plugin/skill name fields.
Nontechnical output: All user-facing output (todo list items, questions, summaries) must be written in plain, nontechnical language. Never mention
~~prefixes, placeholders, or customization points to the user. Frame everything in terms of learning about the organization and its tools.
The process:
~~\w to find all customization points and build a todo listIf an answer cannot be found via knowledge MCPs or user input, leave the customization point unchanged for a future customization cycle.
Use company-internal knowledge MCPs to collect information. See references/search-strategies.md for detailed query patterns by category.
What to gather:
~~-prefixed placeholderSources to search:
Record all findings for use in Phase 3.
Run grep -rn '~~\w' /path/to/plugin --include='*.md' --include='*.json' to find all customization points. Group them by theme and create a todo list with user-friendly descriptions that focus on learning about the organization:
Work through each item using Phase 1 context.
If knowledge MCPs provided a clear answer: Apply directly without confirmation.
Otherwise: Use AskUserQuestion. Don't assume "industry standard" defaults are correct -- if knowledge MCPs didn't provide a specific answer, ask. Note: AskUserQuestion always includes a Skip button and a free-text input box for custom answers, so do not include None or Other as options.
Types of changes:
~~Jira -> Asana, ~~your-org-channel -> #engineeringtickets.example.com/your-team/123 -> app.asana.com/0/PROJECT_ID/TASK_IDIf user doesn't know or skips, leave the ~~-prefixed value unchanged.
After all customization points have been resolved, connect MCPs for the tools that were identified. See references/mcp-servers.md for the full workflow, category-to-keywords mapping, and config file format.
For each tool identified during customization:
search_mcp_registry(keywords=[...]) using category keywords from references/mcp-servers.md, or search for the specific tool name if already knownsuggest_connectors(directoryUuids=["chosen-uuid"]) -- user completes OAuthplugin.json for custom location, otherwise .mcp.json at root)Collect all MCP results and present them together in the summary output (see below) -- don't present MCPs one at a time during this phase.
Note: First-party integrations (Gmail, Google Calendar, Google Drive) are connected at the user level and don't need plugin .mcp.json entries.
After all customizations are applied, package the plugin as a .plugin file for the user:
setup/ since it's no longer needed):
cd /path/to/plugin && zip -r /tmp/plugin-name.plugin . -x "setup/*" && cp /tmp/plugin-name.plugin /path/to/outputs/plugin-name.plugin
.plugin extension so they can install it directly. (Presenting the .plugin file will show to the user as a rich preview where they can look through the plugin files, and they can accept the customization by pressing a button.)Important: Always create the zip in
/tmp/first, then copy to the outputs folder. Writing directly to the outputs folder may fail due to permissions and leave behind temporary files.
Naming: Use the original plugin directory name for the
.pluginfile (e.g., if the plugin directory iscoder, the output file should becoder.plugin). Do not rename the plugin or its files during customization -- only replace placeholder values and update content.
After customization, present the user with a summary of what was learned grouped by source. Always include the MCPs sections showing which MCPs were connected during setup and which ones the user should still connect:
## From searching Slack
- You use Asana for project management
- Sprint cycles are 2 weeks
## From searching documents
- Story points use T-shirt sizes
## From your answers
- Ticket statuses are: Backlog, In Progress, In Review, Done
Then present the MCPs that were connected during setup and any that the user should still connect, with instructions on how to connect them.
If no knowledge MCPs were available in Phase 1, and the user had to answer at least one question manually, include a note at the end:
By the way, connecting sources like Slack or Microsoft Teams would let me find answers automatically next time you customize a plugin.
references/mcp-servers.md -- MCP discovery workflow, category-to-keywords mapping, config file locationsreferences/search-strategies.md -- Knowledge MCP query patterns for finding tool names and org valuesexamples/customized-mcp.json -- Example fully configured .mcp.json