customize
/customize
Create a Wisp specialist or author a project-local skill using the tools Wisp actually exposes. Use when the user wants a custom Agent persona, a restricted specialist loadout, a new skill, or changes to an existing project-local skill.
- Author
- xuzhougeng ↗
- Repository
- wisp-science ↗
- Licence
- AGPL-3.0
- Last repository change
- 25.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.
AGPL-3.0, copyleft: przeróbki udostępniane innym muszą mieć tę samą licencję.
What it does and when to use it
Create a Wisp specialist or author a project-local skill using the tools Wisp actually exposes. Use when the user wants a custom Agent persona, a restricted specialist loadout, a new skill, or changes to an existing project-local skill.
Original author description
Create a Wisp specialist or author a project-local skill using the tools Wisp actually exposes. Use when the user wants a custom Agent persona, a restricted specialist loadout, a new skill, or changes to an existing project-local skill.
How it works
- Create a specialist
- Author or update a skill
- Custom appearance
- Boundaries
SKILL.md preview
--- name: customize description: Create a Wisp specialist or author a project-local skill using the tools Wisp actually exposes. Use when the user wants a custom Agent persona, a restricted specialist loadout, a new skill, or changes to an existing project-local skill. --- # Customize Wisp Wisp exposes customization through explicit tools and Settings UI. Python has no control-plane SDK. Never invent profile, connector, or skill CRUD methods. ## Create a specialist Use `save_specialist` only when it is advertised in the current session. 1. Ask what single job the specialist owns and what it must not do. 2. Draft a display name, one-line description, and concise instructions that extend Wisp's base prompt. 3. Decide whether to inherit project skills/connectors or use explicit whitelists. Use exact installed skill names returned by `search_skills`. Include connector names only when the user supplied or confirmed them. 4. Show the complete proposal and obtain confirmation before creating or updating it. 5. To edit an existing specialist, call `configure` with `action=get` and key `specialists`, then `save_specialist` with that `id`. Omit `id` to create. Builtin instruction text cannot be replaced. 6. Call `save_specialist` with `name` and `instructions`; add `description`, `model_id`, `skills`, or `connectors` only when intentionally chosen. 7. Report the returned specialist id. Deletion, icons, and color still live under **Settings → Specialists**. Omit `skills` and `connectors` to inherit project settings. An empty list is an explicit zero-access whitelist and is not equivalent to omission. ## Author or update a skill Load `skill-creator`. For a project-local skill, edit files under: ```text .wisp/skills/<skill-name>/SKILL.md ``` Use `read`, `write`, and `edit`. `search_skills` and `use_skill` are discovery and loading tools, not mutation tools. If a newly created project skill is not visible immediately, refresh or reopen the project so Wisp rebuilds its skill index. For a user-wide skill, create the folder in the project first, validate it, then ask the user to install that folder through **Settings → Skills**. Wisp copies installed skills to its user skill directory; there is no Agent-side publish or delete interface. ## Custom appearance For a user stylesheet (hide the lead bar, restyle chat, override tokens), load `custom-theme`. Write CSS that uses documented tokens, then apply it with `configure` `set custom_css` or ask the user to import the file under **Settings → Appearance**. ## Boundaries - Do not modify Wisp's SQLite store directly. - Do not use `python`, `shell`, or `run_in_context` to bypass Settings or tool authorization. - Do not promise conversation identity switching; the user selects specialists through Wisp's UI. - Do not claim connector enumeration when no connector-management tool is advertised.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · xuzhougeng/wisp-science | 100 | AGPL-3.0 |
| aipoch/open-science | 100 | Apache-2.0 |
| DingyangLyu/MatClaw | 100 | Apache-2.0 |
| unicomai/wanwu | 100 | Apache-2.0 |
| microsoft/skills | 100 | MIT |
| nanocoai/nanoclaw | 100 | MIT |
| mcarmona1064-cell/clawbridge-ai | 100 | MIT |
| sliamh11/Deus | 100 | MIT |
| anthropics/defending-code-reference-harness | 100 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version 7409c76a4f14 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100wisp-writer
在 Wisp(Astro 技术博客主题)站点中写作的 skill。用户要求写、改写、扩写一篇博客文章,把笔记、论文、文档或对话整理成博客,批量生成文章草稿,或者检查文章的 frontmatter、格式、标签是否合规时使用。提供文章模板、创建脚本、检查脚本和中文技术写作规范,保证文章风格与主题一致。画图请交给 wisp-diagram skill,本 skill 不负责。 - 100skill-creator
Create, update, validate, and evaluate Wisp skills. Use when authoring a project-local or installable skill, refining its trigger description, adding deterministic scripts or Python/R runtime sidecars, or testing whether another Agent can follow the workflow. - 93wisp-paper
使用 Wisp Paper 的 wisp CLI 或 MCP 新建文献库、导入本地 PDF / BibTeX / RIS / Zotero、在线检索并导入文献、获取开放全文、阅读和检索 PDF 文本、查找引用与提交筛选建议。用户提到 Wisp Paper、文献库、批量收集论文或基于本地论文回答问题时使用。 - 96mcp-server-development
Design, implement, and validate an MCP server that exposes a bounded set of tools or resources to AI clients. Use when integrating an external API, service, or local capability through MCP. - 100agent-creator
Create new Claude Code subagents (the .claude/agents/ kind, NOT skills). Use this skill whenever the user wants to create a subagent, agent, persona, specialist, role, or delegatable worker. Also use when the user says "create an agent", "make me an agent for X", "I need a… - 100compute-env-setup
Set up and validate a reproducible Python or R environment on a Wisp execution context. Use for a selected local, WSL, or direct SSH context when installing scientific packages, configuring caches, recording interpreter activation, or producing an environment smoke test. Do not…