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.
npx skills add https://github.com/xuzhougeng/wisp-science --skill customize
Wisp exposes customization through explicit tools and Settings UI. Python has
no control-plane SDK. Never invent profile, connector, or skill CRUD methods.
Use save_specialist only when it is advertised in the current session. It is
create-only.
extend Wisp's base prompt.
whitelists. Use exact installed skill names returned by search_skills.
Include connector names only when the user supplied or confirmed them.
save_specialist with name and instructions; add description,model_id, skills, or connectors only when intentionally chosen.
Settings → Specialists for edits, deletion, icons, or later loadout
changes; no Agent tool performs those mutations.
Omit skills and connectors to inherit project settings. An empty list is an
explicit zero-access whitelist and is not equivalent to omission.
Load skill-creator. For a project-local skill, edit files under:
.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.
python, shell, or run_in_context to bypass Settings or toolauthorization.
through Wisp's UI.
advertised.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take xuzhougeng/customize from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.