Best use case
wish is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Teams using wish 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/wish/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How wish Compares
| Feature / Agent | wish | 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?
This skill provides specific capabilities for your AI agent. See the About section for full details.
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
# /eidos:wish Quickly capture a feature idea or request — something you want the system to do eventually, but that doesn't need a spec or plan yet. ## Usage ``` /eidos:wish [description] ``` ## Instructions 1. If no description provided, ask what the wish is 2. Run `date '+%y%m%d%H%M'` to get the current timestamp 3. Create `memory/wish - <timestamp> - <claim>.md`: ```markdown --- tldr: [description] --- # Wish: [description] [Optional context — motivation, rough ideas, links to related specs or features] ``` 4. Commit immediately When a wish gets specced out, rename from `wish -` to `specced -` (preserving timestamp and claim), update wiki links, and commit. Link to the resulting spec with an `=>` note. ## Output - Creates: `memory/wish - <timestamp> - <claim>.md`
Related Skills
spec
This skill guides an AI agent to collaboratively think through and create a detailed technical specification document via structured Q&A. It clarifies target, behavior, and design before generating the spec file.
worktree
No description provided.
weave
No description provided.
video
No description provided.
true-name
No description provided.
toskill
No description provided.
toscript
No description provided.
tomd
No description provided.
toeidos
No description provided.
todo
No description provided.
toclaude
No description provided.
tldr
No description provided.