iwsdk-dev
Skill350 starsChanged 24 days agoMITView on GitHub
Single entry point for IWSDK development. Invoke first for every IWSDK implementation request. Routes fresh builds to an internal planning playbook and bounded changes to an established app to an internal iteration playbook.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mirzaaghazadeh/iwsdk-webxr-skillsword for word, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 1
- mirzaaghazadeh/iwsdk-webxr-skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- click-targetSkill
- iwsdk-ui-panelSkill
- test-allSkill
- test-audioSkill
- test-ecs-coreSkill
- test-environmentSkill
- test-grabSkill
- test-interactionsSkill
- test-levelSkill
- test-locomotionSkill
- test-physicsSkill
- test-uiSkill
- xr-mode-testSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
when the request replaces most of the loop, route to the planner even if files already exist.
- Distinctive: line 37
Read exactly one internal playbook immediately:
- Distinctive: line 40
Do not read project files, call Bash, create a plan, or invoke a specialist between this router and the selected playbook.
- Distinctive: line 42
Never load the other playbook later, including after context compaction.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
IWSDK Dev
Route the current request before inspecting files, planning, invoking a specialist, or editing code. This file is only the entry point; after choosing, load exactly one internal playbook and follow it for the rest of the task.
Route
Choose the iterate path only when the workspace already contains an established experience and the request asks to preserve that product while changing, extending, fixing, tuning, or polishing a bounded part of it.
Choose the planner path for a fresh scaffold, a new experience, a replacement of the current product loop, or a request whose implementation requires defining the product rather than preserving it. A detailed acceptance contract does not turn a greenfield build into an iteration.
Observable workspace state wins over wording:
- starter/demo files in a fresh generated scaffold are not an established user product when the request asks to build a new named experience;
- an existing coherent scene/source/UI implementation that the request calls a baseline, approved experience, or current app is an iteration;
- when the request replaces most of the loop, route to the planner even if files already exist;
- explicit user selection of a child route overrides automatic routing.
Internal handoff
- State the selected route in one sentence.
- Read exactly one internal playbook immediately:
- planner path: references/planner.md
- iterate path: references/iterate.md
- Do not read project files, call Bash, create a plan, or invoke a specialist between this router and the selected playbook.
- Never load the other playbook later, including after context compaction.
iwsdk-dev does not add another implementation phase. The selected playbook owns the work, evidence budget, specialist routing, verification, and stopping rule.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

