Playground Rebuild
Use after editing the playground source or code reachable from cmd/agnostic-ai-wasm
mkdir -p ~/.claude/skills/playground-rebuild && curl -fsSL 'https://raw.githubusercontent.com/Chemaclass/agnostic-ai/main/.agnostic-ai/skills/playground-rebuild/SKILL.md' -o ~/.claude/skills/playground-rebuild/SKILL.md
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Playground Rebuild when an AI agent needs a reusable SKILL.md workflow for this job: Use after editing the playground source or code reachable from cmd/agnostic-ai-wasm
When not to use it
Skip Playground Rebuild when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/playground-rebuild && curl -fsSL 'https://raw.githubusercontent.com/Chemaclass/agnostic-ai/main/.agnostic-ai/skills/playground-rebuild/SKILL.md' -o ~/.claude/skills/playground-rebuild/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/playground-rebuild/SKILL.md. For a shared project, commit the folder at .claude/skills/playground-rebuild/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the Playground Rebuild skill for this task: Use Playground Rebuild when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
66/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 67/100
- Practical detail
- 68/100
- Source evidence
- 55/100
- Source signals
- 72/100
Model compatibility evidence
- claudeuntested
No model-specific signal or recorded compatibility test was found.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiuntested
No model-specific signal or recorded compatibility test was found.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# playground-rebuild
The hosted playground at https://agnostic-ai.org/playground/ runs the same code as the CLI, compiled to WebAssembly via `cmd/agnostic-ai-wasm`.
## Build
``` make playground-build ```
Writes `docs/playground/agnostic-ai.wasm` and copies `wasm_exec.js`, the helper script from the Go toolchain. Both are gitignored; CI regenerates them on push to `main`.
## Serve locally
``` make playground-serve ```
Builds the Zola site and WebAssembly bundle, assembles the same files that GitHub Pages publishes, then serves `_site/` with `python3 -m http.server 8080`. Open http://127.0.0.1:8080/playground/.
`file://` does not work because browsers refuse `WebAssembly.instantiateStreaming` on local files.
## After edits
For frontend or Go source changes, stop the server started for this task and rerun `make playground-serve`, then refresh the browser. This rebuilds and copies the bundle into `_site/playground/`. `make playground-build` alone updates `docs/playground/`, leaving the served copy stale.
Exercise the changed spec and target in the browser and inspect its generated output or error. Record the scenario and result. Select any additional checks from repository-root `docs/internal/contributing.md`, section "Choose checks for your change".
## Clean
``` make playground-clean ```
Removes the generated `.wasm` and `wasm_exec.js`.
Intended uses
- Use Playground Rebuild when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.