try-works/role-model / .agents/skills/recursive-mode
recursive-mode
UnverifiedRepository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.
references/benchmarks/scientific-calculator-rust/README.md
View on GitHub# Scientific Calculator (Rust/WASM) benchmark
Tier: **xhard**
This packaged benchmark scenario raises the implementation bar with a browser-hosted Rust/WebAssembly scientific calculator. It is meant to be complex enough that recursive planning, audit, and repair loops should have more room to differentiate from a non-recursive baseline.
## Scenario goals
- realistic multi-file Rust + WebAssembly UI work
- local-browser execution from a temp folder
- no external database or service dependencies
- enough scope to require parser or evaluator design, UI state modeling, scientific-function handling, keyboard support, and visible validation evidence
## Included files
- `00-requirements.md` - canonical project requirements used for both benchmark arms
- `scoring-rubric.md` - transparent scoring weights
- `prompt-recursive-off.md` - prompt template for the non-recursive arm
- `prompt-recursive-on.md` - prompt template for the recursive arm
- `starter/` - bootstrap-only starter copied into disposable benchmark repos; it keeps dependency/bootstrap metadata but does not preseed calculator product code. The Rust starter manifest includes an empty `[workspace]` section so nested recursive worktree cargo commands stay rooted in the product worktree.
If a benchmark agent takes browser or validation screenshots, it should store them under `benchmark/screenshots/` so the harness can include them in the final report.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |