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/scoring-rubric.md
View on GitHub# Scientific Calculator (Rust/WASM) scoring rubric
Total heuristic score: **145**
## Delivery and reliability
- **20** - `trunk build --release` succeeds
- **20** - `cargo test` succeeds
- **10** - local preview starts successfully and serves HTML
- **5** - `benchmark/agent-log.md` exists with timestamped progress notes; timestamp fallback may earn partial credit when the log form is incomplete
## Feature coverage
- **10** - dual display or expression-tape plus editing controls are implemented
- **15** - expression parsing with operator precedence and parentheses is implemented
- **15** - scientific functions and constants are implemented visibly
- **10** - degree/radian mode affects trig behavior and is visible in the UI
- **10** - memory-register support and reusable history are implemented
- **10** - browser-local persistence is implemented
- **5** - keyboard input support is implemented
- **5** - visible error handling is implemented for invalid or domain-error cases
- **5** - result-formatting logic is present for readable output
- **5** - the calculator UI remains usable and screenshot-friendly at laptop widths
## Notes
- Missing metrics should be marked unavailable, not estimated.
- A failed build, failed tests, or timeout should remain visible in the final report.
- If a criterion is substantively met but the evidence form is incomplete, the benchmark may award partial credit instead of a full pass.
- The rubric is intentionally heuristic; it is meant to compare benchmark arms consistently, not to replace human review.
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 |