Menu
O SkillsMP coletou 21 skills de jawsublime-byte/simon-says. Abra uma skill para revisar a origem e os detalhes.
Mostrando 21 de 21 skills coletadas.
Test how a trusted program ages under realistic accumulated use at 3 months, 6 months, 1 year, 5 years, and beyond. Use only when explicitly invoked near build completion to expose storage growth, stale state, latency creep, indexing cost, log or cache bloat,…
Idioma do texto original: inglês
Inspect an in-progress build for demonstrably required pieces that were never named but are necessary for the user's approved final result. Use only when explicitly invoked to find empty slots before integration or testing makes the build fail, while…
Idioma do texto original: inglês
Govern repeated builder drift with evidence-based yellow cards, a three-packet red-card benching period, reinstatement on probation, and expulsion from the current build after repeated post-return violations. Use only when explicitly invoked for multi-builder…
Idioma do texto original: inglês
Run an evidence-grounded adversarial brainstorming session when the user's unconventional build idea conflicts with the model's learned defaults or standard practice. Use only when explicitly invoked to keep both positions intact, challenge assumptions…
Idioma do texto original: inglês
Execute an identified build order exactly as written or explicitly route a builder problem to one bundled playground skill. Use only when the user invokes Simon Says and supplies an authoritative order or asks Simon Says to route a task. Do not activate for…
Idioma do texto original: inglês
Investigate resource growth, retained state, data or information loss, dropped records, missing requirements, lossy transformations, unbounded accumulation, or other accounting failures across a bounded system or workflow. Use when inputs, resources, records,…
Idioma do texto original: inglês
Evaluate competing, sequential, or evolving paths toward a defined goal and classify which paths advance progress, cause regression, contain useful partial progress, or remain unresolved. Use for workflows, architectures, implementations, product evolution,…
Idioma do texto original: inglês
Use when a Rust implementation, review, repair, or Cargo decision requires authoritative syntax, language, edition, ownership, safety, workspace, crate, or build-system guidance from the approved local manuals, including when a Simon Says packet explicitly…
Idioma do texto original: inglês
Create a visible, disposable UI wireframe or prototype, review it against explicit requirements, and erase the temporary draft completely before drawing a fresh alternative when it fails. Use only when the user explicitly invokes Etch A Sketch for interface…
Idioma do texto original: inglês
Run bounded black-box or blind tests to find failures outside the expected end path without first relying on implementation details. Use only when the user explicitly invokes Battleship for software they own or are authorized to test.
Idioma do texto original: inglês
Coordinate a bounded volley of sequential and concurrent defensive tests to reproduce race, contention, ordering, retry, load, or multi-input failures. Use only when the user explicitly invokes Dodgeball for an authorized non-production target or approved…
Idioma do texto original: inglês
Determine where a new process, branch, validation, or handoff can enter an existing workflow without breaking cadence, ordering, ownership, retries, or completion. Use only when the user explicitly invokes Double Dutch.
Idioma do texto original: inglês
Locate an exact line, symbol, file, string, configuration value, call path, or behavior in a codebase or supplied artifacts. Use only when the user explicitly invokes Go Fish. Search and report; do not edit unless separately requested.
Idioma do texto original: inglês
Classify inputs as allowed, rejected, or quarantined by looking beneath filenames, labels, or surface appearance at provenance, structure, content indicators, and behavior. Use only when the user explicitly invokes Heads Up Seven Up for defensive input review.
Idioma do texto original: inglês
Search for hidden defects, silent failures, conflicting configuration, unreachable code, syntax traps, overlooked edge cases, or causes outside the obvious error location. Use only when the user explicitly invokes Hide and Seek for a bounded codebase,…
Idioma do texto original: inglês
Apply K.I.S.S. — Keep It Simple, Stupid — to code, explanations, plans, summaries, documents, messages, and conversation. Use when the user explicitly requests the simplest complete solution, plain language, fewer tokens, no filler, or removal of unnecessary…
Idioma do texto original: inglês
Apply M.I.S.S. — Make It Super Smart — when the user explicitly requests deeper analysis, stronger reasoning, edge-case coverage, or the most robust evidence-based answer. Increase analytical depth without adding unrequested features, scope, prose, or…
Idioma do texto original: inglês
Check whether the user's directive, the current plan, and the work performed remain synchronized. Use only when the user explicitly invokes Patty Cake or asks for an alignment checkpoint. Stop work on any material drift instead of inferring a correction.
Idioma do texto original: inglês
Give the agent one bounded opportunity to propose a single optional improvement beyond completed requested work. Use only when the user explicitly invokes Recess. Never implement the proposal without separate user approval.
Idioma do texto original: inglês
Challenge one user-authorized validation, authentication, serialization, permission, or trust boundary with controlled adversarial tests. Use only when the user explicitly invokes Red Rover and identifies a system they own or are authorized to assess.
Idioma do texto original: inglês
Create or specify a disposable sandbox for testing a function, migration, dependency, workflow, or risky method without affecting production or irreplaceable data. Use only when the user explicitly invokes Sand Castles.
Idioma do texto original: inglês