Menu
SkillsMP has collected 21 skills from jawsublime-byte/simon-says. Open a skill to review its source and details.
Showing 21 of 21 collected skills.
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,…
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…
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…
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…
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…
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,…
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,…
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…
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…
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.
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…
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.
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.
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.
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,…
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…
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…
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.
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.
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.
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.