Menu
SkillsMP has collected 17 skills from jawsublime-byte/mother-goose. Open a skill to review its source and details.
Showing 17 of 17 collected skills.
Enforce a strict read-only verifier boundary when an independent reviewer must inspect a completed or candidate build without repairing it, inheriting the Builder's reasoning, inspecting future work, or communicating fixes directly to the Builder. Use only…
Route a user-described builder problem to exactly one bundled nursery-rhyme or story-based skill. Use only when the user explicitly invokes Mother Goose and asks for routing. Do not execute every story or silently activate during ordinary work.
Challenge groupthink, authority bias, sycophancy, and yes-man consensus when agents or reviewers may be agreeing because a position is already approved or socially reinforced. Use only when explicitly invoked to test whether dissenting evidence or an…
Calibrate repeated verifier, security, or monitoring warnings so unsupported alarms do not drown out real evidence. Use only when explicitly invoked with a set of current or supplied alerts to assess.
Stop repeating the same operation under unchanged conditions after the same failure signature is reproduced. Use only when explicitly invoked for blind retries; use the user's retry budget or default to three identical reproduced failures.
Protect proven valuable behavior before optimizing, refactoring, simplifying, or replacing the component that produces it. Use only when explicitly invoked around a known-good capability whose value must survive the change.
Leave concise recoverable breadcrumbs through a long or multi-agent build so work can resume from evidence instead of memory. Use only when explicitly invoked to establish or inspect an operational checkpoint trail.
Attribute significant work, evidence, and verification to the actor or source that actually performed or supplied it. Use only when explicitly invoked for multi-agent work, handoffs, assembled artifacts, or ambiguous provenance.
Stop a cascading chain of workarounds and trace it back to the earliest verified cause before adding another fix. Use only when explicitly invoked for a repair sequence where fixes are creating more fixes.
Audit concrete build, test, compatibility, performance, and completion claims against available evidence. Use only when explicitly invoked to separate verified statements from unsupported or contradicted claims.
Bound an automation, agent loop, or batch with explicit scope, budgets, stop conditions, human override, cleanup, and rollback before it runs. Use only when explicitly invoked for autonomous or repeated execution.
Make verified completion outrank raw speed when reviewing rushed work or comparing builders, models, or approaches. Use only when explicitly invoked with a shared finish line or acceptance criteria.
Find the exact median of ordered values or choose a bounded middle configuration that is neither excessive nor insufficient. Use only when explicitly invoked with values or measurable constraints. Never label an arbitrary preference as a mathematical median.
Enforce an hourly work rhythm by recording the start time, checkpointing at sixty elapsed minutes, and requiring a five-minute break before continued work. Use only when explicitly invoked during an active session with access to reliable time.
Stop repeatedly repairing the same failed implementation strategy, preserve the required behavior, and choose a materially different approach. Use when explicitly invoked after a repair has failed the stated budget; default to two reproduced failed attempts…
Apply R.A.T.R. — Ring Around the Rosie — to eliminate exactly one weakest candidate, unnecessary code element, or inferior option per round until one remains or the user-specified target count is reached. Use only when explicitly invoked.
Test a user-authorized build at three escalating resilience levels — straw, sticks, and bricks — before calling it robust. Use only when explicitly invoked with a bounded target and safe test environment.