Menu
SkillsMP has collected 89 skills from kinqsradiollc/BrainRouter. Open a skill to review its source and details.
Showing 40 of 89 collected skills.
Design skill for user-facing interfaces built on a user's own project — new pages and apps by default, plus audit, redesign, and study of a reference. Enforces structural variety so two different briefs do not come back as colour-swaps of one template. It…
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Design or change backend APIs and service boundaries with explicit contracts, validation, compatibility, idempotency, and failure semantics.
Implement or review backend authentication, authorization, tenancy, secret, and untrusted-input boundaries without trusting caller-supplied identity or scope.
Verify backend changes at contract and integration boundaries with deterministic success, denial, concurrency, retry, migration, and dependency-failure evidence.
Build or change queues, jobs, workers, schedulers, retries, leases, and distributed workflows with bounded concurrency and idempotent recovery.
Change backend domain models, persistence, schemas, and migrations while preserving invariants, tenant scope, rollback safety, and operational compatibility.
Prepare backend services for deployment with explicit configuration, health, observability, capacity, performance, shutdown, and failure-isolation behavior.
Produce a reproducible analysis from a measurable question through data-quality checks, methods, results, and limitations.
Design, implement, and verify decision-useful charts, dashboards, figures, and interactive data stories without distorting the underlying evidence.
Design or audit an experiment with explicit hypotheses, assignment, metrics, power, stopping rules, and reproducible checks.
Treat accessibility and responsive behavior as frontend acceptance criteria through semantic, keyboard, contrast, zoom, and content-stress checks.
Verify frontend behavior in a real browser with interaction, console, responsive, screenshot, and regression evidence.
Build frontend changes from the workspace design artifact and existing component system, preserving product intent instead of generating isolated generic UI.
Draft or revise an academic paper from a reviewed evidence set with a coherent contribution story, explicit section contracts, and claim-evidence alignment.
Adversarially review an academic paper for reject-level defects, material weaknesses, and advisory improvements without silently rewriting it.
Verify that every material citation resolves, supports its adjacent claim, preserves scope, and is not stale or misleading.
Normalize collected observations into auditable claims with support, contradiction, provenance, limitations, and confidence.
Collect bounded, relevant evidence for an approved research question and source strategy without drafting conclusions.
Continue a bounded research task from prior findings, ground it in available project context, and issue only non-duplicate probes for material evidence gaps.
Refine an ambiguous research request into a bounded question, decision target, sub-questions, evidence threshold, and stopping condition.
Review a completed research artifact for question coverage, evidence quality, citation integrity, uncertainty, and decision usefulness.
Design a bounded source and retrieval strategy that matches each sub-question to source types, query modes, freshness, and fallback paths.
Turn a reviewed claim ledger into a provenance-preserving synthesis that exposes agreement, conflict, inference, and gaps.
Turn a diagnosed learning error into the smallest corrective intervention, changed practice, and delayed re-check without shaming or answer leakage.
Diagnose the learner's goal, prior knowledge, misconceptions, constraints, and readiness before choosing instruction.
Evaluate one objective against its declared mastery gate using observable, objective-type evidence and a deterministic advance-or-remediate decision.
Build or revise a prerequisite-aware objective map with observable mastery gates from a diagnosed learner goal and source material.
Gather bounded, authoritative source material for one learning objective with precise provenance, disagreement, and access gaps, without teaching or grading.
Teach and assess programming through bounded hands-on exercises, executable feedback, progressive hints, debugging, tests, and learner reflection.
Schedule and run recall or transfer practice for previously taught objectives, with answer commitment, feedback, and spaced re-checks.
Explain one learning objective using prior knowledge, source-grounded models, worked examples, checks for understanding, and fading support.
Revise writing in ordered passes for purpose, structure, evidence, clarity, voice, and final correctness.
Plan and draft audience-aware long-form content with a clear purpose, evidence map, structure, and voice.
Create and verify repository-grounded API references, developer guides, tutorials, runbooks, and technical explanations with runnable examples and explicit source provenance.
Critique a frozen writing artifact against an explicit rubric for purpose, structure, evidence, consistency, clarity, and voice without editing it.
Records durable architecture decisions and their implementation taskboard. Use when choosing or changing public APIs, data models, security or runtime boundaries, cross-package ownership, orchestration/context contracts, or another expensive-to-reverse design…
Conducts multi-axis code review across correctness, readability, architecture, security, and performance. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when running an agentic review-fix loop until…