Quirkybrain
UserA reusable, Markdown-first multi-agent software engineering framework for Claude Code with adaptive workflows, artifact-driven orchestration, quality gates, traceability, and incremental development.
Categories
Indexed Skills (20)
adaptive-testing
Select, implement, and execute the smallest sufficient test scope for a change based on affected layer, risk, Contracts, security, and performance. Use after code changes, for test planning, or when existing evidence must be refreshed.
architecture-decision
Evaluate significant technology or architecture alternatives and record an Architecture Decision Record. Use when a choice affects system structure, Contracts, data, security, deployment, compatibility, cost, or long-term evolution.
artifact-validation
Validate an existing or newly produced Artifact for completeness, consistency, correctness, freshness, dependency compatibility, and target fitness. Use before reuse, handoff, downstream consumption, or a Gate decision.
change-impact
Propagate an upstream Artifact, Contract, decision, assumption, dependency, or code change through downstream dependencies, mark evidence stale or unverified, and define revalidation. Use whenever a validated basis changes.
clarification-gate
Decide whether unresolved ambiguity, conflict, intent, or authority requires a user decision and formulate bounded options with tradeoffs. Use before making material product, architecture, technology, data, security, deployment, cost, or high-impact choices.
code-review
Select and perform risk-appropriate Quick, Code, Architecture, Security, Performance, or Integration Review on a concrete revision. Use after implementation or integration to assess whether the solution is reasonable, maintainable, compliant, and safe.
component-planning
Decompose a validated system design into System, Subsystem, Module, Component, and Task graphs with Contracts, dependencies, integration points, parallel work, Gates, and milestones. Use before multi-component implementation or integration planning.
failure-diagnosis
Observe, reproduce, classify, and determine the root cause and correct repair layer for a build, test, regression, integration, or environment failure. Use before patching when the cause is unknown or crosses layers.
failure-escalation
Stop repeated local patching and move unresolved failure to root-cause review, higher-level analysis, or stage rollback. Use after repeated failed repair attempts, cross-layer evidence, exhausted diagnosis budget, or widening regressions.
framework-checkpoint
Persist a recoverable snapshot of project Stage, target, workflow, Artifacts, Components, decisions, assumptions, questions, risks, current path, evidence, and next action. Use at major results, pauses, blockers, escalations, integration, or session end.
framework-resume
Safely resume framework work by reading the latest Checkpoint, validating repository and Artifact state, detecting drift, revalidating affected work, and recomputing the Minimum Necessary Path. Use after session restart, context loss, pause, or handoff.
gap-analysis
Compare validated existing Artifacts with a target Artifact or Target Stage and find missing, partial, unverified, stale, invalid, or incompatible dependencies. Use after Intake/validation and before computing the Minimum Necessary Path.
implement-component
Implement or modify one bounded Component using its validated Contract and constraints, then build, test, review as required, and pass the Component Quality Gate before STABLE. Use for feature work, bug fixes, and refactors with an explicit scope.
integration-gate
Verify that individually STABLE Components remain correct when combined through Contract validation, integration, integration tests, and regression. Use before promoting any combined unit as stable.
minimum-path
Convert a validated Gap Set and Artifact dependencies into the Minimum Necessary Path to a target. Use to prune satisfied work, order required nodes, expose blockers, place Gates, and avoid running the full lifecycle automatically.
project-intake
Discover, inspect, classify, and inventory existing project assets and initial engineering state. Use at project startup, after major input changes, when entering an unfamiliar repository, or before planning from existing work.
reverse-engineering
Derive software structure, Contracts, architecture, UML/models, and cautiously inferred requirements from existing code, tests, schemas, configuration, and runtime evidence. Use when documentation is missing, stale, or must be reconciled with implementation.
stage-gate
Evaluate whether a major lifecycle Stage has complete valid Artifacts, passed required validation and Definition of Done, and reached the configured Target Stage. Use at each relevant Stage boundary before continuing or pausing.
traceability
Create, validate, and update bidirectional links from Requirements through design, architecture, APIs/Components, tasks, code, and tests. Use after Artifact changes, planning, implementation, testing, verification, or Change Impact.
workflow-assessment
Assess project and task complexity, risk, impact, size, maintainability, coordination, existing assets, and target stage to select LIGHTWEIGHT, STANDARD, or STRICT. Use for AUTO mode, new tasks, scope changes, or risk-driven escalation and de-escalation.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.