Loading...
Loading...
Found 466 Skills
Diagnose repeated command failures, stale build caches, branch drift, or contradictory evidence before attempting further code edits. Use when commands fail repeatedly, tests stay red after attempted fixes, build output contradicts source code, or the execution path is confused — even if the user does not explicitly say "fable-recover" (e.g. "still failing", "why did this fail again", "stuck in a failure loop", "diagnose this error"). Do NOT use for routine first-time test failures in fresh TDD (use fable-tdd).
Perform a read-only audit of an existing product interface, prove UI findings from governing design evidence and runtime paths, and prepare implementation-ready recommendations or plans. Use for review and design-system drift analysis; do not use when the user asks to implement fixes directly.
Evaluate changesets, task breakdowns, or code diffs for scope bloat, architectural drift, and regression risks.
A marketing site and its product may differ in density and scale but share one token layer. Use when the two drift apart, share components or need a single token owner.
Use when rigging a character, creature or prop in Maya: "rig this character", placing or orienting joints, Orient Joint doing nothing, IK/FK switch and matching, pole vector flips or elbow drift, space switching, foot roll, spline IK spine, offsetParentMatrix, blendMatrix or matrix rigging, controls and lockdown for animators, Quick Rig, HumanIK, AdvancedSkeleton or mGear, a game skeleton for Unreal or Unity, or a slow rig (parallel evaluation, profiling, GPU Override not kicking in).
Build Celigo syncs (Celigo Data Ingestion) -- managed pipelines that replicate many tables from a source application into a data warehouse, with a historical backfill, incremental runs and schema-drift handling. Covers sync versus flow, the sync integration, datasets, destinations, the enable and license gates, runs and resyncs, and sync jobs, errors and events. Use when replicating application data into Snowflake, Google BigQuery, Microsoft SQL Server or NetSuite Analytics Warehouse, or when building, running or troubleshooting a sync.
Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, replacing, or archiving them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, or when pattern docs no longer reflect current code.
Enforces a pure-Dart value-object core that stores every quantity canonically — money as integer minor units keyed to each currency's real ISO-4217 exponent (never *100), physical amounts as SI whole units, timestamps as UTC — and converts only at the presentation edge; forbids double/num money, cross-currency arithmetic, and defaulting an unknown currency to two decimals; routes every division of money through one largest-remainder allocate() primitive so parts always sum to the whole to the exact minor unit; derives totals instead of storing them, links entities by stable id, and injects a Clock instead of DateTime.now. Use when defining or changing Money, Currency, or a unit value object; parsing or formatting an amount; splitting, prorating, discounting, tax/tip, or distributing money; adding a currency or FX rate; converting quantities; or fixing float-money, hardcoded-100, cross-currency, off-by-a-cent, or stored-total-drift bugs.
Enforces a lean GitHub Actions Flutter CI where every gate maps to one named release-blocking contract — pinned runner + subosito/flutter-action@v2 toolchain, dart format --set-exit-if-changed, flutter analyze --fatal-infos, build_runner and drift schema freshness (git diff --exit-code), flutter test --test-randomize-ordering-seed random, static import/banned-string greps that catch what runtime can't, coverage-as-report-never-a-gate with the upward-lie fixed, verify-never-bless goldens (no --update-goldens in CI), and an honest statement of what CI cannot prove (audio, real fonts, on-device behaviour). Use when editing .github/workflows/*.yml, adding or removing a job or step, wiring a codegen/schema/format/analyze/coverage gate, writing a grep-based policy test or gate script under test/policy or tool/, pinning action versions, or claiming CI proves something it can't.
Enforces test doctrine where shape follows code not the pyramid: pushes logic into Flutter-free packages tested with pure package:test and an injected Clock; asserts invariants with seeded fuzz tests against an independent oracle plus round-trip and rounding goldens; prefers bare-implements fakes over mocktail for code you own; tests the data layer against a real NativeDatabase.memory Drift engine, never a mocked DAO; drives Notifiers headlessly with ProviderContainer overrides; guards one end-to-end acceptance gate and a runtime invariant tripwire; floors coverage on unrecoverable-bug files not a global percentage; and fixes the coverage-lies-upward gap. Use when writing tests under test/ or integration_test/, choosing unit vs widget vs integration, adding a fuzz or round-trip property, wiring a fake or ProviderContainer test, gating coverage, or triaging a flaky-suite failure.
Implement one accepted, bounded work card with immediate local verification, invariant preservation, and zero scope drift. Use when executing a planned work card, applying a well-defined code change, implementing an isolated function, or performing targeted single-scope edits — even if the user does not explicitly say "fable-execute" (e.g. "implement this card", "write the code for this step", "apply the agreed changes", "build this component"). Do NOT use when new architectural decisions are required (use fable-plan) or when tests are repeatedly failing (use fable-recover).
Low-level agentic design patterns and cognitive reflexes across Depth, Breadth, Coil, and Mesh. Turns senior engineering wisdom into reflexes that remove bloat, preserve truth, prevent drift, and compound learning (re0, readchk, autobahn, ssotize, detool, feynman, debloat, sip, hate, macrothink, prism). Use when refactoring complex systems, stripping AI slop, rewriting drifted artifacts from clean v0, consolidating truth into single sources, or evaluating architectural decisions against contrarian counter-arguments.