36 skills · sorted by relevance
Use when explaining branch predictors, mispredict penalties, speculative execution, Spectre or Meltdown mitigations, or branchless code. Not for pipeline stage theory: use cpu-pipelines-and-hazards.
The English summary is being prepared. Showing the original description.
Use when a task needs the judgment of a Crematory Operator — running a cremation cycle safely, verifying chain-of-custody and identification before charging a retort, handling implanted-device or oversized-decedent hazards, or documenting and troubleshooting an incident during processing.
The English summary is being prepared. Showing the original description.
Deep codebase cleanup — kills dead code, fixes all lint/format warnings, removes orphaned files, cleans stale TODOs, strips security hazards, tightens TypeScript strict mode, and organizes imports. Triggers: clean up, dead code, unused imports, lint, technical debt cleanup.
The English summary is being prepared. Showing the original description.
Analyze disaster prediction and early warning systems — model accuracy for flood, earthquake, wildfire, hurricane, and tsunami hazards, data pipeline reliability from sensor networks and satellite feeds, alert distribution latency and channel coverage.
The English summary is being prepared. Showing the original description.
Review code changes for correctness defects, regressions, security risks, data-integrity problems, concurrency hazards, and missing meaningful tests. Use for pull requests, branches, commits, patches, or working-tree reviews; do not use for implementation unless the user separately requests fixes.
The English summary is being prepared. Showing the original description.
Use when reviewing a migration diff or schema change for scale hazards — indexes, unsafe migrations, unbounded growth, N+1. Triggers on 'review this migration', 'will this scale'.
The English summary is being prepared. Showing the original description.
GStack careful mode for risky work that needs a conservative pass, hazards, safeguards, and explicit confirmation points before execution.
The English summary is being prepared. Showing the original description.
The catalog of every config-as-data surface in nuxt-crouton — which file controls what, who actually reads it, its drift hazards, and how to change it safely. Use when asking "where is X configured", "who reads this file", "what happens if I edit harness.config.mjs / routing.json / digests.yml / labels.yml / a deploy.config.json / an e2e.manifest.json", when a setting change had no effect (silent no-op), when adding a new config surface, or when a gen-*.mjs --check fails. Trigger phrases: "where do I configure", "what reads this config", "config drift", "the setting didn't do anything", "stale generated doc", "add a new config-as-data surface".
The English summary is being prepared. Showing the original description.
Detects Vitest test-isolation hazards: unrestored vi.spyOn/vi.mock without afterEach cleanup or restoreMocks config, un-awaited resolves/rejects assertions, and shared mutable module state across tests.
The English summary is being prepared. Showing the original description.
Transfers gene annotations between genome assemblies via coordinate liftover (UCSC liftOver, CrossMap for same-species version updates) or feature/sequence projection (Liftoff for same/close species, miniprot for protein-level cross-species, TOGA/GeMoMa/CAT for distant clades). Covers the coordinate-vs-projection decision by divergence, why a successful lift is not biological confirmation, reference bias, the silent-dropping of unmapped features, build/PAR/MHC/inversion hazards, and transfer-vs-de-novo validation. Use when annotating a new assembly of a species with an existing reference, harmonizing coordinates across builds, or mapping annotations across related species.
The English summary is being prepared. Showing the original description.
Transfers gene annotations between genome assemblies via coordinate liftover (UCSC liftOver, CrossMap for same-species version updates) or feature/sequence projection (Liftoff for same/close species, miniprot for protein-level cross-species, TOGA/GeMoMa/CAT for distant clades). Covers the coordinate-vs-projection decision by divergence, why a successful lift is not biological confirmation, reference bias, the silent-dropping of unmapped features, build/PAR/MHC/inversion hazards, and transfer-vs-de-novo validation. Use when annotating a new assembly of a species with an existing reference, harmonizing coordinates across builds, or mapping annotations across related species.
The English summary is being prepared. Showing the original description.
Safety-case design for always-on agents with episodic memory. Covers data hygiene, privacy and security risk surfaces, cost controls, scope, user dependency concerns, retention, incident containment, and responsible deployment evidence. It identifies hazards and asks for named controls, tests, owners, and residual uncertainty; it does not provide legal, clinical, youth-safety, or jurisdictional determinations. Activate on: "agent safety", "always-on agent privacy", "agent cost control", "persistent agent risks", "AI companion safety", "agent data hygiene", "runaway agent costs", "parasocial AI risk", "/always-on-agent-safety". NOT for: architecture design (use always-on-agent-architecture), input design (use always-on-agent-inputs), application brainstorming (use always-on-agent-applications), healthcare compliance specifically (use hipaa-compliance).
The English summary is being prepared. Showing the original description.