Results for “unit-curation”

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.

GPU-accelerated data curation for LLM training, supporting text, image, video, and audio with fuzzy deduplication, quality filtering, semantic deduplication, PII redaction, and NSFW detection.

Apply-now consolidation of a drifted design system into one token/component SSOT. Use after an approved plan-uiux-unification pass, or when "clean up the design system now", "migrate to one button", or "resolve token conflicts". Plan-only burndown → plan-uiux-unification.

Systematically adds unit test coverage to existing source files in any project, tracking progress across sessions via scan, plan, and write modes.

`analysis-agent`/`task-agent`/`review-agent`: use when logic, rules, invariants, branches, edges, or failure paths need isolated tests; skip without a unit-test decision.

Curation-Bench Protocol (skill-grounded)

This skill should be used when the user asks to "improve test coverage", "add unit tests", "TDD", "test this module", "write tests for", "increase coverage", "/ut command", or discusses unit testing strategies. Covers the unit test loop workflow, React Testing Library best practices, query priorities, and coverage improvement strategies.

Data-driven modularity specialist - Masters ScriptableObjects, decoupled systems, and single-responsibility component design for scalable Unity projects

Organiza, compara e seleciona variações de imagens geradas, publicando uma grade de comparação como Artifact para aprovação do time, com critérios de avaliação e registro de decisões.

黑崎一护（少年漫）认知与表达框架（压缩蒸馏）：守护宣言、代打美学、成长型热血 触发：BLEACH 等。虚构；非暴力教唆

Runs an interactive QA session, clarifying user-reported problems, exploring the codebase for context, and filing durable, user-focused GitHub issues.

unified-query-provider

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Finetunes the NV-Generate-CTMR MR-brain diffusion UNet from user-supplied NIfTI training volumes using a wrapper that stages configs and delegates to upstream scripts.

Write effective unit tests with best practices for any project. Use when writing tests, creating test cases, improving test coverage, increasing confidence before release, or when the user mentions testing. Mutation score / assertion theater → test-mutation.

Audits and improves course player UX against LMS best practices, covering layout proportions, progressive disclosure, progress psychology, sidebar hierarchy, video sizing, light/dark harmony, sidebar naming, cohort pacing, and AI integration points.

Configure and use UnoCSS, an instant atomic CSS engine with presets, rules, shortcuts, and integrations for Vite and Nuxt.

Generates comprehensive unit tests with edge cases, error paths, and boundary values. Auto-detects the test framework, scans for untested functions, adopts existing conventions, runs tests, and self-heals failures in up to 3 iterations while measuring coverage.

Preview, validate, and bake bone-rotation edits on AnimSequences with constraint awareness and retarget safety. Use when the user asks to edit/pose/adjust an animation's bones, raise an arm, create a swing/wave/dance/pose, mirror or copy a pose, set joint limits, or learn bone constraints. Load together with animsequence (keyframes) and skeleton (structure).

Full test suite improvement composite — audit health, prune dead tests, validate with mutation testing, capture rationale in ADR. Use after a major feature ship, before tightening coverage gates, or when the suite shows bloat, excessive skips, or slow runtime. Chains test-health → test-cleanup → mutation-test → adr-write.

Determines whether to recommend unilateral laparoscopic adrenalectomy or medical therapy with a mineralocorticoid receptor antagonist for patients with confirmed unilateral PA (aldosterone-producing adenoma or unilateral adrenal hyperplasia). Triggered when discussing treatment options after confirming unilateral PA in a hypertensive patient with hypokalemia or resistant hypertension.

Audits game user experience across HUD clarity, menu navigation, tutorial effectiveness, control responsiveness, camera systems, feedback loops, loading screens, and settings completeness. Detects game engine (Unity UGUI/UI Toolkit, Unreal UMG, Godot Control, web-based), maps all UI screens and input contexts.

UAT Sign-off

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Audits and repairs Markdown link health across a skills repo via a four-tier pipeline (config hardening, intra-repo file-ref fixes, external URL substitutions, residual exclusions) and enforces a Tier 3 substitution guardrail that prevents regressions of previously-passing links; designed for lychee-based GitHub Actions link checkers but generalizes to markdown-link-check and similar tools. Use when the request mentions link audit, dead links, link health, lychee, broken links, link checker, markdown link audit, link-health audit, 404 audit, check-links failing, CI link-check, or 連結健檢, 死鏈, 失效連結, 斷鏈檢查. Part of the AlterLab Academic Skills suite.

Conducts structured post-breach remediation using a lessons learned framework covering root cause remediation, control gap closure, policy updates, training modifications, monitoring enhancements, and regulatory follow-up. Provides a systematic approach to preventing breach recurrence and demonstrating accountability to supervisory authorities. Keywords: post-breach, remediation, lessons learned, root cause, control gap, policy update, training.

Provides a framework for proactive health monitoring and optimization, treating the human body as an asset to be maintained through telemetry, diagnostics, and interventions.

Form UX

Composite skill — diagnose, repair, and validate a test suite end-to-end. Chains test-health (diagnose) → config-drift-detect (gate compatibility) → test-cleanup (prune + add integration tests) → mutation-test (validate survivors) → adr-write (capture decisions) → docs-sync. Use when "the test suite is bad" or you've hit the test-cleanup-bails-at-the-gate failure mode.

Add distributed training support to any PyTorch script with minimal code changes using a unified API for DDP, DeepSpeed, FSDP, and mixed precision.

Create care plans with assessments and interventions. TRIGGERS - Use when user needs help with care-plan related tasks.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Use the pk-doctor skill to run the aggregator health check and resolve

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.