33 skills found
Design CCF experiment protocols and evidence schemas: datasets, baselines, metrics, ablations, and result-table contents. Use for 设计实验, 消融, benchmark planning, and 结果表证据结构. Preserve real values. Table styling/rendering belongs to ccf-visual-composer; broad retrieval belongs to ccf-literature-searcher.
Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use when analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards. Also use when the user mentions "social media audit," "engagement rate," or "which platform performs best."
Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.
Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.
Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo.
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Analyze compensation — benchmarking, band placement, and equity modeling. Trigger with "what should we pay a [role]", "is this offer competitive", "model this equity grant", or when uploading comp data to find outliers and retention risks.
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side
Analyze competitors systematically. Compare products, features, pricing, positioning, and market strategies. Generate comprehensive competitive intelligence reports.
