Навыки: Продуктивность

Start a Ralph Loop for iterative self-referential development. Use when the user asks to run a ralph loop, start an iter...

Use when setting up pstack native Codex model choices for the current task or an explicitly requested persistent policy,...

Maintain bounded positive-curvature L-BFGS correction memory for large-scale quasi-Newton optimization.

Create and run custom background analysis workers with composable phases. Use when you need automated code analysis, sec...

Customer success skill — support triage, health scoring, churn prediction, onboarding. Use when tasks involve customers,...

Elite AI-powered customer support specialist mastering conversational AI, automated ticketing, sentiment analysis, and o...

Elite AI-powered customer support specialist mastering conversational AI, automated ticketing, sentiment analysis, and o...

Customer-support umbrella skill. Use when Codex should draft support replies, triage issues, summarize tickets, or prepa...

Customise the prd-taskmaster-v2 skill workflow via curated brainstorm questions. AI asks, user answers in plain English,...

Alpha-weighted focal loss that down-weights easy examples to focus training on hard, misclassified pixels in imbalanced...

Replaces global average pooling with Generalized Mean (GeM) pooling, using a learnable or fixed exponent to emphasize hi...

Grid search binarization thresholds on validation predictions to find the cutoff that maximizes mean IoU

Uses PyTorch AMP autocast and GradScaler for FP16 training, halving memory usage and speeding up training on modern GPUs...

Assign an unknown/novel class when all nearest-neighbor distances exceed a tuned cutoff threshold for open-set recogniti...

Uses pack_padded_sequence to exclude padding tokens from cross-entropy loss in variable-length sequence generation.

Encodes binary segmentation masks into compressed RLE format for efficient storage and submission.

Resample a 3D medical volume to a fixed depth N (e.g. 32) and feed the N slices as input *channels* to a 2D CNN with `in...

Assembles N extracted tiles into a sqrt(N) x sqrt(N) mosaic image for single-forward-pass CNN inference on whole slide i...

Tversky loss with independent alpha/beta constants to separately penalize false positives and false negatives in imbalan...

Extracts calibrated yes/no probabilities from a VQA model by masking all logits except yes/no token variants and renorma...

BCE loss with per-class asymmetric positive/negative weights to match competition metrics or handle class imbalance in m...

Use this skill when the user asks to "set up parsing", "create parsing rule", "extract fields from logs", "regex extract...

Use to design the process that gets a revenue signal out of support and to the account owner without turning agents into...

MUST USE for external, current, real-time, or public-web lookups — latest releases/versions, news, prices, docs, status,...

Executes one PRD task end-to-end using a provided task file, PRD directory, tracking file paths, and auto-commit mode. U...

Design cyber mission support plans for defensive and authorized offensive operations. Use when coordinating mission obje...

Render `.claude/canvas/cycle-history.yml` as a Gantt chart + outcome distribution pie (or ascii / json). Read-only. Cons...

Use when creating a complete editable medical academic PowerPoint deck from papers, PDFs, Figures, screenshots, or suppo...

Use when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropr...

Compute and audit D4RL normalized returns from raw, random-baseline, and expert-reference scores.

Parses complex problems into DAG (Directed Acyclic Graph) execution structures. Decomposes tasks into nodes with depende...

The intelligence layer of Jury-rig. Decomposes natural language tasks into proposed Hierarchical Task DAGs (HTDAGs), mat...

Specifies bounded DAG execution contracts and evaluates executor receipts for dispatch, cancellation, joins, and effect...

Executes DAG workflows with parallel wave processing, agent spawning, context isolation, permission enforcement, and ful...

Create today's daily note in the Obsidian vault.

Define functions using standard schema workflow skill. Use this skill when the user needs Documentation and capabilities...

Use this skill when creating today's daily note in the Meta-Vault (03-daily/YYYY-MM-DD.md) with valid vaultFrontmatterSc...

Compose a morning briefing for the user by pulling today's calendar, open tasks, and relevant memory, then delivering a...

Create or review daily briefing deliverables with traceable assumptions, decision criteria, ownership, and risk controls...

Generate daily briefing with priorities, progress, and alerts. Used as part of session-start or when user asks "what's o...

Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a struc...

Generate a clean morning brief in Claude Code — pulls today's priorities, unposted content, and weather from your vault.

A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries afte...

Daily journal management for the my-vault Obsidian vault. Use for morning routines, daily reviews, quick journal updates...

Generate structured daily operation logs following standardized format for memory persistence and progress tracking.

Automated news aggregation and reporting agent.

Manages daily notes with M-D-YYYY format (e.g., 1-1-2026.md). Use when the user asks to view recent notes, create daily...

Review today's HuggingFace daily papers, pick the most relevant one, write a LaTeX summary report with follow-up researc...