vital-sign-extraction
Estimate heart rate (HR) and breathing rate (BR) in bpm from a cleaned 1-D physiological time series such as radar phase, WiFi CSI amplitude, PPG, or a chest-motion signal. Use when Claude needs to choose HR/BR bandpass edges, pick a peak frequency from a noisy band, reject the HR second harmonic that often dominates the fundamental, handle respiration-harmonic leakage into the HR band on slow breathers, or flag low-confidence estimates. Not for arrhythmia / beat-to-beat analysis, multi-subject source separation, or rapidly non-stationary rates.
ada-plan-view-accessibility
Use when checking simplified ADA-derived plan-view bathroom accessibility constraints such as turning space, door clear width, toilet centerline, grab bars, and lavatory knee/toe clearance.
architectural-dxf-extraction
Use when extracting plan-view architectural geometry from DXF files with semantic CAD layers, especially when outputs must normalize rooms, doors, fixtures, clearances, and grab bars into machine-checkable JSON.
attention-variants-from-papers
Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom attention into an existing transformer stack.
attitude-controller-planner
Use this skill when implementing the inner control loop for a quadrotor — attitude (roll/pitch/yaw) PID control and attitude planning (converting desired acceleration to desired Euler angles). Covers gain layout, integral reset pattern, and the attitude planner inverse kinematics.
cache-policy-comparison
Compare and implement eviction policies (LRU, LFU, FIFO, S3FIFO, ARC) for bounded-capacity caches. Use when choosing or implementing an eviction policy for a buffer pool, page cache, CDN edge, or LLM KV cache, or when writing a replay simulator that supports multiple policies. Clarifies recency vs frequency semantics, queue topology, saturating counters, ghost buffers, and the second-chance rule that distinguishes modern FIFO-family policies from classic LRU.
comp3-packed-decimal
>-
contract-playbook-review
Methodology for clause-by-clause review of a contract against a structured deviation policy ("playbook"). Covers how to walk a playbook, locate the matching provision in the contract, apply rule types (max-value, must-be-present, must-be-absent, acceptable-set, must-have-feature), classify the result (ok / risk / reject), choose the prescribed action, and ground each finding in a verbatim excerpt. Use whenever reviewing any contract — NDA, MSA, vendor DD questionnaire, lease, DPA — against a structured rules-based playbook.
d3-visualization
Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.
ebcdic-overpunch-decoding
>-
ffmpeg-audio-processing
Extract, normalize, mix, and process audio tracks - audio manipulation and analysis
ffmpeg-format-conversion
Convert media files between formats - video containers, audio formats, and codec transcoding
ffmpeg-media-info
Analyze media file properties - duration, resolution, bitrate, codecs, and stream information
ffmpeg-video-filters
Apply video filters - scale, crop, watermark, speed, blur, and visual effects
flight-plan-parser
Use this skill when converting natural language flight commands into waypoints and timing for a drone simulator. Covers parsing commands like "Take off to X m height in Y seconds", "Hover at X m height for Y seconds", "Fly from (x,y,z) to (x',y',z') in T seconds", and "Land from X m height in Y seconds" into structured (4×n) waypoint arrays and segment mode lists.
fragmentation-aware-packing
Choose placements that preserve useful residual capacity. Use for bin packing, GPU sharing, accelerator placement, and multi-resource scheduling where stranded capacity hurts future fit.
geometric-layout-repair
Use when producing a minimally changed repaired 2D layout in JSON from extracted architectural geometry and rule-based clearance constraints.
geospatial-routing-data
Geospatial routing data handling for depot and station coordinates, route node IDs, internal index mappings, great-circle distance matrices, and route-distance reconstruction. Use when optimization or reporting tasks involve latitude/longitude, station IDs, depots, distance metrics, vehicle routes, or validating travel distance from reported paths.
gl-posting-codes
>-
gnucobol-mainframe-batch
>-
grpo
Reference for the GRPO (Group Relative Policy Optimization) algorithm. Use when implementing, debugging, or verifying a GRPO training pipeline — covers the mathematical formulation (group-relative advantages, clipped surrogate loss, KL penalty), the training loop (generate → score → advantage → loss), log-probability computation, advantage estimation, and relationship to PPO/REINFORCE.
image-editing
Comprehensive command-line tools for modifying and manipulating images, such as resize, blur, crop, flip, and many more.
logistics-rules-to-optimization
Translate logistics and operations rules into optimization variables and constraints. Use when an operations problem describes vehicles, routes, depots, pickups, dropoffs, inventory, capacity, assignments, time windows, service targets, penalties, resource limits, or other business rules that need to become an optimization model.
milp-solver-workflow
Use for formulating, solving, debugging, and validating mixed-integer linear optimization models with open-source solvers, including variable indexing, sparse constraints, linearized costs, solver limits, MIP gaps, incumbent extraction, numerical tolerances, and deterministic output reporting.
mip-solver-and-solution-audit
Operational workflow for hard integer-programming optimization tasks: selecting an installed solver, preserving solver/incumbent certificates, extracting feasible schedules, recomputing metrics from final outputs, and writing consistent reports. Use when a task requires a MIP, solver status, objective value, bound, gap, formulation write-up, or benchmark output files.
motor-model-dynamics
Use this skill when simulating quadrotor physical dynamics — mapping desired thrust/moments to individual motor RPMs via a propeller allocation matrix, applying first-order motor lag, and integrating the nonlinear equations of motion (translational and rotational) using RK45.
multi-resource-allocation-validation
Validate and repair proposed resource allocations by replaying them against temporary capacity. Use when actions consume several resource dimensions such as CPU, memory, GPUs, or accelerators.
nda-clause-taxonomy
Reference for the standard clauses found in commercial non-disclosure agreements (mutual and one-way) — what each clause does, the surface forms it appears in, and how to recognise it in unfamiliar drafting. Use when reviewing, comparing, or extracting provisions from any confidentiality / NDA / mutual NDA / standstill-and-confidentiality agreement.
object-counter
Count occurrences of an object in the image using computer vision algorithm.
online-resource-scheduling
Design deterministic online scheduling policies from current observations. Use when assigning arriving work to limited resources without seeing future requests.
ordered-window-sequencing-mip
Permutation and sequencing integer-programming formulations with ordered local-window variables, prefix/suffix continuity, and overlap penalties. Use when assigning exams, jobs, tasks, visits, blocks, or resources to ordered positions and costs depend on adjacent pairs, sliding triples, n-grams, short-horizon pressure, or overlapping local patterns.
ortools-pickup-delivery-routing
Model OR-Tools paired pickup-and-delivery routing problems, including PDPTW, dial-a-ride, paratransit, patient transport, and courier jobs with same-vehicle pairing, precedence, capacity, optional connected service, rider time windows, and vehicle shifts.
ortools-routing-modeling
Build OR-Tools RoutingModel vehicle-routing models with transit matrices, dimensions, capacity constraints, time windows, optional visits, invalid-arc handling, search parameters, and route extraction.
paired-reversal-cancellation
>-
plot-quadrotor
Use this skill when visualising drone simulation results. Produces three matplotlib figures — desired vs actual trajectories, instantaneous error, and cumulative absolute error — for all 5 state groups (position, orientation, velocity, angular velocity, acceleration). Saves figures to a plots/ directory automatically.
position-controller-trajectory-planner
Use this skill when implementing the outer control loop for a quadrotor — position PID control (position/velocity error → thrust and desired acceleration) and trajectory planning from flight-plan waypoints (takeoff, hover, fly, land segments → smooth 15-row state matrix).
prefix-cache-replay
Replay an LLM inference request trace (Mooncake / vLLM / SGLang hash_ids format) against a block-level KV prefix cache and compute hit statistics. Use when given a request trace plus cache configuration and asked for hit rate, hit tokens, or final cache contents. Covers the longest-contiguous-prefix semantics that distinguishes KV prefix caching from full-prompt prompt caching, the policy-specific residency and eviction rules (LRU, LFU, S3FIFO), and the partial-last-block accounting rule.
radar-signal-processing
Parse raw radar I/Q captures (CW or FMCW mmWave) and produce a cleaned 1-D slow-time signal ready for motion or vital-signs analysis. Use when Claude needs to read interleaved I/Q binary, do a Range FFT on FMCW chirps, remove static clutter, pick a subject range bin, extract phase with unwrapping, or debug why a radar pipeline is returning garbage. Not for pulse/UWB range gating, MIMO beamforming, or Doppler-only gesture radar.
radar-vital-signs
End-to-end pipeline for extracting heart rate (HR) and breathing rate (BR) from raw short-range radar I/Q captures — both continuous-wave (CW, 24 GHz clinical boards) and FMCW mmWave (60/77 GHz, TI IWR/AWR). Use when Claude needs to parse interleaved I/Q binary, do a Range FFT on FMCW chirps, remove static clutter, pick a subject range bin, extract phase with unwrapping, design HR/BR bandpass filters, pick a peak frequency via PSD, reject the HR second harmonic that often dominates the fundamental, or handle respiration-harmonic leakage on slow breathers. Not for pulse/UWB range gating, MIMO beamforming, Doppler-only gesture radar, arrhythmia detection, or multi-subject source separation.
reflow-machine-maintenance-guidance
This skill should be considered when you need to answer reflow machine maintenance questions or provide detailed guidance based on thermocouple data, MES data or defect data and reflow technical handbooks. This skill covers how to obtain important concepts, calculations, definitions, thresholds, and others from the handbook and how to do cross validations between handbook and datasets.
rl-post-training
Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). Use proactively when debugging a training pipeline that shows no improvement, loss anomalies, reward stagnation, NaN gradients, or other unexpected behavior during reinforcement learning fine-tuning. Work through all pipeline stages — reward, advantages, log-probs, loss, generation/decoding — before concluding the diagnosis is complete; stopping after one or two fixes is a common failure mode. Covers log-probability math, advantage estimation, numerical stability, reward processing, and generation/decoding pipeline issues.
routing-subtour-elimination
Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables. Use when route-continuity constraints may permit disconnected cycles and the model needs MTZ constraints, flow-based connectivity constraints, DFJ subset cuts, or lazy/iterative subtour cuts.
scip-opt
SCIP optimization with PySCIPOpt. Use when facing an optimization problem with an objective, hard constraints, soft penalties, integer decisions, routing, assignment, scheduling, allocation, packing, capacity, inventory, or service-level rules. Prefer modeling and solving the problem with PySCIPOpt when it is available.
stepinfo-3d
Use this skill when computing 3D step-response performance metrics for point-to-point drone flight — rise time, settling time, percent overshoot, and steady-state error based on Euclidean distance to the final target. Use instead of 1D stepinfo for any flight where all three position axes move simultaneously.
task-creator
SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the user wants to create a new SkillsBench task, scaffold a task from an existing workflow (notebook, Excel workbook, document, dataset), convert a prompt or a benchmark item into a SkillsBench task, write skills for a task, or prepare a SkillsBench PR. Pairs with `task-review` (run that as a self-check before submitting).
task-review
SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric, benchmarks the task across oracle plus Claude and Codex (with and without skills), audits trajectories for cheating and skill invocation, and produces a `pr-N-task-timestamp-run.txt` review report alongside a `prN.zip` bundle of trajectories. Use when reviewing a SkillsBench task PR (by number, branch, or local task path), when the user asks to review a task, run benchmarks on a PR, audit a submission, classify a task as research or multimodal track, or prepare a comment to post on a SkillsBench PR.
text-to-speech
Practical mastering steps for TTS audio: cleanup, loudness normalization, alignment, and delivery specs.
triangulated-fx-rates
>-
trl
Reference for the TRL (Transformer Reinforcement Learning) library codebase. Use proactively before reading or editing any file under `trl/` so you have the intended contracts and invariants in mind, not just what the current code says. Covers trainer hierarchy (SFT, DPO, GRPO, KTO), shared utility functions (selective_log_softmax, decode_and_strip_padding, padding helpers), configuration system, model wrappers, and how data flows through any TRL trainer.
unit-commitment-data-modeling
Use for parsing structured unit commitment input data from JSON, CSV, benchmark cases, spreadsheets, databases, or nested tables; finding fields for time periods, resources, load, reserve, generator limits, initial conditions, startup data, renewable availability, and production costs without assuming one source-specific schema.
Page 180 of 1672 · 83572 results
