Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
NVIDIA/skills Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk I/O with GPUDirect Storage (GDS). Do not use it for Parquet/cuDF/raw-binary or other sharded/custom layouts (see the cupynumeric-parallel-data-load skill), Zarr or object-store/S3 output, .npz or pickled archives, plain h5py without cuPyNumeric, or pure array compute such as FFT, matmul, or reductions. | Skills | — |
NVIDIA/skills Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply. | Skills | — |
NVIDIA/skills Local or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use when running TAO jobs on the current machine, a directly attached Docker host, or a remote GPU box exposed through DOCKER_HOST. Trigger phrases include "run locally", "local Docker", "remote Docker", "use my GPU", "run on my machine", "host Docker daemon". | Skills | — |
Chachamaru127/claude-code-harness This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message. | Skills | — |
Chachamaru127/claude-code-harness This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message. | Skills | — |
davidondrej/skills Launch new CLI coding agents through Corral Design 1, or correctly reopen existing agent sessions inside a Corral-active Herdr repository. Use when the user asks to launch, spawn, batch-start, reopen, relaunch, or resume agents. New launches create Corral-owned tasks; resumptions reuse existing worktrees and sessions. | Skills | — |
debpalash/VoiceStudio Triage GitHub issues, review contributor pull requests, diagnose CI, and prepare explicitly requested releases using the target repository's rules. Use for repository maintenance work, not ordinary VoiceStudio audio generation. | Skills | — |
debpalash/VoiceStudio Legacy VoiceStudio skill alias for existing Claude installations. Generate local speech, discover saved voices, and transcribe audio through the running VoiceStudio backend. | Skills | — |
different-ai/openwork Publish test evidence, publish all test runs, update PR verification, audit red evidence, prove a PR, or declare a PR verdict. Use after @openwork/testkit runs. | Skills | — |
titanwings/distilly Distill colleague, relationship, or celebrity source material into reusable Person Profiles for agents. | Skills | — |
doogal-rm-tgt6-20260911/repo-public-1 Stands in for a public repo the customer merely scanned | Skills | — |
doogal-purge-tgt5-20260908/repo-3 Synthetic purge-rehearsal skill t5-delta | Skills | — |
doogal-purge-tgt5-20260908/repo-2 Synthetic purge-rehearsal skill t5-gamma | Skills | — |
doogal-purge-tgt5-20260908/repo-2 Synthetic purge-rehearsal skill t5-beta | Skills | — |
doogal-purge-tgt5-20260908/repo-1 A review checklist deliberately shared between two inventories | Skills | — |
doogal-purge-tgt5-20260908/repo-1 Synthetic purge-rehearsal skill t5-alpha | Skills | — |
doogal-purge-ctl-20260827/repo-2 Synthetic purge-rehearsal skill ctl-beta | Skills | — |
doogal-purge-ctl-20260827/repo-1 A review checklist deliberately shared between two inventories | Skills | — |
doogal-purge-ctl-20260827/repo-1 Synthetic purge-rehearsal skill ctl-alpha | Skills | — |
Rewrite text to sound collaborative, human, and on-brand for Metis Strategy Contains: metis-humanizer Rewrite text to sound collaborative and human, not pushy or authoritative, free of AI-generated writing patterns, and lightly in Metis Strategy's brand voice. Builds on the humanizer skill's detection catalog (inflated symbolism, promotional language, -ing tails, vague attribution, em dashes, rule of three, AI vocabulary, filler) and adds a Metis brand tint, an opt-in advisory register, document-type modes (email, proposal, exec summary, memo, slide copy), a consulting cliche ban, and a cinematic staging ban. Defaults to plain, peer-to-peer, non-authoritative tone. Use for Metis client-facing or internal prose. Trigger on "metis humanizer", "humanify", "make it human", "metis voice", "metis tone", "consultant tone", "make this sound like Metis", or "humanize for a client". | Skills |
Can't find what you're looking for? Evaluate a missing skill.