Find the skill for your next task.

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

test-model-qwen2.5-14b-fp8kv-gsm8k

LightLLM Qwen2.5-14B-Instruct GSM8K with FP8 KV cache quantization: either fp8kv_sph (per-head calibration JSON) or fp8kv_spt (per-tensor calibration JSON). Single api_server tp 2 fixed HTTP port 8089 (not configurable), lm_eval local-completions. Assign GPUs via nvidia-smi then export CUDA_VISIBLE_DEVICES. Before starting api_server, cwd must be LightLLM repo root; pass --kv_quant_calibration_config_path as the repo-relative path from the table row that matches --llm_kv_type (fp8kv_sph with per-head JSON only; fp8kv_spt with per-tensor JSON only; no absolute path, no REPO_ROOT/CALIB_JSON shell concatenation). If default MODEL_DIR path is missing or load fails with path errors, ask the user for the correct MODEL_DIR. LOG_DIR, summary.txt, port listen checks (not health), no_proxy, background server with log redirect. Two variants documented in one skill.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-qwen3.5-0.8b-gsm8k-scenarios

LightLLM Qwen3.5-0.8B GSM8K multi-scenario regression: five isolated runs (baseline api_server, prefill cudagraph, linear-attention cache flags, CPU cache plus linear-att, disk cache with LIGHTLLM_DISK_CACHE_PROMPT_LIMIT_LENGTH). Each scenario uses api_server tp 2 port 8089, then lm_eval local-completions gsm8k batch 500. Scenarios 4 and 5 run lm_eval twice for cache warm hit. Per-scenario LOG_DIR, server.log, eval logs, summary.txt. GPUs from nvidia-smi; port listen readiness not health; clear proxies and set no_proxy. Default MODEL_DIR HuggingFace hub snapshot path; default DISK_CACHE_DIR /mtc/test/tmp/ for scenario 5; ask user for paths if missing or not writable.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-qwen3.5-0.8b-pd-nixl

LightLLM Qwen3.5-0.8B PD disaggregation over NIXL gsm8k: pd_master on 8089, prefill on 8001, decode on 8002. Supports TP1 and TP2 runs by setting TP / PREFILL_CUDA_DEVICES / DECODE_CUDA_DEVICES. Qwen3.5 has linear-attention state transfer; use --pd_kv_page_size 2048 and --pd_kv_page_num 16. lm_eval hits pd_master URL. Requires UCX/RDMA env, nvidia_peermem check, curl warmup before lm_eval, registration wait in pd_master.log, and summary.txt. Includes optional repeated-prompt decode cache probe for linear-att page-boundary behavior.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-qwen3-8b-gsm8k-scenarios

LightLLM Qwen3-8B GSM8K multi-scenario regression: seven isolated api_server configs (baseline, vllm-fp8w8a8 quant, tpsp mix, tpsp with dp2 and dp prefill balance, cpu cache, int8kv on top of cpu cache, disk cache with LIGHTLLM_DISK_CACHE_PROMPT_LIMIT_LENGTH). Each scenario then lm_eval gsm8k batch 500. Scenarios 5–7 run lm_eval twice for cache hit. Per-scenario LOG_DIR, server.log, eval logs, summary.txt. Default MODEL_DIR /mtc/models/qwen3-8b; DISK_CACHE_DIR /mtc/test/tmp/ for scenario 7; ask user if paths invalid. Fixed HTTP port 8089 (not configurable). nvidia-smi GPUs, port listen not health, clear proxies and no_proxy.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-qwen3-8b-pd-nixl

LightLLM Qwen3-8b PD disaggregation gsm8k: pd_master on 8089, prefill on 8001, decode on 8002, tp 2 each. Assign four GPUs via nvidia-smi then export PREFILL_CUDA_DEVICES / DECODE_CUDA_DEVICES (no fixed card IDs; no complex shell automation). UCX_NET_DEVICES and TLS for RDMA per cluster. lm_eval hits pd_master URL. HOST vs PD_MASTER_IP when co-located. Before lm_eval, must POST one completion via curl to pd_master for warmup verification. Requires LOG_DIR, MODEL_DIR, proxy cleared, no_proxy, summary.txt. Same-GPU model_infer + pd_*_trans need NVIDIA MPS for best KV copy perf; record MPS on/off in summary. Run check_nvidia_peermem.sh in this skill dir; record in summary.txt. Use for PD separation tests with either the default NIXL transport or NCCL transport.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-qwen3-vl-8b-mmmu-val

LightLLM Qwen3-VL-8B-Instruct: api_server tp 2 on port 8089, then lmms-eval CLI (python -m lmms_eval, model openai_compatible, tasks mmmu_val, batch_size 900) with OPENAI_API_BASE pointing at LightLLM OpenAI-compatible /v1. Restore https_proxy for Hub while no_proxy includes 127.0.0.1. Requires lmms-eval install, OPENAI_API_KEY placeholder, LOG_DIR and MODEL_DIR, nvidia-smi GPU choice, pipefail with tee, summary.txt. No wrapper script; use command line only.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-qwen3-vl-8b-vit-sep-mode

LightLLM Qwen3-VL-8B-Instruct visual separation (ViT sep / proxy): three processes in order—config_server on 8090; internal Redis on 6000; visual_only with visual_rpyc 8091 and afs_image_embed_dir; normal api_server tp 2 port 8089 with visual_use_proxy_mode. After HTTP /v1/models on normal, lmms_eval mmmu_val (openai_compatible, batch 900, OPENAI_API_BASE http://HOST:8089/v1); restore https_proxy for Hub while no_proxy includes 127.0.0.1. lmms_eval_out, console log, mmmu_acc in summary. pipefail for tee exit code.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

tsdown-migrate

Migrate TypeScript library projects from tsup to tsdown. Provides complete option mappings, config transformation rules, default value differences, and unsupported option alternatives so AI agents can intelligently perform migrations.

4.17k repo starsObserved in 1 repos
Development
GitHub

cangjie-skill

Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into skills" — i.e. wants the frameworks, principles, and methodologies in long-form content extracted into atomic, reusable Claude skills that an agent can invoke in real-world situations. NOT for simple summarization, book reviews, or role-playing as the author (that is nuwa-skill's job).

4.16k repo starsObserved in 1 repos
Agent Building
GitHub

retire-add-ast-query

Add an AST query for a JavaScript library to the retire.js vulnerability database. Given a library name, downloads multiple versions, analyzes the code structure where the version string is assigned, writes an ASTronomical XPath-like query anchored with library-specific identifiers, tests the query locally, adds it to jsrepository-ast.js, and runs validate/test-detection. Use this skill whenever adding an AST-based version detection query to retire.js.

4.16k repo starsObserved in 1 repos
Development
GitHub