Find the skill for your next task.

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

find-bpf-tutorial-topic

Audit bpf-developer-tutorial coverage, research current Linux BPF work and real open-source eBPF projects, maintain the repository tutorial candidate registry, and rank the next lesson by reader value, eBPF leverage, reproducibility, distinctness, teaching clarity, ecosystem evidence, maturity, and maintenance cost. Use when deciding what eBPF tutorial to write next, checking whether an idea is already covered, comparing feature-driven and scenario-driven topics, refreshing the topic roadmap, or asking which candidate has the highest value.

4.20k repo starsObserved in 1 repos
Research
GitHub

test-bpf-tutorial-kvm

Build and smoke-test bpf-developer-tutorial lessons without loading BPF programs into the host kernel. Use when creating, changing, reviewing, or debugging an eBPF tutorial and the runtime test should reuse the already-built x86 kernel under bpf-benchmark through virtme-ng/KVM. Also use for checking whether a tutorial needs a newer kernel feature. Do not use this workflow for performance benchmarking or for rebuilding the benchmark kernel.

4.20k repo starsObserved in 1 repos
Testing & Quality
GitHub

auto-capture-claude-code

Claude Code adapter for the auto-capture skill. Extends auto-capture with automatic session-end hooks that capture transcripts to Open Brain without manual intervention. Use this when you want every meaningful Claude Code session to be preserved automatically — not just the ones where you remember to say "wrap up".

4.19k repo starsObserved in 1 repos
Agent Building
GitHub

ob1-local-http

Capture and search thoughts against a self-hosted Open Brain over plain HTTPS, with no MCP transport involved. Use this skill in environments where Claude Code's MCP feature is disabled or the network blocks remote MCP endpoints, but the brain stack from the companion `local-brain-no-mcp` recipe is reachable on the local network. Triggers: prompts like "remember this", "save that for later", "what did I note about X", "search my brain for Y", "what thoughts touched on Z", or any explicit request to record or recall personal memory.

4.19k repo starsObserved in 1 repos
Apps & Automation
GitHub

port-npm-to-perry

Port an npm package to run under Perry — audit it for TypeScript-subset gaps, add it to perry.compilePackages, and patch whatever breaks so the package compiles natively. EXPERIMENTAL — feedback welcome at github.com/PerryTS/perry/issues/115.

4.17k repo starsObserved in 1 repos
Development
GitHub

lightllm-profiler-control

LightLLM profiler 使用说明。用于需要启动或停止 LightLLM 的 torch_profiler / nvtx profiling 功能时，尤其是查看 --enable_profiling、/profiler_start、/profiler_stop 的使用方法。

4.17k repo starsObserved in 2 repos
DevOps & Security
GitHub

test-model-common

Common override guidance for all skills/test_model sub-skills. Applies to LightLLM model accuracy/speed tests that use lm_eval or lmms_eval, especially local-completions GSM8K runs.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-deepseekr1-base-tp

Runs LightLLM DeepSeek-R1 baseline TP gsm8k: single api_server with --tp 8 and --batch_max_tokens only, no MTP draft, no --dp, no EP MoE (distinct from deepseekr1-mtp-tp which adds MTP). GSM8K lm_eval on localhost port 8089. Requires a dedicated log directory, api_server and eval logs under that tree, summary.txt as consolidated report, tokenizer aligned with MODEL_DIR. Use for baseline R1 tensor-parallel accuracy runs without MTP/EP.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-deepseekr1-mtp-ep

Runs LightLLM DeepSeek-R1 EP MoE + MTP (EAGLE) server variants and GSM8K lm_eval against localhost. Requires each full run to use a dedicated log directory: persist every api_server process log under that tree (per-variant subdirectories recommended), write the consolidated summary to summary.txt in that same log directory, and keep artifacts separated from other test runs. Use when running DeepSeek-R1 MTP EP accuracy workflows or when the user asks to run these four server configurations one-by-one with logged results.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub

test-model-deepseekr1-mtp-tp

DeepSeek-R1 MTP-TP test: LightLLM api_server with MTP (EAGLE) draft, tensor parallel only (--tp 8, no --dp, no EP MoE), plus GSM8K lm_eval on localhost. Distinct from the MTP-EP-TPDP skill which uses --tp 8 --dp 8 and EP MoE. Requires a dedicated log directory, summary.txt, tokenizer aligned with MODEL_DIR. Use for TP-only MTP gsm8k accuracy runs.

4.17k repo starsObserved in 2 repos
Testing & Quality
GitHub