Laporan audit skill
peft-fine-tuning Laporan audit.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Trust Score OpenAgentSkill
Trust Score OpenAgentSkill
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
Adopsi GitHub
Lulus100
13K star GitHub
Aktivitas star/fork
Lulus92
13K star dan 948 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus100
3 hari sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Lulus94
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Peringatan44
command execution surface, credential or environment access
Ketersediaan pemasangan
Lulus92
npx skills add Orchestra-Research/AI-Research-SKILLs --skill peft-fine-tuning
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Peringatan50
secrets or environment access, shell or command execution
Bukti repositori
Lulus86
https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/03-fine-tuning/peft
Status peninjauan
Peringatan50.9
Persetujuan tinjauan AI belum ada
Hasil terbukti Agent
Info54
Belum ada data hasil Agent
Pemeriksaan
Tinjauan pemasangan dan adopsi
Jalur pemasangan
92
npx skills add Orchestra-Research/AI-Research-SKILLs --skill peft-fine-tuning
Repositori
88
https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/03-fine-tuning/peft
Lisensi
86
MIT
Pemeliharaan
100
3 hari sejak push
Tinjauan AI
55
Review approval is missing
Kelengkapan README/SKILL.md
94
Usable description available
Risiko dependensi
44
command execution surface, credential or environment access
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
50
secrets or environment access, shell or command execution
Aktivitas star/fork
92
13K star dan 948 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
13K star GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Peringatan
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Persetujuan tinjauan AI belum ada
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
- Review status: AI review approval is missing
Metode
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Bandingkan opsi sekitar
Skill terkait untuk diaudit berikutnya
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
96K Star · Laporan audit
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
13K Star · Laporan audit
litert-lm
Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. Use this skill to build a new chat, summarization or extraction app with a .litertlm model from Hugging Face litert-community (Gemma, Qwen, Llama, Phi) - the dependency and manifest entries, getting the model file onto the device, engine initialization, a streamed multi-turn conversation, the ViewModel and screen.
459 Star · Laporan audit