kevinnft

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

中文简介正在准备中。当前显示原文说明。

DSPy: declarative LM programs, auto-optimize prompts, RAG.

中文简介正在准备中。当前显示原文说明。

Compact the current conversation into a handoff document for another agent to pick up.

中文简介正在准备中。当前显示原文说明。

SAM: zero-shot image segmentation via points, boxes, masks.

中文简介正在准备中。当前显示原文说明。

Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.

中文简介正在准备中。当前显示原文说明。

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

中文简介正在准备中。当前显示原文说明。

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

中文简介正在准备中。当前显示原文说明。

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

中文简介正在准备中。当前显示原文说明。

llama.cpp local GGUF inference + HF Hub model discovery.

中文简介正在准备中。当前显示原文说明。

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

中文简介正在准备中。当前显示原文说明。

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

中文简介正在准备中。当前显示原文说明。

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

中文简介正在准备中。当前显示原文说明。

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

中文简介正在准备中。当前显示原文说明。

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

中文简介正在准备中。当前显示原文说明。

Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

中文简介正在准备中。当前显示原文说明。

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

中文简介正在准备中。当前显示原文说明。

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

中文简介正在准备中。当前显示原文说明。

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

中文简介正在准备中。当前显示原文说明。

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

中文简介正在准备中。当前显示原文说明。

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

中文简介正在准备中。当前显示原文说明。

OBLITERATUS: abliterate LLM refusals (diff-in-means).

中文简介正在准备中。当前显示原文说明。

vLLM: high-throughput LLM serving, OpenAI API, quantization.

中文简介正在准备中。当前显示原文说明。

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

中文简介正在准备中。当前显示原文说明。

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

中文简介正在准备中。当前显示原文说明。