GITHUB AGENT SKILLS / 技能收录

给你的 AI 助手
装上专业技能

我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

hashgraph-online
hashgraph-online/awesome-codex-plugins

roadmap-init

Create a fresh ROADMAP.md by scanning the repo and asking the user 3 minimal questions. Groups tasks by phase and code area. Never overwrites an existing ROADMAP.md.

产品经理
★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

live-editor

Control and verify a running Unity Editor with the low-token hera-agent-unity CLI.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

ui-theme-qa

Use this skill to find and fix undisciplined Control-node UI in a Godot project — spacing that follows no ladder, font sizes with no modular scale, near-duplicate colours, and text that fails WCAG contrast — by measuring the live editor with the `hera-godot` CLI and snapping theme tokens to a reference corpus. It also reports (without changing) inert container wrappers and decorative nodes. Triggers: "clean up the UI spacing/type/contrast", "the UI values look arbitrary", "tidy the Godot UI", "check UI contrast", or any request to mechanically remove statistical UI-design defects without a redesign. Reductive only; edits per-node theme overrides (undoable), never copy or layout content.

设计师视觉设计
★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

live-editor

Use this skill whenever a request involves a Godot project's live editor or running game: inspect scene, node, or UI state; change scenes, nodes, properties, or signals; run a scene; or prove gameplay or UI behavior. Prefer the `hera-godot` CLI over guessing from project files or stale editor state.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

token-harbor

Open Token Harbor, report stored Sail Power and harbor progress, or help the user configure local Codex token tracking.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

review-session

Review what changed in this session with RepoPilot before claiming work is done or that tests pass. Use after edits to tests, CI config, auth, or request handling, and whenever you are about to say "all tests pass".

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

since-cutoff

Find which dependency APIs this project's Python code uses changed after the model's training cutoff (no model calls), write short AGENTS.md or CLAUDE.md notes from the API diff, each with its source, and keep them in step with the lockfile; optionally measure which of the changes the model gets wrong. Use when the user asks whether the model knows their library versions, when code keeps failing on renamed or removed library APIs, or after upgrading dependencies. Trigger with requests such as "does the model know my openai version", "scan my dependencies for API changes" or "check whether the library notes are up to date".

开发工程师后端与接口
★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

unslop

Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle, balanced (default), full, voice-match, anti-detector. Use when user says "humanize this", "make this sound human", "de-slop this", "rewrite without AI tone", "match my voice", "less robotic", or invokes /unslop. Also auto-triggers when text-quality is requested.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

unslop-review

Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if perhaps...", "It might be worth considering..."). Each comment is direct: location, the issue, a concrete fix. Use when user says "humanize review", "de-slop PR comment", "make this feedback sound human", "review this PR", "code review", "/review", "/unslop-review". Auto-triggers when reviewing PRs.

代码审查
★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

unslop-reasoning

Strip AI-slop patterns from reasoning traces (chain-of-thought, extended thinking, agent decomposition) — not final prose. Reasoning text has its own slop catalog that regular unslop doesn't target: over-explaining the question, over-hedging, over-decomposing trivial problems into 6-bullet substeps, infinite-loop rationalization. Trigger: /unslop-reasoning, "clean up my reasoning", "fix this chain of thought", "this CoT sounds robotic". Applies to reasoning output; does not override regular /unslop mode.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

unslop-help

Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

unslop-file

Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version overwrites the original file. Plain backup saved as FILE.original.md. Trigger: /unslop-file <filepath> or "humanize memory file"

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

unslop-commit

Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why" isn't obvious from the subject. Use when user says "humanize commit", "de-slop commit message", "make this commit sound human", "/unslop-commit", "/commit", "write a commit", or pastes a draft commit to clean up. Auto-triggers when staging changes.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

unforgit-memory

Use Unforgit MCP tools as durable repository memory for decisions, conventions, gotchas, and playbooks.

Skill与智能体开发
★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

setup

暂无简介

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

metis-check

Use when the user asks to check or verify a citation, DOI, identifier, reference list, case citation, company or registry id, or whether a cited source exists. Metis Check settles each identifier at the body that issues it and files a report.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

metamask-agent-wallet

Use when the user asks anything about blockchain wallets, transactions, signing, token transfers, supported chains, wallet balances, perpetual futures trading, funding rates, and Hyperliquid vaults, prediction markets, token swaps, cross-chain bridges, market data, token discovery, tokenized real-world assets, RWAs, AI-generated market and asset summaries via pulse, decoding EVM calldata, DeFi earn/yield vaults, installing or removing third-party `mm` CLI plugins, or authentication via the MetaMask Agentic CLI; also when an HTTP request returns 402 Payment Required / x402, when an MCP tool call returns an x402 payment-required result, or the agent needs to pay for a paywalled API, endpoint, file, tool, or resource. Single entry point for all mm CLI operations. Financial operations are protected by server-enforced access controls including MFA approval, configurable wallet policies, and trading-mode guards (guard/beast) that restrict operation scope independently of the agent.

Skill与智能体开发
★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

validate

Run the profile-aware DocFlow documentation readiness gate. Always blocks broken links, stale maps, and missing headings; applies native naming and section rules strictly to new scaffolds while treating established adopted structures as cleanup guidance.

★ 1.6k