AgentHubAgentHub

Agent Skills

共 333 个资源 · Agent Skill 是带 SKILL.md 的指令包。安装后,AI 会根据 description 在匹配任务时自动加载,无需每次手动粘贴提示词。

“writing” 共 333 个结果

Humanizer

v2.1.0

SkillClawHub

io.clawhub.brandonwise/ai-humanizer

Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.

source

writing-e2e-tests

vmain

SkillSkillsMP

io.github.comet-ml/opik/writing-e2e-tests

Use when a developer wants to add, write, or create an end-to-end test for an Opik feature, page, or branch — e.g. "add an e2e test for the experiments comparison page", "write a test for the feature I just built", "e2e test for this branch", "cover the dataset items flow with a test". Runs the full loop in tests_end_to_end/e2e/ — analyze the feature and frontend code, explore the live UI with the Playwright MCP, write the Page Object Model + spec, and run it locally until green.

source

writing-skills

vmain

SkillSkillsMP

io.github.software-mansion/react-native-audio-api/writing-skills

How to write, structure, and maintain Claude skill files. Covers the three-level progressive disclosure model, all YAML frontmatter fields (context:fork, allowed-tools, disable-model-invocation, user-invocable, hooks, argument-hint), invocation control patterns, string substitutions ($ARGUMENTS, ${CLAUDE_SKILL_DIR}), shell preprocessing with backtick syntax, and the Maintenance section contract. Use when creating a new skill file, rewriting an existing one, or reviewing a skill for quality. Trigger phrases: "add a skill", "write a skill", "create a skill file", "update skill", "skill quality", "skill review", "context fork", "allowed-tools", "user-invocable".

source
Agent Skills · AgentHub