write
Invoke only when explicitly asked to write, edit, or polish prose in Chinese or English.
Skill by leo1oel
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/leo1oel-write
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/write
What's inside
- Skill name
write- Description
- Invoke only when explicitly asked to write, edit, or polish prose in Chinese or English. Strips AI writing patterns and rewrites to sound natural. Not for code comments, commit messages, or inline docs.
- License
- unknown
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- write-en.md · references/
- write-zh.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from leo1oel/ResearchKit
- 0.406score
read
leo1oel
Invoke when given any URL, web page link, or PDF to read.
SkillDFreshness: DClaude Code +9 - 0.406score
design
leo1oel
Invoke when building any UI, component, page, or visual interface.
SkillDFreshness: DClaude Code +9 - 0.403score
check
leo1oel
Invoke after any implementation task completes or before merging.
SkillDFreshness: DClaude Code +9 - 0.401score
health
leo1oel
Invoke when Claude ignores instructions, behaves inconsistently, hooks malfunction, or MCP servers need auditing.
SkillDFreshness: DClaude Code +9 - 0.401score
hunt
leo1oel
Invoke when debugging any error, crash, unexpected behavior, or failing test.
SkillDFreshness: DClaude Code +9 - 0.398score
think
leo1oel
Invoke before writing any code for a new feature, design, or architecture decision.
SkillDFreshness: DClaude Code +9 - 0.398score
research
leo1oel
Systematic research workflow: define question, collect sources, analyze, synthesize, and produce structured output.
SkillDFreshness: DClaude Code +9 - 0.208score
learn
leo1oel
No description from the publisher yet.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 6, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/leo1oel/ResearchKit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from leo1oel
- 0.406score
read
leo1oel
Invoke when given any URL, web page link, or PDF to read.
SkillDFreshness: DClaude Code +9 - 0.406score
design
leo1oel
Invoke when building any UI, component, page, or visual interface.
SkillDFreshness: DClaude Code +9 - 0.403score
check
leo1oel
Invoke after any implementation task completes or before merging.
SkillDFreshness: DClaude Code +9 - 0.401score
hunt
leo1oel
Invoke when debugging any error, crash, unexpected behavior, or failing test.
SkillDFreshness: DClaude Code +9 - 0.401score
health
leo1oel
Invoke when Claude ignores instructions, behaves inconsistently, hooks malfunction, or MCP servers need auditing.
SkillDFreshness: DClaude Code +9 - 0.398score
research
leo1oel
Systematic research workflow: define question, collect sources, analyze, synthesize, and produce structured output.
SkillDFreshness: DClaude Code +9
Cite this page
write skill. Agent Mart. https://agentmart.dev/skills/leo1oel-write (last updated 2026-10-24)