writing-for-agents
Write or edit instructions for agents, including skills, AGENTS.md, and CLAUDE.md.
Skill by luan
Chalk Labs
Need help deploying writing-for-agents?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/luan-writing-for-agents
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/writing-for-agents
What's inside
- Skill name
writing-for-agents- Description
- Write or edit instructions for agents, including skills, AGENTS.md, and CLAUDE.md.
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (3)
- SKILL-MECHANICS.md
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
Write agent instructions that produce clear and consistent decisions. Preserve the user's intent, project language, and existing authority boundaries. ## Instructions - Keep instructions used by every matching task in the main file. - Move substantial task-specific detail to a referenced file. State when the agent must read it. - Put actions in execution order. Keep related definitions, rules, and exceptions together. - Give an action a clear and checkable completion condition when incomplete work is a real risk. - Keep each rule in one place. Remove duplicate, stale, speculative, and ineffective instructions. - Use plain project language. Add a term only when it makes repeated instructions clearer. - State the desired behavior directly. Keep explicit prohibitions for safety, authority, and destructive-action boundaries. - Preserve necessary detail. Do not shorten an instruction until its behavior changes. - Preserve unrelated content when editing an existing file. When the document is a skill, read [SKILL-MECHANICS.md](SKILL-MECHANICS.md). Finish when every instruction changes behavior and all conditional detail remains discoverable.
From luan/agents, MIT.
More from luan/agents
- 0.606score
spriteforge
luan
Create or adapt Blender models and render consistent pixel-art characters, terrain, props, and inventory items with palette-locked sprites, animation sheets…
SkillAFreshness: A★ 3Claude Code +9 - 0.564score
plannotator
luan
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant…
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
plannotator-review
luan
Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 2
- Open issues
- 1
- Last commit (this folder)
- Aug 24, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/luan/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from luan
- 0.606score
spriteforge
luan
Create or adapt Blender models and render consistent pixel-art characters, terrain, props, and inventory items with palette-locked sprites, animation sheets…
SkillAFreshness: A★ 3Claude Code +9 - 0.564score
plannotator
luan
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant…
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
plannotator-review
luan
Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.
SkillBFreshness: B★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get writing-for-agents running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
writing-for-agents skill. Agent Mart. https://agentmart.dev/skills/luan-writing-for-agents (last updated 2026-10-24)