Agent skill

Writing Claude Directives

A skill your agent uses when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts.

No licenceAuto-check passedAI & LLM Engineering

Install Writing Claude Directives

skills CLI

$ npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install ed3dai/ed3d-plugins writing-claude-directives --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/ed3dai/ed3d-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ed3d-extending-claude/skills/writing-claude-directives .claude/skills/writing-claude-directives && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "writing-claude-directives" agent skill from https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives into .claude/skills/writing-claude-directives/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-claude-directives", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ed3dai/ed3d-plugins writing-claude-directives --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ed3dai/ed3d-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/ed3d-extending-claude/skills/writing-claude-directives .agents/skills/writing-claude-directives && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "writing-claude-directives" agent skill from https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives into .agents/skills/writing-claude-directives/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-claude-directives", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ed3dai/ed3d-plugins writing-claude-directives --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ed3dai/ed3d-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/ed3d-extending-claude/skills/writing-claude-directives .cursor/skills/writing-claude-directives && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "writing-claude-directives" agent skill from https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives into .cursor/skills/writing-claude-directives/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-claude-directives", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/ed3dai/ed3d-plugins.git --path plugins/ed3d-extending-claude/skills/writing-claude-directives

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ed3dai/ed3d-plugins writing-claude-directives --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ed3dai/ed3d-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/ed3d-extending-claude/skills/writing-claude-directives .gemini/skills/writing-claude-directives && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "writing-claude-directives" agent skill from https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives into .gemini/skills/writing-claude-directives/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-claude-directives", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ed3dai/ed3d-plugins writing-claude-directives

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ed3dai/ed3d-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/ed3d-extending-claude/skills/writing-claude-directives .github/skills/writing-claude-directives && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "writing-claude-directives" agent skill from https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives into .github/skills/writing-claude-directives/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-claude-directives", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ed3dai/ed3d-plugins writing-claude-directives --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ed3dai/ed3d-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/ed3d-extending-claude/skills/writing-claude-directives .opencode/skills/writing-claude-directives && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "writing-claude-directives" agent skill from https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives into .opencode/skills/writing-claude-directives/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-claude-directives", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: writing-claude-directives
GitHub stars: 250
Token cost: ~2.4k tokens
SKILL.md length: 658 words
Files: 3
Skills in repo: 34
Repo updated: Sep 6, 2026
First seen: Oct 7, 2026
Licence: None found

At a glance

A skill your agent uses when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts.

Works in 3 steps: Baseline: Run scenario WITHOUT… → Apply: Add directive, verify compliance → Iterate: Find new loopholes → add…
Writing instructions that guide Claude behavior - skills
SKILL.md covers Core Principles, Token Efficiency, Discovery (for Skills) and Compliance Techniques, plus 10 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Writing Claude Directives is an agent skill from ed3dai/ed3d-plugins. Use when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts. Covers token efficiency, compliance techniques, and discovery optimization.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `long-running-state-patterns.md`).

It sits in AI & LLM Engineering, covering Prompt engineering and Agent instruction files. The repository describes itself as: Ed's repo of Claude Code plugins, centered around a research-plan-implement workflow. Only a tiny bit cursed. If you're lucky.

When your agent uses it

Writing instructions that guide Claude behavior - skills
CLAUDE.md files

Example prompts

“/writing-claude-directives”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Baseline: Run scenario WITHOUT directive, document failures
Apply: Add directive, verify compliance
Iterate: Find new loopholes → add counters → re-test

What it can do on your machine

Read from SKILL.md and the folder at commit 0c90f4b. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, xml and yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing Claude Directives loads about 2.4k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 658 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~54
When it runs · the whole SKILL.md, loaded when a task matches: ~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 658 words (~2,360 tokens).

“REQUIRED: Also apply ed3d-extending-claude:prompt-security-hardening when using this skill. Directives that demonstrate unsafe secrets handling teach agents to leak secrets.”

— opening of SKILL.md by ed3dai

name: writing-claude-directives
user-invocable: false

Outline of SKILL.md

Writing Claude Directives
Core Principles
Token Efficiency
Discovery (for Skills)
Compliance Techniques
Primary: Context + Motivation
Secondary: Structural Enforcement
Escalation: Imperatives (Use Sparingly)
By Skill Type
Structure Patterns
XML for Directives and Format Control
Match Prompt Style to Desired Output
Workflows
Feedback Loops
Degrees of Freedom
Action Bias Templates
Proactive (Default to Action)
Conservative (Research First)
Overengineering Prevention
Model-Specific Notes
Opus 4.5: "Think" Sensitivity
Naming (for Skills)
Common Mistakes
Anti-Rationalization
Testing Directives
Long-Running Tasks
Graphviz (for Process Flows)

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files in plugins/ed3d-extending-claude/skills/writing-claude-directives of ed3dai/ed3d-plugins.

SKILL.md
graphviz-conventions.dot
long-running-state-patterns.md

Open the folder on GitHubat commit 0c90f4b

Compare with similar skills

Writing Claude Directives next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Writing Claude Directives compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Writing Claude Directives this skilled3dai/ed3d-plugins	250	—	~2.4k	Automated safety check: Pass	None	1 mo ago
Context Auditundefined-ui/second-brain-os	1k	—	~802	Automated safety check: Pass	MIT	yesterday
Asd Ste100 SkillTwiTech-LAB/devchain	101	—	~1.2k	Automated safety check: Pass	MIT	yesterday
Create Simple Promptpnp/copilot-prompts	893	—	~2.6k	Automated safety check: Pass	MIT	5 days ago
Create System Promptpnp/copilot-prompts	893	—	~3.1k	Automated safety check: Pass	MIT	5 days ago
Prompt Regressionagentscope-ai/OpenJudge	871	—	~2.8k	Automated safety check: Pass	Apache-2.0	1 mo ago

Similar skills

Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
1k GitHub stars~802 tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Asd Ste100 Skill
TwiTech-LAB/devchain
Write or rewrite English with ASD-STE100 Simplified Technical English rules: one meaning per word, active voice, simple tenses, one instruction per sentence.
101 GitHub stars~1.2k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Create Simple Prompt
pnp/copilot-prompts
This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…
893 GitHub stars~2.6k tokensUpdated 5 days ago
AI & LLM EngineeringAuto-check passed
Create System Prompt
pnp/copilot-prompts
This skill should be used when the user asks to "create an agent instruction", "add agent instructions", "scaffold an agent sample", "create a system prompt sample", "add a system prompt", "create a…
893 GitHub stars~3.1k tokensUpdated 5 days ago
AI & LLM EngineeringAuto-check passed
Prompt Regression
agentscope-ai/OpenJudge
A skill your agent uses when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline.
871 GitHub stars~2.8k tokensUpdated 1 mo ago
AI & LLM EngineeringAuto-check passed
003 Skills Inventory
jabrena/plinth
A skill your agent uses when you need to generate a checklist document with Java system prompts from skills.xml, following the embedded section template and producing INVENTORY-SKILLS-JAVA.md.
447 GitHub stars~792 tokensUpdated 3 days ago
AI & LLM EngineeringAuto-check passed

More from ed3dai/ed3d-plugins

All 34 skills in this repo

Systematic Debugging
ed3dai/ed3d-plugins
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis…
250 GitHub starsUsed in 3 repos~2.4k tokens
Auto-check passed
Testing Skills With Subagents
ed3dai/ed3d-plugins
A skill your agent uses when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation…
250 GitHub starsUsed in 3 repos~3.5k tokens
Auto-check passed
Brainstorming
ed3dai/ed3d-plugins
A skill your agent uses when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning…
250 GitHub starsUsed in 1 repo~4.3k tokens
Auto-check passed
Writing Good Tests
ed3dai/ed3d-plugins
A skill your agent uses when writing or reviewing tests - covers test philosophy, condition-based waiting, mocking strategy, and test isolation
250 GitHub starsUsed in 1 repo~2.7k tokens
Auto-check passed
Writing Skills
ed3dai/ed3d-plugins
A skill your agent uses when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing…
250 GitHub starsUsed in 1 repo~1.3k tokens
Auto-check passed
Coding Effectively
ed3dai/ed3d-plugins
ALWAYS use this skill when writing or refactoring code. An agent skill from ed3dai/ed3d-plugins.
250 GitHub stars~1.9k tokensUpdated 1 mo ago
Auto-check passed

Questions about Writing Claude Directives

What does Writing Claude Directives do?

A skill your agent uses when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts. Writing Claude Directives is an agent skill from ed3dai/ed3d-plugins.md files, agent prompts, system prompts.

When should I use Writing Claude Directives?

Writing Claude Directives fits situations like: writing instructions that guide Claude behavior - skills; CLAUDE.md files.

How do I install Writing Claude Directives in Claude Code?

Run `npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a claude-code`. Or copy the skill folder (plugins/ed3d-extending-claude/skills/writing-claude-directives in ed3dai/ed3d-plugins) into .claude/skills/writing-claude-directives in your project. Claude Code loads it when a task matches its description.

How do I install Writing Claude Directives in Codex?

Run `npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a codex`. Or copy the skill folder (plugins/ed3d-extending-claude/skills/writing-claude-directives in ed3dai/ed3d-plugins) into .agents/skills/writing-claude-directives in your project. Codex loads it when a task matches its description.

Can I use Writing Claude Directives in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ed3dai/ed3d-plugins --skill writing-claude-directives -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-claude-directives, .gemini/skills/writing-claude-directives, .github/skills/writing-claude-directives and .opencode/skills/writing-claude-directives in your project.

What does Writing Claude Directives need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Claude Directives is instructions for the agent only.

Does Writing Claude Directives access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Writing Claude Directives safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Writing Claude Directives use?

No licence was found for Writing Claude Directives or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Writing Claude Directives use?

About 2.4k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Writing Claude Directives?

Skills that share tags, products or a category with Writing Claude Directives: Context Audit (undefined-ui/second-brain-os, 1k stars), Asd Ste100 Skill (TwiTech-LAB/devchain, 101 stars), Create Simple Prompt (pnp/copilot-prompts, 893 stars) and Create System Prompt (pnp/copilot-prompts, 893 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Claude Directives?

ed3dai (a GitHub organization) maintains it in ed3dai/ed3d-plugins, which has 250 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on September 6, 2026.

Source: ed3dai/ed3d-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Writing Claude Directives

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

More from ed3dai/ed3d-plugins

Related

Questions about Writing Claude Directives