Anti-Defensive Writing
A skill that strips defensive caveats, apologies and excess hedging from text and makes claims direct while keeping needed limits
Low risk
We rate an entry low when it mostly gives the agent instructions and reference material.
Why this level
- The skill is text-editing instructions and runs no code
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/anti-defensive-writingDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Assembled automatically, review before installing.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a claude-code -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .claude/skills
cp -R "$tmp/skill/anti-defensive-writing" .claude/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a cursor -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .agents/skills
cp -R "$tmp/skill/anti-defensive-writing" .agents/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a github-copilot -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .github/skills
cp -R "$tmp/skill/anti-defensive-writing" .github/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a codex -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .agents/skills
cp -R "$tmp/skill/anti-defensive-writing" .agents/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a gemini-cli -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .agents/skills
cp -R "$tmp/skill/anti-defensive-writing" .agents/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .devin/skills
cp -R "$tmp/skill/anti-defensive-writing" .devin/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Formerly Windsurf.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a cline -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .cline/skills
cp -R "$tmp/skill/anti-defensive-writing" .cline/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a roo -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .roo/skills
cp -R "$tmp/skill/anti-defensive-writing" .roo/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
A fork of Roo Code, same .roo folders.
Run in a terminal in the project folder
npx skills add kiterlin/anti-defensive-writing --skill 'Anti-Defensive Writing' -a opencode -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5d69bd5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .agents/skills
cp -R "$tmp/skill/anti-defensive-writing" .agents/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .agents/skills
cp -R "$tmp/skill/anti-defensive-writing" .agents/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/kiterlin/anti-defensive-writing.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/anti-defensive-writing/
git -C "$tmp" checkout 5d69bd55b1c5f1780d87cb0e4fe26dd916d8c975
mkdir -p .agents/skills
cp -R "$tmp/skill/anti-defensive-writing" .agents/skills/anti-defensive-writingCommands for macOS and Linux, on Windows run them in Git Bash.
Install the skill: curl -fsSL https://raw.githubusercontent.com/Kiterlin/anti-defensive-writing/main/install.sh | sh. Then ask it to remove defensive phrasing from a text.
Other ways from the author
curl -fsSL https://raw.githubusercontent.com/Kiterlin/anti-defensive-writing/main/install.sh | shmacOS, Linux, WSL. Windows has install.ps1 via irm.
This is third-party code. Review the repository files before installing.
What it does
The skill rewrites academic and professional text so the point leads. It spots defensive moves: preemptive apologies, stacks of modal hedges, negative self-limiting statements and caveats in high-impact spots, and removes what weakens the text without helping accuracy. Real limits about method, ethics, law and safety stay, but move to their proper sections and are stated once, calmly. It ships a checklist and a procedure for rebuilding a paragraph around its main claim.
Who it is for. For writers, editors, researchers and teachers who want direct, confident prose.
Good fit when
- The text is loaded with caveats, apologies and hedges
- You want the contribution and findings up front, not defense
- You are revising a paper, abstract or grant proposal
Not a fit when
- The limitations are essential and must stay in place
- You need fact-checking rather than tone and structure
Example request
Remove the defensive caveats and apologies from this paragraph and lead with the contributionLimitations
The skill works on the form and tone of text; it does not verify whether claims are true. The material targets English academic and professional prose. The result depends on the model of the agent it runs in.
How to disable. Remove the anti-defensive-writing skill folder from the agent's skills directory.
Security check
- The skill is text-editing instructions and runs no code
README in short
The README explains what defensive writing is and shows before and after pairs. The skill leads with the claim, separates excess caveats from real limits and provides a checklist and a revision procedure. It installs in one line via install.sh or install.ps1, and a ready prompt standard covers web chats and editor rules like Cursor and Windsurf. The repo holds SKILL.md, examples and an agent config. MIT licensed.
SKILL.md
--- name: anti-defensive-writing description: Reduce defensive writing in drafts and revisions by removing unnecessary caveats, disclaimers, hedges, apology-like framing, negative self-limiting statements, and over-explanations while preserving necessary scope, accuracy, safety, legal, ethical, and methodological limits. Use when drafting or revising academic writing, papers, essays, abstracts, introductions, contribution statements, discussions, conclusions, technical explanations, grant writing, product writing, policy writing, professional reports, or any text the user wants to be clearer, stronger, more direct, more concise, more confident, less verbose, less caveated, less apologetic, or less defensive. --- # Anti-Defensive Writing ## Core Rule Advance the claim directly. Say what is true, what the text argues, what the evidence shows, or what the method does. Do not default to explaining what the text does not claim, does not prove, does not imply, does not cover, or does not attempt. Use a calm, competent authorial posture. Write as an author explaining an argument to the reader, not as an author negotiating with an imagined critic. ## Preserve Necessary Precision Keep limitations when they are necessary for accuracy, ethics, law, safety, or methodological transparency.
FAQ
Will it strip every caveat?
No. It keeps real limits about method, ethics, law and safety and moves them to their sections, removing only excess defense.
Can I use it without installing?
Yes. The README gives a ready prompt standard to paste into a system prompt or editor rules.
Related
Microsoft's utility and MCP server that turn PDF, Word, Excel, PowerPoint, HTML and other files into Markdown for models
Anthropic skills
Skills
Anthropic's official skill examples: docx, pdf, pptx and xlsx documents, design, MCP builder and the Agent Skills spec
A skill that builds editable PPTX decks from PDF, DOCX, URLs and Markdown with native shapes, charts and animations
A skill that draws editorial diagrams as standalone HTML and SVG files: architecture, flowcharts, ER, funnels and about forty more types