Is the Writing Intelligence skill free?

Yes. The skill itself is free from antonio0720/writing-intelligence. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Writing Intelligence SkillProof Score?

7.2/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 2/5.

How do I install Writing Intelligence?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Writing Intelligence with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Writing Intelligence

Anti-slop writing framework: banned-phrase lists, cadence rules, and genre score

by antonio0720 · antonio0720/writing-intelligence

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 7.2/10
Tested: Jul 25, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 6b6f4d1

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Rewrote a slop paragraph twice -- an unguided baseline versus one following the bundled anti_patterns/phrases.md -- and the checklist mattered: the baseline kept three hard-ban cliches ('in today's', 'leverage', 'at the end of the day', 'smarter not harder') while the guided version hit zero and lifted sentence-length variance from a stdev of 3.1 to 6.4 with concrete detail added. All 77 reference files exist and the git-clone-into-skills install works verbatim from a fresh HOME. The value in practice is the banned-phrase list plus cadence and specificity heuristics; the advertised '12 engines, 11-pass governed compiler, 1000-point composite, Sovereign Writing Operating System' is heavy framing over that core. Its own flagship before/after example manufactures confident specifics (a dated OpenAI claim) to raise the score, which sits awkwardly against the skill's own no-fabricated-facts rule.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 7/10
Docs & honesty 2/5

What Writing Intelligence does

A large prose-engineering skill built around anti-pattern phrase lists, sentence-cadence and specificity heuristics, an epistemic claim-classification ledger, and per-genre 100-point scorecards across 26 domain packs. It rewrites, edits, and scores writing through an 11-pass pipeline with optional multi-agent roles. Triggers on write, rewrite, edit, draft, score, or humanize requests for prose, fiction, sermons, resumes, grants, and similar.

How to install Writing Intelligence

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Writing Intelligence

/writing-intelligence Anti-slop writing framework: banned-phrase lists, cadence rules, and genre score

It also activates on plain-language prompts like these:

Rewrite this paragraph so it doesn't sound like AI wrote it
Score my cover letter and cut the corporate cliches
Help me draft a sermon that avoids generic filler phrases

Frequently asked questions

Is the Writing Intelligence skill free?: Yes. The skill itself is free from antonio0720/writing-intelligence. SkillProof publishes the install command and an independent test verdict at no cost.
Does Writing Intelligence work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Tested · Works. Rewrote a slop paragraph twice -- an unguided baseline versus one following the bundled anti_patterns/phrases.md -- and the checklist mattered: the baseline kept three hard-ban cliches ('in today's', 'leverage', 'at the end of the day', 'smarter not harder') while the guided version hit zero and lifted sentence-length variance from a stdev of 3.1 to 6.4 with concrete detail added. All 77 reference files exist and the git-clone-into-skills install works verbatim from a fresh HOME. The value in practice is the banned-phrase list plus cadence and specificity heuristics; the advertised '12 engines, 11-pass governed compiler, 1000-point composite, Sovereign Writing Operating System' is heavy framing over that core. Its own flagship before/after example manufactures confident specifics (a dated OpenAI claim) to raise the score, which sits awkwardly against the skill's own no-fabricated-facts rule.
What is the Writing Intelligence SkillProof Score?: 7.2/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 2/5.
How do I install Writing Intelligence?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Writing Intelligence with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.