Cursor rule Cursor
Humanize AI-sounding prose, rewrite in a writer's voice, and conservatively clean suspicious invisible Unicode in supplied prose. Use whenever the user wants to humanize, de-slop, de-AI, or de-robotify text; fix writing that sounds like an LLM, corporate, salesy, generic, or off; make a draft sound like them or a…
Skill Claude Code
Humanize and de-slop AI-sounding prose while preserving meaning, specific detail, and genuine human quirks. When a voice sample or style profile is available, rewrite in that writer's actual voice. Remove recurring AI tells such as inflated significance, stock vocabulary, uniform rhythm, excessive hedging, formulaic…
Agent Claude Code
Verifies logical, chronological, and factual consistency across drafted units. Flags contradictions, timeline issues, and character state drift.
Agent Claude Code
Drafts a single atomic unit (scene, subsection, passage, stanza) in the writer's voice. Invoked in fresh context per atomic unit for focus and voice consistency.
Agent Claude Code
Reviews a unit plan for completeness and craft soundness before drafting begins. Catches gaps, contradictions, and weak spots.
Agent Claude Code
Researches topics needed for planning and drafting. Genre conventions, period details, technical accuracy, theological sources, scholarly citations.
Agent Claude Code
Translates a single atomic unit (scene, subsection, passage, stanza) into the target language while preserving the writer's voice. Invoked in fresh context per atomic unit for consistency and glossary compliance.
Agent Claude Code
Compares a drafted unit against STYLE-GUIDE.md and flags voice drift. Returns a score and specific issues.
Plugin Claude Code
Bundles 9 skills, 4 agents, 3 hooks · 558 tokens together
Durable project state, evidence-backed "done", and gates enforced by hooks. Eight commands and four agents.
Skill Claude CodeCodex
Audit a codebase end to end and emit validated JSON plus remediation MDX, or review one diff for non-obvious blast radius with explicit safety facts and a compiled merge proof gate. godaudits fingerprints the repository, detects six project forms, validates Pillars 1.1 and arc-ready artifacts, evaluates 437 checks…
Skill Claude CodeCodex
Produce an audit-aware, agent-executable master plan (PLAN.mdx) before application code is written. One command runs discovery, forces hard-to-reverse decisions, and plans product, business (pricing, entitlements, billing, metrics, feedback), architecture, roadmap, stack, repo, build, deploy, observability, launch…
hannsxpeter/authenticity-check
Cursor rule Cursor
Score how authentically text reads as a real human author's work, flag AI-generated, AI-templated, or derivative spans, and report suspicious Unicode provenance carriers. Use when the user asks if text is authentic, reads like AI, sounds like them, or contains a hidden AI watermark or invisible Unicode. Apply even…
hannsxpeter/authenticity-check
Skill Claude Code
Score how authentically text reads as a real human author's work, flag spans that read as AI-generated, AI-templated, or generically derivative, and run a separate read-only scan for suspicious Unicode provenance carriers. Return an authenticity band, a 0-100 score, provenance signals, and span-level reasons. Use when…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: