Adversarial AI text detection and humanization system. Detects AI-generated text and iteratively revises it to read as authentically human.
Plugin ghostwriter from marketplace tutor in svallory/tutor. Commands read from the repo's manifest — 24 days ago.
detector-red-flagsAI writing detection patterns and red flags. Load when the slop-detector agent needs to analyze text for AI signals.
surgical-updateApply targeted fixes to specific sentences without regenerating entire text
writer-examplesGood vs bad examples for humanizing AI text. Load when the writer agent needs transformation examples.
/ghostwriter:analyzeAnalyze text to determine if it was written by a human or AI
/ghostwriter:auditScan all files in a publication for AI signals and report which need work
/ghostwriter:authorsList, add, remove, or show author profiles
/ghostwriter:createGenerate new text from a topic using adversarial Writer vs Detector training
/ghostwriter:helpShow available ghostwriter commands and quick start guide
/ghostwriter:humanize-allHumanize all .md files in a folder by running the humanize loop for each file
/ghostwriter:humanizeRun iterative text revision sessions
/ghostwriter:migrateMigrate from v1 project layout to v2 (.ghostwriter/ workspace)
/ghostwriter:publicationsList, add, remove, or show publications
/ghostwriter:setupInteractive setup wizard for the ghostwriter plugin. Creates author personas, publications, and writing configs. Run this before using any other ghostwriter command.
ai-engineerSenior AI Engineer that owns the humanization system. Analyzes Detector feedback and improves the Writer through instruction updates, tool development, and pipeline changes. Use when the Writer fails to fool the Detector.
reviewerApplies mechanical cleanup (in-place), then runs analysis tools and build-fix-plan to produce a sentence-centric fix plan for the Writer.
slop-detectorAnalyzes text for AI-generation signals and provides evidence. Use when you need to detect if text was AI-generated.
writerProduces human-like text that evades AI detection. Use when generating text that needs to pass as human-written.
Hyper Coding workflow support: project spaces (a bare repo wrapping all of a project's worktrees plus local-only dirs), per-edit integration with the linters and typecheckers a project already uses, spec-driven planning, and template-driven generation.
8 skills · 11 commands · hooks
Structured problem decomposition for hard problems: reduce an unknown into a collection of smaller knowns, turn confusion into testable hypotheses, and solve forward one variable at a time.
1 skill
Produce narrated, subtitled MP4 demos of web-app features: Playwright records the browser with an animated cursor, ffmpeg assembles takes paced by TTS narration, with optional title cards, subtitles, and an outro slate.
1 skill
Drive the Obscura headless browser from an agent: fetch and scrape JavaScript-rendered pages, run Playwright scripts and E2E suites against its CDP server without bundled Chromium, and watch the session live.
1 skill
Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Covers v0.2 provenance, trust, lifecycle, and Attested Computations.
1 skill
Decision sheets: several questions with the agent's suggested answers become a page where you change only what you disagree with, add notes, and copy one short reply back into the chat.
1 skill
AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server
3 skills · 1 command · 1 agent · 1 MCP server
Rewrite AI-sounding text so it reads like the writer without changing what it says.
1 skill
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Query Trackio projects, runs, and metrics using the `trackio` CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system metrics. Designed for LLM agents and automation scripts.
1 skill
OpenAPI specification generation, Mermaid diagram creation, tutorial writing, API reference documentation
3 skills · 1 command · 5 agents
Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.
1 skill · 9 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.