humanizer
Humanizer: AI Pattern Detection & Voice Injection
Transform AI-generated text into human writing by detecting patterns and injecting authentic voice.
NEVER
- Never remove AI phrases without also injecting personality — sterile text is still obviously AI.
- Never over-correct (random punctuation chaos !== human voice).
- Never remove ALL structure from formal or academic contexts — know what the audience expects.
- Never batch-replace AI words without checking domain context ("landscape" in CV papers may be correct terminology).
- Never fix every pattern at once — identify the 3-5 dominant patterns and address those.
Before You Edit: Diagnostic Framework
Answer these before applying any changes:
Voice assessment:
- What personality should come through? (witty, skeptical, conversational, authoritative)
- Does the text have opinions, or just facts? Human writing has stakes.
More from acedergren/agentic-tools
cloudflare-zero-trust
Use when working with Cloudflare Tunnel or Access - tunnel setup, authentication configuration, 502 Bad Gateway errors, Docker/Kubernetes deployment, service token management, private network routing (SSH/RDP/databases), WebSocket/gRPC connection issues, replica scaling problems, WARP routing, Terraform/IaC automation, local development with quick tunnels, audit logging setup, compliance requirements (SOC2/HIPAA), or advanced network debugging. Keywords - cloudflared, 502 error, service tokens, terraform, metrics port 20241, trycloudflare, Logpush, SIEM. CRITICAL - Authentication mandatory not optional.
23turborepo
Use when making Turborepo monorepo architecture decisions: choosing between monorepo vs polyrepo, deciding when to split packages, debugging cache misses, setting package boundaries, or avoiding circular dependencies. NOT for basic CLI syntax. Triggers on: turborepo, turbo cache miss, package boundaries, monorepo architecture.
23orchestrate
Use when executing a multi-task implementation plan with parallel agents. Coordinates task assignment, wave sequencing, heartbeat monitoring, git safety, and quality gates. Supports interactive (TeamCreate/Task) and headless (claude -p) modes. Keywords: parallel agents, wave execution, orchestrate, headless, phase execution, task plan.
22refactor-module
Use when deciding whether to extract Terraform code into a reusable module, determining module boundaries, or migrating state after modularization. Covers the refactoring decision (modularize vs inline), anti-patterns causing module sprawl, and state migration risk. Keywords: terraform module, refactor terraform, module boundaries, terraform abstraction, module sprawl, state migration, terraform state mv.
22api-audit
Use when auditing API routes for schema drift, missing auth, or validation gaps. Scans routes against shared TypeScript types to find mismatches, missing middleware, and undocumented endpoints. Read-only — produces a severity-grouped report. Keywords: audit routes, schema drift, auth gaps, missing validation, type mismatch, orphaned schemas.
21firecrawl
Use when scraping web pages, extracting content from JS-rendered sites or SPAs, running search-plus-scrape workflows, or mapping entire site URL trees. Produces clean LLM-friendly Markdown. Prefer over WebFetch when JavaScript execution is required. Keywords: web scraping, fetch URL, scrape website, search web, extract content, SPA, JS-rendered, site map, crawl, Firecrawl.
20