Review or draft prose so it reads like a person wrote it, not an AI. Catches AI-slop tells (cliché clusters, promotional register, "not just X but Y" parallelisms, copula avoidance, uniform sentence rhythm, and em-dash or emoji overuse) and suggests rewrites. Use when writing, editing, or reviewing docs, READMEs, blog posts, release notes, or marketing copy, or when the user asks to check content for AI slop, "sloppy AI", or to make writing sound human.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# slop-check
Make prose read like a person wrote it. This is a craft tool: the goal is a genuine voice that fits the piece, not a trick to fool an AI detector. Ignore detector scores entirely. They are noisy, and chasing them produces worse writing.
## The one rule that governs the rest
No single feature proves text is AI-written. Good human writers use em dashes, emoji, the word "delve," and the occasional cliché. The tell is a *cluster*: several markers stacked together, plus a flat, promotional register and a rigid shape. So weigh concentration and context, not isolated hits. One em dash in a strong paragraph is fine. Five em dashes, three "crucial"s, and a "in today's fast-paced world" in one section is slop.
Match the register, too. A playful blog post, a legal memo, and a terminal README have different rules. Fix what betrays a machine; keep what serves the reader.
## When reviewing a file or a passage
1. Read the target (a file the user names, a pasted passage, or the draft in progress).
2. Find the tells. Prioritize clusters and register over lone words.
…
The line at the top of this page pins the label git:20260924.dde2a86, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_uz4nak5qyib7ydff
GET https://markdownregistry.com/api/v1/resolve?ref=sigistry/marketplace/audit
GET https://markdownregistry.com/api/v1/blob/adeb1c553410771b783d78204655e499eedd2e4c71ff1986dda75d3da078107f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
sigistry/marketplace · plugins/a11y-i18n-remediator/skills/catalog-hygiene/SKILL.md · This skill should be used when the user mentions "translation catalog", "i18n keys", "missing translations", "unused…
sigistry/marketplace · plugins/a11y-i18n-remediator/skills/icu-messageformat/SKILL.md · This skill should be used when the user mentions "i18n", "internationalization", "ICU", "MessageFormat"…
sigistry/marketplace · plugins/a11y-i18n-remediator/skills/wcag-remediation/SKILL.md · This skill should be used when the user mentions "accessibility", "a11y", "WCAG", "ARIA", "screen reader", "keyboard…
sigistry/marketplace · plugins/api-contract-keeper/skills/error-envelope/SKILL.md · This skill should be used when the user mentions "error handling", "problem details", "rfc 9457", "rfc 7807", "request…
sigistry/marketplace · plugins/api-contract-keeper/skills/idempotency-patterns/SKILL.md · This skill should be used when the user mentions "idempotency", "idempotency key", "retries", "exactly once", "double…
sigistry/marketplace · plugins/api-contract-keeper/skills/job-reliability/SKILL.md · This skill should be used when the user mentions "background jobs", "queue", "worker", "dead letter", "DLQ", "retry"…
sigistry/marketplace · plugins/api-contract-keeper/skills/openapi-drift/SKILL.md · This skill should be used when the user mentions "openapi", "swagger", "spec drift", "api contract", "breaking change"…
sigistry/marketplace · plugins/ci-incident-medic/skills/dockerfile-smells/SKILL.md · This skill should be used when the user mentions "Dockerfile", "docker image size", "container security", "multi-stage…
sigistry/marketplace · plugins/ci-incident-medic/skills/gha-failure-taxonomy/SKILL.md · This skill should be used when the user mentions "github actions failing", "CI failure", "workflow failed", "actions…
sigistry/marketplace · plugins/ci-incident-medic/skills/incident-response/SKILL.md · This skill should be used when the user mentions "postmortem", "incident", "root cause analysis", "blameless"…
sigistry/marketplace · plugins/ci-incident-medic/skills/k8s-manifest-validation/SKILL.md · This skill should be used when the user mentions "kubernetes manifest", "k8s yaml", "deployment not ready", "pod…
sigistry/marketplace · plugins/code-auditor/skills/architecture-diagramming/SKILL.md · This skill should be used when the user asks to "generate architecture diagrams", "create dependency graph", "draw…
jeremylongshore/tons-of-skills-marketplace · plugins/ai-agency/hyperflow/skills/audit/SKILL.md · Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a…
suboss87/fdeops · skills/audit/SKILL.md · Audit an inherited engagement or implementation against its evidence. Use when taking over work or joining mid-project…
jasonxudeveloper/nino · .claude/skills/audit/SKILL.md · Run an audit round of Nino with parallel agents in worktrees - layout, redundancy, code, core, security, performance…
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/audit/SKILL.md · Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when…