synthesis-content-quality SKILL.md skillA
synthesis-content-quality from synthesisengineering/synthesis-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add synthesisengineering/synthesis-skills/synthesis-content-quality@v5.0.0Pins v5.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- synthesisengineering/synthesis-skills
- Path
skills/synthesis-content-quality/SKILL.md- Versions recorded
- 5
- Latest version
- v5.0.0, committed Oct 6, 2026
- First version recorded
- Jul 29, 2026
- Size
- 7,061 bytes
- Repository stars
- 23
- License
- Apache-2.0
Detect AI slop and empty substance in prose: model-family fingerprints (Claude, GPT, Gemini, Llama and more), substance and depth tests, combined signals, two-axis calibration, ESL safe-harbor. Use for content quality, slop detection, AI content audits, editorial review and publishing standards.
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
# Content Quality A systematic methodology for evaluating writing quality and identifying slop, with or without AI involvement. The framework targets bad content, not provenance. Ethically authored AI-collaborated content can be excellent; styled empty human content is slop. This skill detects slop. ## Binding rules 1. **Keep four outputs apart:** editorial quality, model-shaped style, technical provenance, authorship. Prose shows only the first two, so no pattern, count, combination or detector score establishes authorship. 2. **Ask the mode first.** Artifact mode (default for editorial work) skips WRAPPER-OPENER and WRAPPER-CLOSER patterns; full-response mode (chat-log forensics) applies all. Wrapper patterns in an artifact audit are false positives. 3. **Literal defects first:** placeholder text, chatbot artifacts, fabricated citations or DOIs, raw markdown, reasoning-tag leakage. Confirm and repair each; a residue shows a tool touched the text, not who wrote it. 4. **Combinations beat counts.** Three matched B2 combos outweigh ten independent indicators; no single indicator proves AI generation. Inherited false-positive estimates are unvalidated hypotheses. …
Read the whole file at its exact version.
How to install
mdr add synthesisengineering/synthesis-skills/synthesis-content-quality@sha256:11e9173ceda2f348The line at the top of this page pins the label v5.0.0, 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.
[](https://markdownregistry.com/a/art_fhezcat7xppv3yac)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 29, 2026 and Oct 6, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v5.0.0 latest | 2026-10-06 | 45bd34b | 7,061 B | A | view · diff |
| v4.2.0 | 2026-08-29 | 07a3710 | 39,286 B | A | view · diff |
| v4.1.0 | 2026-08-23 | 416b582 | 35,931 B | A | view · diff |
| v4.0.0 | 2026-08-22 | 7abe60d | 34,680 B | A | view · diff |
| v4.0.0 | 2026-07-29 | 9b134e7 | 31,068 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7061 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
synthesisengineering/synthesis-skills · 23 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fhezcat7xppv3yac GET https://markdownregistry.com/api/v1/resolve?ref=synthesisengineering/synthesis-skills/synthesis-content-quality GET https://markdownregistry.com/api/v1/blob/11e9173ceda2f348576db9689bf674734088de4f91659b8063593070573492d1
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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.