quality-scoring SKILL.md skillA
quality-scoring from akaszubski/autonomous-dev is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add akaszubski/autonomous-dev/quality-scoring@git:20260317.e64d556Pins git:20260317.e64d556 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- akaszubski/autonomous-dev
- Path
plugins/autonomous-dev/skills/archived/quality-scoring/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260317.e64d556, committed Mar 17, 2026
- Size
- 8,103 bytes
- Repository stars
- 34
- License
- none declared
Multi-dimensional data assessment for training quality evaluation including IFD scoring, factuality, and reasoning validation. Use when scoring training data or evaluating dataset quality. TRIGGER when: quality scoring, data assessment, IFD, factuality, training data quality. DO NOT TRIGGER when: code quality, test coverage, documentation, non-data tasks.
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
# Quality Scoring Multi-dimensional assessment for training data quality. ## When Activates Quality assessment, data scoring, multi-dimensional evaluation, IFD scoring, factuality checks, reasoning validation, training data prep --- ## Core Concepts ### Quality Scorers (6 Types) Fast to comprehensive scoring approaches: 1. **FastIFD** - Instruction-following difficulty (10-20x faster) 2. **Quality** - LLM-based quality (Qwen3-30B, 0.85 ex/s) 3. **MultiDimensional** - 5-dimension composite 4. **LLMQuality** - Multi-backend (MLX/OpenRouter) 5. **Ensemble** - Cross-model ensemble 6. **Tulu3** - Multi-dimensional reference (training_metrics.py) ### Quality Dimensions (6 Metrics) 1. **IFD Score** (0.0-1.0) - Instruction-following difficulty 2. **Factuality** (0.0-1.0) - Hallucination detection 3. **Reasoning** (0.0-1.0) - Step-by-step logic quality 4. **Diversity** (0.0-1.0) - Dataset-level diversity 5. **Domain** (0.0-1.0) - Domain-specific relevance 6. **LLM Quality** (1-10) - Tulu3 comprehensive score ### Training Thresholds | Type | Quality | IFD | Use Case | |------|---------|-----|----------| | **SFT** | ≥8.0 | ≥0.3 | Base training | …
Read the whole file at its exact version.
How to install
mdr add akaszubski/autonomous-dev/quality-scoring@sha256:bd697ebae164c71cThe line at the top of this page pins the label git:20260317.e64d556, 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_7zf2zflkqegfrhum)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Mar 17, 2026.
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 (8103 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
akaszubski/autonomous-dev · 34 stars · license none declared · pushed 2026-10-04 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_7zf2zflkqegfrhum GET https://markdownregistry.com/api/v1/resolve?ref=akaszubski/autonomous-dev/quality-scoring GET https://markdownregistry.com/api/v1/blob/bd697ebae164c71c8146f1e2f1219678999639449d09e34525d9356d75413f83
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.