text-classification SKILL.md skillA
text-classification from scdenney/open-science-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add scdenney/open-science-skills/text-classification@git:20261019.3e1eabePins git:20261019.3e1eabe in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- scdenney/open-science-skills
- Path
plugin/skills/text-classification/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261019.3e1eabe, committed Oct 19, 2026
- First version recorded
- Jul 2, 2026
- Size
- 17,172 bytes
- Repository stars
- 69
- License
- a license file GitHub does not identify
Advises on setting up LLM-based text classification as a validated measurement design. Covers codebook construction, learning-regime and model choice, prompt construction, validation against human coding with kappa and F1, hybrid human-LLM review, downstream measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline for repeated free text against a closed codebook. Use when the user wants to classify, code, or label text at scale. Category discovery goes…
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
# LLM-Based Text Classification for Social Science Research ## Instructions Treat the classifier as a measurement instrument the user is designing, not a script to write. Work through the decisions below with the user in this order, explain the trade-off and the governing standard at each, and record the choice and its rationale. Code comes after the codebook, regime, model, and validation plan are settled. If the categories are not yet known and finding them is the goal, this is discovery — route to `topic-modeling`. ### 1. Codebook Design - Start from the population, sampling frame, and (for experimental data) the treatment condition each response comes from. These constrain which categories can plausibly exist and which subgroups any bias assessment must cover. LLM classification extends the open-ended coding tradition in survey methodology rather than replacing it (Geer 1988; Lupia 2018). - The codebook is the most consequential decision in the pipeline. LLMs given loose instructions fall back on general-purpose definitions instead of the researcher's operationalization (Halterman & Keith 2025). - Give each code five components (adapted from Halterman & Keith 2025): …
Read the whole file at its exact version.
How to install
mdr add scdenney/open-science-skills/text-classification@sha256:9e0e3b7e0932c260The line at the top of this page pins the label git:20261019.3e1eabe, 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_wbpno6dzu3tilfs7)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jul 2, 2026 and Oct 19, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261019.3e1eabe latest | 2026-10-19 | 3e1eabe | 17,172 B | A | view · diff |
| git:20261008.697c89f | 2026-10-08 | 697c89f | 17,203 B | A | view · diff |
| git:20260909.08bf795 | 2026-09-09 | 08bf795 | 23,038 B | A | view · diff |
| git:20260905.c12f077 | 2026-09-05 | c12f077 | 23,143 B | A | view · diff |
| git:20260905.39e8276 | 2026-09-05 | 39e8276 | 23,112 B | A | view · diff |
| git:20260902.8289c42 | 2026-09-02 | 8289c42 | 22,654 B | A | view · diff |
| git:20260808.46edbfc | 2026-08-08 | 46edbfc | 19,735 B | A | view · diff |
| git:20260702.539af7b | 2026-07-02 | 539af7b | 19,279 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 (17172 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
scdenney/open-science-skills · 69 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wbpno6dzu3tilfs7 GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/text-classification GET https://markdownregistry.com/api/v1/blob/9e0e3b7e0932c26087b0e8754e176f32c6945acc4c580419d423f16a9ca08399
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.
More from scdenney/open-science-skills
Every file in scdenney/open-science-skills