Sweep a marketplace or catalogue with a keyless classification API: one pass for category, one multi-label pass for prohibited, counterfeit and misstated-condition signals, one for review-abuse…
$ npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mrmps/classifier-dev listing-hygiene-check --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/listing-hygiene-check .claude/skills/listing-hygiene-check && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "listing-hygiene-check" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/listing-hygiene-check into .claude/skills/listing-hygiene-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "listing-hygiene-check", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mrmps/classifier-dev/tree/main/skills/listing-hygiene-checkType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mrmps/classifier-dev listing-hygiene-check --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/listing-hygiene-check .agents/skills/listing-hygiene-check && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "listing-hygiene-check" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/listing-hygiene-check into .agents/skills/listing-hygiene-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "listing-hygiene-check", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mrmps/classifier-dev listing-hygiene-check --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/listing-hygiene-check .cursor/skills/listing-hygiene-check && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "listing-hygiene-check" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/listing-hygiene-check into .cursor/skills/listing-hygiene-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "listing-hygiene-check", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mrmps/classifier-dev.git --path skills/listing-hygiene-check--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mrmps/classifier-dev listing-hygiene-check --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/listing-hygiene-check .gemini/skills/listing-hygiene-check && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "listing-hygiene-check" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/listing-hygiene-check into .gemini/skills/listing-hygiene-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "listing-hygiene-check", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mrmps/classifier-dev listing-hygiene-checkInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/listing-hygiene-check .github/skills/listing-hygiene-check && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "listing-hygiene-check" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/listing-hygiene-check into .github/skills/listing-hygiene-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "listing-hygiene-check", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mrmps/classifier-dev listing-hygiene-check --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/listing-hygiene-check .opencode/skills/listing-hygiene-check && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "listing-hygiene-check" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/listing-hygiene-check into .opencode/skills/listing-hygiene-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "listing-hygiene-check", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
listing-hygiene-checkSweep a marketplace or catalogue with a keyless classification API: one pass for category, one multi-label pass for prohibited, counterfeit and misstated-condition signals, one for review-abuse…
Listing Hygiene Check is an agent skill from mrmps/classifier-dev. Sweep a marketplace or catalogue with a keyless classification API: one pass for category, one multi-label pass for prohibited, counterfeit and misstated-condition signals, one for review-abuse patterns, severity set by the calibrated confidence band, and a queue file only a person acts on. Use on "check these listings", "find counterfeits", "audit the catalogue", "are these reviews fake", or before a category goes live.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Zero-shot text classification over plain HTTP — no API key, no account. One Cloudflare Worker, a CLI, and an MCP server. https://classifier.dev. The licence is MIT.
Read from SKILL.md and the folder at commit 629df75. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curlFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
classifier.devFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Listing Hygiene Check loads about 1.5k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 595 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mrmps/classifier-dev at commit 629df75, republished under its MIT licence (© mrmps). 595 words, ~1,499 tokens.
.claude/skills/listing-hygiene-check/SKILL.md (or your agent's skills folder).classifier.dev tags text against labels you write and returns a score per
label. No key. Three passes over a catalogue export give a category, a set of
policy signals and a review-abuse read, each with a number. It removes nothing
and messages nobody. It fills a queue.
"labels": ["consumer electronics and accessories", "kitchen and home",
"health and supplements", "knives and weapons", "none of these"]Single label. Miscategorisation is an old listing trick, and a category that
disagrees with a signal is a strong review candidate. Keep none of these:
without it every listing lands in a category whatever it sells.
A listing can break two rules at once, so ask for every label that applies.
curl -s https://classifier.dev/v1/classify \
-H 'content-type: application/json' \
-d '{
"labels": ["counterfeit or replica of a known brand",
"restricted or prohibited item: weapons, drugs, live animals",
"unapproved health or medical claim",
"condition misstated: used or refurbished sold as new",
"pushes the buyer to contact or pay off the platform",
"no policy problem found"],
"instructions": "Flag every signal the listing text actually shows. Do not flag a signal that is only implied by the category.",
"multi": true, "max_labels": 3,
"inputs": ["Aple AirPads Pro 1:1 Original Quality, sealed box, same chip as retail. Message us on WhatsApp for bulk pricing.",
"Cast Iron Skillet 26cm, pre-seasoned, oven safe to 260C, made in Portugal, 2.9kg"]
}'Real output. labels holds everything at or above 0.7, most likely first;
scores holds all six either way:
["pushes the buyer to contact or pay off the platform", "counterfeit or replica of a known brand"]
counterfeit 0.79 restricted 0.01 health claim 0.03
condition 0.21 off platform 0.93 no problem 0.22
["no policy problem found"]
every risk score 0.03 or lower no problem 0.72Two labels fired on one listing: the misspelled brand and the off-platform contact are separate violations with separate remedies.
Reviews are their own corpus. Classify review text, max_labels: 2:
"labels": ["paid or incentivised review: free product, refund or discount for the review",
"duplicated or templated text",
"the seller writing as a customer",
"solicits reviews off platform",
"ordinary review, positive or negative"]Measured on six real-shaped reviews: "Got this free in exchange for my honest
review" scored incentivised 0.98; one offering a discount code for any review
fired incentivised 0.98 and off-platform 0.96 together. A negative two-star
review scored ordinary, 0.93 — say in instructions that abuse is not a bad
rating, or the pass becomes a sentiment filter.
Per signal, not per listing. Each label carries its own score:
Nothing is delisted, deleted or messaged by this. A person works the queue.
Clear a listing on the risk scores, not the clean label. Multi-label scores
are independent, and no policy problem found has no reason to be high: clean
listings came back at 0.72, 0.77 and 0.78, with every risk score at 0.04 or
lower. Auto-clear when max(risk scores) < 0.5, never on the clean label.
One JSON object per line, written by your code, never by the classifier:
{"id":"L-101","category":"consumer electronics and accessories","cat_conf":1.0,
"signals":[["off platform",0.93],["counterfeit",0.79]],"severity":"high","action":"none yet"}Keep every score, the ones under 0.5 included. When a reviewer overturns a flag you need the number behind it to say whether the label or the threshold was wrong.
max_labels truncates and 0.7 is the floor. Four problems return three
at max_labels: 3, and a signal at 0.6 is missing from labels entirely.
The scores map has everything; your medium band lives there.labels can be empty. A plain chef's knife listing returned []: no risk
signal reached 0.7 and neither did no policy problem found, at 0.58. Code
that reads labels[0] breaks here. Read scores.confidence field. Each label has its own
score and the bands apply per score; reading confidence here is a KeyError.Retry-After.© mrmps, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/listing-hygiene-check of mrmps/classifier-dev.
Open the folder on GitHubat commit 629df75
Listing Hygiene Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Listing Hygiene Check this skillmrmps/classifier-dev | 424 | — | ~1.5k | Automated safety check: Pass | MIT | |
| List Hygiene Monitoraaron-he-zhu/aaron-marketing-skills | 2.9k | 2 repos | ~3.7k | Automated safety check: Pass | Apache-2.0 | |
| Music Listruvnet/ruflo | 74k | — | ~332 | Automated safety check: Pass | MIT | |
| Semantic Liststhedaviddias/Front-End-Checklist | 74k | — | ~504 | Automated safety check: Pass | MIT | |
| List Structurethedaviddias/Front-End-Checklist | 74k | — | ~438 | Automated safety check: Pass | MIT | |
| Definition Listthedaviddias/Front-End-Checklist | 74k | — | ~449 | Automated safety check: Pass | MIT |
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "watch my list health over time", "flag decaying / unengaged subscribers on a schedule", "why is my open rate drifting down / bounces creeping up", or…
ruvnet/ruflo
List the account's saved music productions with metadata and audiourl
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use semantic list elements.
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use correct list structure.
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use correct definition list structure.
sickn33/agentic-awesome-skills
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase.
mrmps/classifier-dev
Sort many texts into your own categories without reading them, using a keyless HTTP API that returns a calibrated confidence per answer.
mrmps/classifier-dev
Pick a browser or desktop agent's next action by choosing among the actions actually on screen instead of inventing one.
mrmps/classifier-dev
Check user-generated text against a written policy before it is published.
mrmps/classifier-dev
Label each context chunk keep, drop or replace-with-a-pointer and pass the survivors through byte for byte instead of summarising, with key-shaped chunks decided locally and never sent, and a…
mrmps/classifier-dev
Label each page of an intake packet with a document type and a page role before extraction runs, so only confident pages reach an extractor and the rest reach a person.
mrmps/classifier-dev
Filter hundreds or thousands of headlines, search results or feed items against a written brief before opening any of them, using a two-stage cascade that spends a fast model on everything and a…
Sweep a marketplace or catalogue with a keyless classification API: one pass for category, one multi-label pass for prohibited, counterfeit and misstated-condition signals, one for review-abuse…. Listing Hygiene Check is an agent skill from mrmps/classifier-dev. Sweep a marketplace or catalogue with a keyless classification API: one pass for category, one multi-label pass for prohibited, counterfeit and misstated-condition signals, one for review-abuse patterns, severity set by the calibrated confidence band, and a queue file only a person acts on.
Run `npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a claude-code`. Or copy the skill folder (skills/listing-hygiene-check in mrmps/classifier-dev) into .claude/skills/listing-hygiene-check in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a codex`. Or copy the skill folder (skills/listing-hygiene-check in mrmps/classifier-dev) into .agents/skills/listing-hygiene-check in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mrmps/classifier-dev --skill listing-hygiene-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/listing-hygiene-check, .gemini/skills/listing-hygiene-check, .github/skills/listing-hygiene-check and .opencode/skills/listing-hygiene-check in your project.
Going by SKILL.md and its folder, Listing Hygiene Check needs the command-line tools its instructions call (curl).
SKILL.md names 1 domain. In commands or code: classifier.dev; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Listing Hygiene Check is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Listing Hygiene Check: List Hygiene Monitor (aaron-he-zhu/aaron-marketing-skills, 2.9k stars), Music List (ruvnet/ruflo, 74k stars), Semantic Lists (thedaviddias/Front-End-Checklist, 74k stars) and List Structure (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mrmps (a GitHub user) maintains it in mrmps/classifier-dev, which has 424 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.
Source: mrmps/classifier-dev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
