Agent skill

Semantic CI Lint

Check every changed hunk of a pull request against conventions written in prose (naming, error handling, logging, docs) with a keyless classifier, and comment only on findings above a confidence…

MITAuto-check passedDevelopment

Install Semantic CI Lint

skills CLI

$ npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install mrmps/classifier-dev semantic-ci-lint --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/semantic-ci-lint .claude/skills/semantic-ci-lint && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "semantic-ci-lint" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/semantic-ci-lint into .claude/skills/semantic-ci-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-ci-lint", 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

$skill-installer install https://github.com/mrmps/classifier-dev/tree/main/skills/semantic-ci-lint

Type 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.

skills CLI

$ npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install mrmps/classifier-dev semantic-ci-lint --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/semantic-ci-lint .agents/skills/semantic-ci-lint && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "semantic-ci-lint" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/semantic-ci-lint into .agents/skills/semantic-ci-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-ci-lint", 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.

skills CLI

$ npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install mrmps/classifier-dev semantic-ci-lint --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/semantic-ci-lint .cursor/skills/semantic-ci-lint && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "semantic-ci-lint" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/semantic-ci-lint into .cursor/skills/semantic-ci-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-ci-lint", 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

$ gemini skills install https://github.com/mrmps/classifier-dev.git --path skills/semantic-ci-lint

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install mrmps/classifier-dev semantic-ci-lint --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/semantic-ci-lint .gemini/skills/semantic-ci-lint && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "semantic-ci-lint" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/semantic-ci-lint into .gemini/skills/semantic-ci-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-ci-lint", 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.

GitHub CLI

$ gh skill install mrmps/classifier-dev semantic-ci-lint

Installs 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).

skills CLI

$ npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/semantic-ci-lint .github/skills/semantic-ci-lint && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "semantic-ci-lint" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/semantic-ci-lint into .github/skills/semantic-ci-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-ci-lint", 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.

skills CLI

$ npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install mrmps/classifier-dev semantic-ci-lint --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mrmps/classifier-dev.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/semantic-ci-lint .opencode/skills/semantic-ci-lint && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "semantic-ci-lint" agent skill from https://github.com/mrmps/classifier-dev/tree/main/skills/semantic-ci-lint into .opencode/skills/semantic-ci-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-ci-lint", 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.

Facts

Skill name: semantic-ci-lint
GitHub stars: 424
Token cost: ~1.5k tokens
SKILL.md length: 420 words
Files: 1
Skills in repo: 21
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Check every changed hunk of a pull request against conventions written in prose (naming, error handling, logging, docs) with a keyless classifier, and comment only on findings above a confidence…

A convention cannot be expressed as a lint rule
SKILL.md covers One convention per call, The script, The workflow and Thresholds, plus 2 more sections
Calls git; reaches classifier.dev; needs GH_TOKEN and GITHUB_TOKEN
Someone says enforce our conventions in CI

What it does

Semantic CI Lint is an agent skill from mrmps/classifier-dev. Check every changed hunk of a pull request against conventions written in prose (naming, error handling, logging, docs) with a keyless classifier, and comment only on findings above a confidence threshold. Use when a convention cannot be expressed as a lint rule, when someone says "enforce our conventions in CI" or "check the PR against the style guide", or when the same review comment keeps being typed by hand.

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.

It sits in Development, covering Linting and formatting and Pull requests. 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.

When your agent uses it

A convention cannot be expressed as a lint rule
Someone says enforce our conventions in CI
Check the PR against the style guide
The same review comment keeps being typed by hand

Example prompts

“enforce our conventions in CI”
“check the PR against the style guide”
“/semantic-ci-lint”

Requirements

Python 3
A credential in GITHUB_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit 629df75. It shows what the files ask for, not the result of running them.

Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- classifier.dev
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- GH_TOKEN
- GITHUB_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Semantic CI Lint loads about 1.5k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 420 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~108
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from mrmps/classifier-dev at commit 629df75, republished under its MIT licence (© mrmps). 420 words, ~1,500 tokens.

Download SKILL.mdSave it as .claude/skills/semantic-ci-lint/SKILL.md (or your agent's skills folder).

name: semantic-ci-lint
description: Check every changed hunk of a pull request against conventions written in prose (naming, error handling, logging, docs) with a keyless classifier, and comment only on findings above a confidence threshold. Use when a convention cannot be expressed as a lint rule, when someone says "enforce our conventions in CI" or "check the PR against the style guide", or when the same review comment keeps being typed by hand.
license: MIT

Lint the conventions a linter cannot express

"Log ids, never a person's name" and "never swallow a failure" are rules a team writes down and then enforces by memory. A classifier can check them: one label and a calibrated confidence per hunk, no prose, cheap on every push.

One convention per call

The instructions field carries the convention in your own words; each call asks about one convention. Four conventions in a single instructions line put a hunk that logs a person's address and name at follows the convention 0.27. The same hunk against the logging convention alone came back breaks the convention, and with the whole hunk and its file path in the input, 1.0.

Keep three labels: follows, breaks, and the convention does not apply to this hunk - the third stops unrelated hunks being forced into a verdict.

The script

.github/semantic-lint.py reads the output of git diff -U0:

python

import json, re, sys, urllib.request

CONVENTIONS = [
    ("logging", "One convention only: a log line may carry ids and counts, never "
                "a person's name, address or anything else that identifies them."),
    ("errors", "One convention only: a failure is raised as a typed error class "
               "and is never swallowed by an empty or logging-only catch block."),
]
LABELS = ["follows the convention", "breaks the convention",
          "the convention does not apply to this hunk"]
BREAKS, COMMENT_AT, NOTE_AT = LABELS[1], 0.9, 0.5

def hunks(diff):
    out, path, buf, line = [], None, [], 0
    for raw in diff.splitlines():
        if raw.startswith("+++ b/"):
            path = raw[6:]
        elif raw.startswith("@@"):
            if buf: out.append((path, line, "\n".join(buf))); buf = []
            m = re.search(r"\+(\d+)", raw)
            line = int(m.group(1)) if m else 0
        elif raw.startswith("+"):
            buf.append(raw[1:])
        elif buf:
            out.append((path, line, "\n".join(buf))); buf = []
    if buf: out.append((path, line, "\n".join(buf)))
    return [h for h in out if h[0] and h[2].strip()]

def judge(texts, rule):
    req = urllib.request.Request("https://classifier.dev/v1/classify",
        data=json.dumps({"labels": LABELS, "instructions": rule,
                         "inputs": [t[:32000] for t in texts]}).encode(),
        headers={"content-type": "application/json", "user-agent": "ci-lint/1"})
    return json.load(urllib.request.urlopen(req))["results"]

chunks = hunks(open(sys.argv[1], encoding="utf-8").read())
texts = [f"{p}:{n}\n{t}" for p, n, t in chunks]   # whole hunk, with its path
found = []
for name, rule in CONVENTIONS:
    for (p, n, _), r in zip(chunks, judge(texts, rule) if texts else []):
        if r["label"] == BREAKS and (r["confidence"] or 0) >= NOTE_AT:
            found.append((p, n, name, r["confidence"]))
for p, n, name, c in found:
    print(f"{'BREAKS' if c >= COMMENT_AT else 'unsure'}  {name:8} {p}:{n}  {c}")
sure = [f for f in found if f[3] >= COMMENT_AT]
if sure:
    with open("comment.md", "w") as f:
        f.write("Convention check\n\n")
        for p, n, name, c in sure:
            f.write(f"- `{p}` line {n}: breaks the **{name}** convention ({c})\n")

On a diff that logs a person's details and swallows a refund failure:

BREAKS  logging  src/api/orders.ts:42  1
BREAKS  errors   src/api/orders.ts:61  1

Against this repository's last three commits, 46 hunks and two conventions, it printed nothing.

The workflow

yaml

name: conventions
on: pull_request
permissions:
  contents: read
  pull-requests: write
jobs:
  conventions:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
      - name: hunks
        run: git diff -U0 ${{ github.event.pull_request.base.sha }}...HEAD > diff.txt
      - name: judge
        run: python3 .github/semantic-lint.py diff.txt | tee -a $GITHUB_STEP_SUMMARY
      - name: comment
        if: hashFiles('comment.md') != ''
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: gh pr comment ${{ github.event.pull_request.number }} --body-file comment.md

fetch-depth: 0 is required or the base commit is missing from the clone. The job never fails the build; an advisory job stays switched on.

Show full SKILL.md (208 more words)Show less

Thresholds

Comment at 0.9 and above, where answers were right 82 to 92% of the time. Put findings between 0.5 and 0.9 in the job summary, where they cost nobody a notification. Below 0.5, say nothing. A bot that is wrong twice gets muted, so the threshold guards the job more than the diff.

Latency is free in CI, so "tier": "smart" is worth it: it re-asks answers under 0.7 of a reasoning model. Six hunks took 1.8 seconds with one escalation, against about 110ms on fast.

Pitfalls

Send the whole hunk, added lines only. One changed line scored 0.57 where the hunk with its path scored 1.0; unchanged context drags the verdict towards the old code.
Write each convention as one sentence naming the wrong thing. Vague rules ("keep it clean") produce vague scores.
Count your classifications. Hunks times conventions is the bill: 46 hunks and two conventions is 92, against a limit of 3,000 a minute.

When not to use this

Skip conventions a real linter already enforces; eslint and ruff are exact and free. Skip generated files and vendored directories. Where a wrong comment on a pull request costs more than the convention is worth, write to the job summary and drop the comment step.

Files

Just SKILL.md in skills/semantic-ci-lint of mrmps/classifier-dev.

Open the folder on GitHubat commit 629df75

Compare with similar skills

Semantic CI Lint 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.

Semantic CI Lint compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Semantic CI Lint this skillmrmps/classifier-dev	424	—	~1.5k	Automated safety check: Pass	MIT	2 days ago
Babysit PR To Pass CIsgl-project/sglang	37k	2 repos	~3k	Automated safety check: Pass	Apache-2.0	today
Changesetbiomejs/biome	26k	—	~839	Automated safety check: Pass	Apache-2.0	today
Pre Pipeline Reviewsuperplanehq/superplane	7.7k	—	~1.2k	Automated safety check: Pass	Custom licence	today
Lint Commit PRTresjs/tres	3.8k	—	~1.1k	Automated safety check: Pass	MIT	yesterday
PR Pushicebear0828/codex-proxy	1.8k	—	~2.2k	Automated safety check: Notes	Custom licence	today

Similar skills

Babysit PR To Pass CI
sgl-project/sglang
Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head.
37k GitHub starsUsed in 2 repos~3k tokens
DevelopmentAuto-check passed
Changeset
biomejs/biome
Official
A skill your agent uses when a Biome change may affect users and you must decide whether it needs a changeset, choose the release level, or create and edit .changeset/.md release-note text.
26k GitHub stars~839 tokensUpdated today
DevelopmentAuto-check passed
Pre Pipeline Review
superplanehq/superplane
Reviews SuperPlane code changes for correctness and reuse, then runs fast Make targets (lint, format, build) that Semaphore CI runs so easy checks do not fail in the pipeline.
7.7k GitHub stars~1.2k tokensUpdated today
DevelopmentAuto-check passed
Lint Commit PR
Tresjs/tres
Lint local changes, auto-fix, conventional commit, and optionally create PR
3.8k GitHub stars~1.1k tokensUpdated yesterday
DevelopmentAuto-check passed
PR Push
icebear0828/codex-proxy
Package the current working changes into a standards-compliant codex-proxy pull request: branch hygiene, commit message linting, CHANGELOG prompt, conventional commit, push, and gh pr create against…
1.8k GitHub stars~2.2k tokensUpdated today
DevelopmentAuto-check: notes
PR Push
icebear0828/codex-proxy
Package the current working changes into a standards-compliant codex-proxy pull request: branch hygiene, commit message linting, CHANGELOG prompt, conventional commit, push, and gh pr create against…
1.8k GitHub stars~2.3k tokensUpdated today
DevelopmentAuto-check: notes

More from mrmps/classifier-dev

All 21 skills in this repo

Bulk Classify
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.
424 GitHub stars~3.1k tokensUpdated 2 days ago
Auto-check passed
Computer Use Action Picker
mrmps/classifier-dev
Pick a browser or desktop agent's next action by choosing among the actions actually on screen instead of inventing one.
424 GitHub stars~1.5k tokensUpdated 2 days ago
Auto-check passed
Content Moderation Gate
mrmps/classifier-dev
Check user-generated text against a written policy before it is published.
424 GitHub stars~1.5k tokensUpdated 2 days ago
Auto-check passed
Context Compaction Keep Or Drop
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…
424 GitHub stars~1.5k tokensUpdated 2 days ago
Auto-check passed
Document Intake Routing
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.
424 GitHub stars~1.5k tokensUpdated 2 days ago
Auto-check passed
Headline Filter Map Reduce
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…
424 GitHub stars~1.5k tokensUpdated 2 days ago
Auto-check passed

Questions about Semantic CI Lint

What does Semantic CI Lint do?

Check every changed hunk of a pull request against conventions written in prose (naming, error handling, logging, docs) with a keyless classifier, and comment only on findings above a confidence…. Semantic CI Lint is an agent skill from mrmps/classifier-dev. Check every changed hunk of a pull request against conventions written in prose (naming, error handling, logging, docs) with a keyless classifier, and comment only on findings above a confidence threshold.

When should I use Semantic CI Lint?

Semantic CI Lint fits situations like: A convention cannot be expressed as a lint rule; someone says enforce our conventions in CI; check the PR against the style guide; the same review comment keeps being typed by hand.

How do I install Semantic CI Lint in Claude Code?

Run `npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a claude-code`. Or copy the skill folder (skills/semantic-ci-lint in mrmps/classifier-dev) into .claude/skills/semantic-ci-lint in your project. Claude Code loads it when a task matches its description.

How do I install Semantic CI Lint in Codex?

Run `npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a codex`. Or copy the skill folder (skills/semantic-ci-lint in mrmps/classifier-dev) into .agents/skills/semantic-ci-lint in your project. Codex loads it when a task matches its description.

Can I use Semantic CI Lint in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mrmps/classifier-dev --skill semantic-ci-lint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/semantic-ci-lint, .gemini/skills/semantic-ci-lint, .github/skills/semantic-ci-lint and .opencode/skills/semantic-ci-lint in your project.

What does Semantic CI Lint need to run?

Going by SKILL.md and its folder, Semantic CI Lint needs the command-line tools its instructions call (git) and credentials named GH_TOKEN and GITHUB_TOKEN. Our summary lists: Python 3; A credential in GITHUB_TOKEN.

Does Semantic CI Lint access the network?

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.

Is Semantic CI Lint safe to install?

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.

What licence does Semantic CI Lint use?

Semantic CI Lint is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Semantic CI Lint use?

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.

What are the alternatives to Semantic CI Lint?

Skills that share tags, products or a category with Semantic CI Lint: Babysit PR To Pass CI (sgl-project/sglang, 37k stars), Changeset (biomejs/biome, 26k stars), Pre Pipeline Review (superplanehq/superplane, 7.7k stars) and Lint Commit PR (Tresjs/tres, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Semantic CI Lint?

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.

Install Semantic CI Lint

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Lint the conventions a linter cannot express

One convention per call

The script

The workflow

Thresholds

Pitfalls

When not to use this

Files

Compare with similar skills

Similar skills

More from mrmps/classifier-dev

Related

Questions about Semantic CI Lint