New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Lead Qualification

by mrmps in mrmps/classifier-dev

Qualify inbound form submissions against your own ICP with a keyless classification API: one pass for ICP fit, one for buyer intent, then a route (sales, nurture, drop) gated on calibrated confidence.

MITAuto-check passed

Install Lead Qualification

skills CLI
$ npx skills add mrmps/classifier-dev --skill lead-qualification -a claude-code

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

GitHub CLI
$ gh skill install mrmps/classifier-dev lead-qualification --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/lead-qualification .claude/skills/lead-qualification && 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/

Facts

Skill name
lead-qualification
GitHub stars
424
Token cost
~1.5k tokens
SKILL.md length
730 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Qualify inbound form submissions against your own ICP with a keyless classification API: one pass for ICP fit, one for buyer intent, then a route (sales, nurture, drop) gated on calibrated confidence.

  • Works in 4 steps: turn the ICP document into labels → run fit and intent as separate calls → route on the pair, gate on the weaker… → …
  • SKILL.md covers When not to use this, Step 1 — turn the ICP document…, Step 2 — run fit and intent as… and Step 3 — route on the pair,…, plus 2 more sections
  • Calls curl; reaches classifier.dev

What it does

Lead Qualification is an agent skill from mrmps/classifier-dev. Qualify inbound form submissions against your own ICP with a keyless classification API: one pass for ICP fit, one for buyer intent, then a route (sales, nurture, drop) gated on calibrated confidence. Covers turning an ICP document into labels and instructions, and a weekly loop over the low-confidence band that fixes the labels rather than the leads. Use on "qualify these leads", "is this in our ICP", "who should sales call first", "score the demo requests", "clean up the contact-form backlog".

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.

Example prompts

  • “qualify these leads”
  • “is this in our ICP”
  • “who should sales call first”
  • “/lead-qualification”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. turn the ICP document into labels
  2. run fit and intent as separate calls
  3. route on the pair, gate on the weaker confidence
  4. the weekly loop over the unsure band

What it can do on your machine

Read from SKILL.md and the folder at commit b9211dd. 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:

    • curl

    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 no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lead Qualification loads about 1.5k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 730 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
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 b9211dd, republished under its MIT licence (© mrmps). 730 words, ~1,497 tokens.

Download SKILL.mdSave it as .claude/skills/lead-qualification/SKILL.md (or your agent's skills folder).
name
lead-qualification
description
Qualify inbound form submissions against your own ICP with a keyless classification API: one pass for ICP fit, one for buyer intent, then a route (sales, nurture, drop) gated on calibrated confidence. Covers turning an ICP document into labels and instructions, and a weekly loop over the low-confidence band that fixes the labels rather than the leads. Use on "qualify these leads", "is this in our ICP", "who should sales call first", "score the demo requests", "clean up the contact-form backlog".
license
MIT

Qualify inbound leads against your ICP

classifier.dev answers one multiple-choice question about a text and returns a calibrated confidence with it. No key. Two passes over the same submissions, fit and intent, give you a route you can defend and a number saying how much to trust it. It does not write the follow-up email; that stays yours.

When not to use this

  • Fewer than about twenty leads in front of you. Just read them.
  • Scoring a person rather than a request. Job title and company are in scope; who the person is, is not.
  • Enrichment. It classifies the text you give it. If headcount, sector and funding matter, look them up first and paste them into the input.

Step 1 — turn the ICP document into labels

Find the sentences in the ICP doc that state a threshold: sector, headcount, whether they have engineers, what they are replacing. Each becomes one label, written as a full clause. Codes and single words classify badly.

"core ICP: a software or data company with 100 to 2,000 staff and its own engineering team"
"edge of ICP: right kind of company but too small, too large, or no engineering team"
"out of ICP: consumer, agency, reseller, student, or a company with no software to build"
"not enough in the form to tell"

The last two labels matter more than the first two. Every call returns one of your labels, so with no out of ICP and no not enough to tell, a plumber and a blank form both land in a bucket sales will call.

Put the tie-breaks from the ICP doc in instructions, one or two sentences: "Judge the company against the ICP, not the enthusiasm of the message."

Step 2 — run fit and intent as separate calls

One input per lead: form fields and message joined into one string, plus whatever you already know about the company.

curl -s https://classifier.dev/v1/classify \
  -H 'content-type: application/json' \
  -d '{
  "labels": ["ready to buy: names budget, a contract, a renewal or a deadline",
             "actively evaluating: comparing vendors, asking for pricing, security or a trial",
             "early research: learning what the product is, no timeline",
             "not a buyer: job seeker, student, vendor pitch, reseller or a support request"],
  "instructions": "Intent is what the person asked for, not how senior they are.",
  "inputs": ["CTO at a 120-person payments company: trial ran out last week, who do I talk to about an annual contract",
             "no company given: is this free? just looking around",
             "agency, 35 staff: we build sites for clients, would we be able to resell this"]
}'

Real output:

1     ready to buy
0.57  early research
1     not a buyer

Up to 1,000 leads per call; post the fit request the same way. That middle row lands anywhere from 0.5 to 0.7 across runs, which is the review band working.

Step 3 — route on the pair, gate on the weaker confidence

Route from the two labels; let the lower of the two confidences decide whether a person sees it first.

fitintentroute
coreready to buy or evaluatingsales, today
coreearly researchnurture
edgeready to buysales, with the form attached
edgeevaluating or researchnurture
outanythingdrop, except a support request, which goes to support
cannot tellanythingnurture and ask one qualifying question
  • Both at or above 0.9 — route it.
  • Either 0.5 to 0.9 — route it, flag the row, and let no irreversible step fire from it. Nothing is deleted out of this band.
  • Either under 0.5 — a person reads the lead before anything happens.

Dropping a lead is irreversible in practice, so only drop on out of ICP at or above 0.9. Measured on eight real-shaped submissions, the plumber, the student and the reseller came back out of ICP at 0.99, 1.0 and 1.0. The band under 0.9 is not where the mistakes are; it is where the missing labels are.

Show full SKILL.md (260 more words)Show less

Step 4 — the weekly loop over the unsure band

Pull every lead where either confidence fell under 0.9 and read twenty of them. You are not correcting leads. You are looking for the sentence your ICP doc never wrote down.

A real one: a Head of Data at an 1,800-person health insurer scored edge of ICP at 0.31, with scores showing 0.48 edge against 0.40 core — a genuine tie, because the ICP doc said "software or data company" and never said what a large non-software enterprise with an in-house data team is. Adding "core ICP: any company over 500 staff with an in-house data or platform team" moved that lead to the new label at 0.62 on a re-run.

Then check the whole batch, not the lead you fixed. Adding a label splits the probability mass: on that re-run another core lead slipped from 0.85 to 0.77, two core labels now competing for it. Keep the previous output and diff.

Pitfalls

  • Do not put the route in the labels. A label such as send to sales bakes today's policy into the answer. Classify fit and intent; decide the route in your code, where changing it costs nothing.
  • A support request in the sales form is common. Keep it in the intent labels or it will be qualified as a lead.
  • Confidence predicts accuracy among your labels, not fit to the world. An empty message still gets a label; that is what not enough to tell is for.
  • Per IP: 3,000 classifications a minute, 20,000 a day. A 429 carries 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

Files

Just SKILL.md in skills/lead-qualification of mrmps/classifier-dev.

Open the folder on GitHubat commit b9211dd

Compare with similar skills

Lead Qualification 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.

Lead Qualification compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lead Qualification this skillmrmps/classifier-dev424—~1.5kAutomated safety check: PassMIT
Inbound Lead Qualificationgooseworks-ai/goose-skills1.2k1 repos~4.3kAutomated safety check: PassMIT
Inbound Lead QualifierOneWave-AI/claude-skills322—~1.4kAutomated safety check: PassMIT
Form Fillingasgeirtj/system_prompts_leaks69k—~400Automated safety check: PassCC0-1.0
Lead Qualificationgooseworks-ai/goose-skills1.2k1 repos~3.8kAutomated safety check: PassMIT
Inbound Lead Triagegooseworks-ai/goose-skills1.2k1 repos~3.9kAutomated safety check: PassMIT

Similar skills

  • Inbound Lead Qualification

    gooseworks-ai/goose-skills

    Qualifies inbound leads against full ICP criteria — company size, industry, use case fit, role/seniority of the person.

    1.2k GitHub starsUsed in 1 repo~4.3k tokens
    Marketing & SEOAuto-check passed

  • Inbound Lead Qualifier

    OneWave-AI/claude-skills

    Analyze inbound leads (form fills, demo requests) and score based on ICP fit, intent, and urgency.

    322 GitHub stars~1.4k tokensUpdated 5 days ago
    Marketing & SEOAuto-check passed

  • Form Filling

    asgeirtj/system_prompts_leaks

    Fill out online forms (Google Forms, Typeform and similar) or PDF, Word and DocuSign forms; prepare a reviewable draft and get approval before submitting or sending.

    69k GitHub stars~400 tokensUpdated yesterday
    Documents & OfficeAuto-check passed

  • Lead Qualification

    gooseworks-ai/goose-skills

    Lead qualification engine with conversational intake. An agent skill from gooseworks-ai/goose-skills.

    1.2k GitHub starsUsed in 1 repo~3.8k tokens
    Data & AnalyticsAuto-check passed

  • Inbound Lead Triage

    gooseworks-ai/goose-skills

    Triages all inbound leads from a given period — demo requests, free trial signups, content downloads, webinar registrations, chatbot conversations.

    1.2k GitHub starsUsed in 1 repo~3.9k tokens
    Marketing & SEOAuto-check passed

  • Inbound Lead Enrichment

    gooseworks-ai/goose-skills

    Fills in missing data for inbound leads — researches the company, identifies the person's role and seniority, finds other stakeholders at the company, checks for existing CRM relationships, and…

    1.2k GitHub starsUsed in 1 repo~4.6k tokens
    Marketing & SEOAuto-check passed

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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    Auto-check passed

Questions about Lead Qualification

What does Lead Qualification do?

Qualify inbound form submissions against your own ICP with a keyless classification API: one pass for ICP fit, one for buyer intent, then a route (sales, nurture, drop) gated on calibrated confidence. Lead Qualification is an agent skill from mrmps/classifier-dev. Qualify inbound form submissions against your own ICP with a keyless classification API: one pass for ICP fit, one for buyer intent, then a route (sales, nurture, drop) gated on calibrated confidence.

How do I install Lead Qualification in Claude Code?

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

How do I install Lead Qualification in Codex?

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

Can I use Lead Qualification 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 lead-qualification -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lead-qualification, .gemini/skills/lead-qualification, .github/skills/lead-qualification and .opencode/skills/lead-qualification in your project.

What does Lead Qualification need to run?

Going by SKILL.md and its folder, Lead Qualification needs the command-line tools its instructions call (curl).

Does Lead Qualification 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 Lead Qualification 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 Lead Qualification use?

Lead Qualification 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 Lead Qualification 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 Lead Qualification?

Skills that share tags, products or a category with Lead Qualification: Inbound Lead Qualification (gooseworks-ai/goose-skills, 1.2k stars), Inbound Lead Qualifier (OneWave-AI/claude-skills, 322 stars), Form Filling (asgeirtj/system_prompts_leaks, 69k stars) and Lead Qualification (gooseworks-ai/goose-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lead Qualification?

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 6, 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.