New: 98,000+ 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

Buying Signal Monitor

by unifapi-agent in unifapi-agent/agents

When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that…

MITAuto-check passedMarketing & SEO

Install Buying Signal Monitor

skills CLI
$ npx skills add unifapi-agent/agents --skill buying-signal-monitor -a claude-code

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

GitHub CLI
$ gh skill install unifapi-agent/agents buying-signal-monitor --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/unifapi-agent/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/social-selling-agent/buying-signal-monitor .claude/skills/buying-signal-monitor && 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
buying-signal-monitor
GitHub stars
589
Token cost
~2.4k tokens
SKILL.md length
1,099 words
Files
3 (incl. references)
Skills in repo
47
Repo updated
First seen
Licence
MIT

At a glance

When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that…

  • Works in 6 steps: Define the signal set — required. From… → Pull recent public activity. Run… → Qualify each match. Resolve X authors… → …
  • Find prospects on Twitter/LinkedIn
  • SKILL.md covers Use UnifAPI for live evidence, Workflow, Lead-scoring rubric and Output: ranked warm-lead list, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Buying Signal Monitor is an agent skill from unifapi-agent/agents. When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that implies a need. Also use on "buying signals," "intent signals," "social listening for sales," "warm leads," "who's looking for a tool like ours," "people switching vendors," "hiring signal," "trigger event," "find prospects on Twitter/LinkedIn," or "monitor for sales triggers." Reads public posts only — read-only…

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/signal-taxonomy.md`).

It sits in Marketing & SEO, covering Social media marketing. It works with LinkedIn and X (Twitter). The repository describes itself as: Open-source marketing agents for Claude, ChatGPT, Codex, OpenClaw & Hermes. One plugin: SEO audits, GEO / AI-visibility, local SEO, KOL pricing, social listening & competitive… The licence is MIT.

When your agent uses it

  • Find prospects on Twitter/LinkedIn
  • Monitor for sales triggers. Reads public posts only — read-only research
  • The operator sends from their own accounts

Example prompts

  • “buying signals,”
  • “intent signals,”
  • “social listening for sales,”
  • “/buying-signal-monitor”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Define the signal set — required. From what the operator sells, write the watch phrases for each signal type and name the target segment…
  2. Pull recent public activity. Run x/tweets/search/recent per phrase (last ~14 days) and linkedin/search/posts for the same intent; for any…
  3. Qualify each match. Resolve X authors with x/users/by/username/{username} and pull account fit with linkedin/companies/{slug}; discard…
  4. Classify by signal type using the taxonomy — active demand, vendor switch, hiring trigger, expansion/funding, or pain vent.
  5. Score warmth with the rubric below. Drop anything stale or off-ICP; keep and rank the rest.
  6. Draft the angle. For each kept lead, write a one-line outreach angle that quotes or references the proving post, so the opener reads as a…

What it can do on your machine

Read from SKILL.md and the folder at commit fb53247. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Buying Signal Monitor loads about 2.4k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 147 tokens; SKILL.md has 1,099 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~147
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

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 unifapi-agent/agents at commit fb53247, republished under its MIT licence (© unifapi-agent). 1,099 words, ~2,417 tokens.

Download SKILL.mdSave it as .claude/skills/buying-signal-monitor/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
buying-signal-monitor
description
When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that implies a need. Also use on "buying signals," "intent signals," "social listening for sales," "warm leads," "who's looking for a tool like ours," "people switching vendors," "hiring signal," "trigger event," "find prospects on Twitter/LinkedIn," or "monitor for sales triggers." Reads public posts only — read-only research; the operator sends from their own accounts.
license
MIT
metadata.author
UnifAPI
metadata.version
1.0.0

Buying Signal Monitor

You are a social-selling researcher who catches public buying intent the moment it appears.

The best time to reach a prospect is the moment they say out loud that they have the problem you solve. People announce intent in public all the time — asking for a tool recommendation, venting about the vendor they're stuck with, or posting a job req that only exists because of a gap. This skill watches the public X/Twitter and LinkedIn surface for those moments and returns a ranked warm-lead list where every lead is anchored to the post that proves intent, plus a tailored outreach angle. Read-only: it finds the signal and preps the opener; the operator sends from their own account.

This is an enhanced skill: it reads live public data through UnifAPI.

Use UnifAPI for live evidence

A "warm lead" is only as good as the public post that proves it. Live search is what separates a verbatim, dated intent signal from a guess about who might be in-market. Use the unifapi skill to connect (OAuth MCP), then call:

  • X/Twitter intent search — x/tweets/search/recent — pull recent public posts matching the intent phrases for each signal type ("anyone recommend a…", "alternative to [competitor]", "migrating off…"); this is the raw demand stream.
  • Qualify the poster — x/users/by/username/{username} — resolve each match's author to followers, bio, verified status, and created_at for role/company/reach context, so an off-ICP or throwaway account drops out before scoring.
  • LinkedIn intent posts — linkedin/search/posts — find public posts from buyers and their teams that signal a project, reorg, or stated pain in the B2B surface X misses.
  • Hiring triggers — linkedin/companies/{slug}/jobs and linkedin/companies/{slug}/job-count — an open role that owns your category (or a backfill that reveals the gap) is a budgeted, dated buying signal; the count trend shows a function ramping.
  • Account fit — linkedin/companies/{slug} — pull industry, headcount band, HQ, and specialties so a signal is weighted by how well the account matches the segment.
  • Corroborate the trigger — news/search — funding, leadership, or expansion items that confirm an account is in motion and sharpen timing; for a full news-driven hook list on one account, hand to account-news-signals.

UnifAPI reads public data only — it reads LinkedIn's public surface via URL slug, never private or logged-in data, and never the operator's own X/LinkedIn accounts. Keep any billing metadata UnifAPI returns so the report can state actual record cost. The X route map lives in ../../unifapi/references/twitter-x.md.

Workflow

  1. Define the signal set — required. From what the operator sells, write the watch phrases for each signal type and name the target segment (industry, size, geography). (Read .agents/product-marketing.md / .claude/product-marketing.md first if it exists.) Don't run on a bare product name; without phrases and a segment, matches are noise. The full phrase library and classification rules live in references/signal-taxonomy.md.
  2. Pull recent public activity. Run x/tweets/search/recent per phrase (last ~14 days) and linkedin/search/posts for the same intent; for any named target accounts pull linkedin/companies/{slug}/jobs + linkedin/companies/{slug}/job-count (hiring triggers) and news/search (corroborating triggers).
  3. Qualify each match. Resolve X authors with x/users/by/username/{username} and pull account fit with linkedin/companies/{slug}; discard anything off-segment or from a non-buyer (job-seeker, vendor, competitor employee) before it reaches scoring.
  4. Classify by signal type using the taxonomy — active demand, vendor switch, hiring trigger, expansion/funding, or pain vent.
  5. Score warmth with the rubric below. Drop anything stale or off-ICP; keep and rank the rest.
  6. Draft the angle. For each kept lead, write a one-line outreach angle that quotes or references the proving post, so the opener reads as a relevant reply rather than a cold pitch.
Show full SKILL.md (514 more words)Show less

Lead-scoring rubric

Warmth = signal strength × fit × recency. Score each factor, multiply, then band. See references/signal-taxonomy.md for the per-signal-type strength anchors.

Factor321
Signal strengthExplicit ask for a tool like yours, or "leaving [competitor]"Naming the pain you solve, or hiring the role that owns itAdjacent topic interest; pain implied, not stated
Fit (ICP)Segment, size, and geo all matchTwo of three matchLoosely adjacent
Recency≤ 3 days4–14 days15–30 days
  • Multiply the three (1–27). Hot ≥ 18, Warm 9–17, Watch < 9. Drop anything > 30 days old or below segment regardless of score.
  • A confirmed signal (verbatim ask) outranks an inferred one (hiring/topic) at the same product score — never let an inferred signal sit in Hot.
  • Tie-break by author reach and decision authority (title seniority where public), then by whether a corroborating second signal exists (e.g. a job post from linkedin/companies/{slug}/jobs plus a complaint post, or a news/search funding item).

Output: ranked warm-lead list

A ranked warm-lead table, then per-lead detail. Lead with the table:

markdown
# Warm Leads — [segment / phrases] (generated YYYY-MM-DD, window: last 14d)

| Rank | Name / handle | Company | Role (public?) | Signal type    | Strength×Fit×Recency | Warmth |
| ---- | ------------- | ------- | -------------- | -------------- | -------------------- | ------ |
| 1    | @jdoe         | Acme    | VP Eng (conf.) | vendor switch  | 3×3×3 = 27           | Hot    |
| 2    | @rkim         | Beta Co | (inferred)     | hiring trigger | 2×2×3 = 12           | Warm   |

Then for each lead:

  • Proving post — verbatim quote or link + date that demonstrates intent.
  • Outreach angle — one line, tied to that post, that reads as a relevant reply.
  • Confidence flag — confirmed (role/company/intent all public) or inferred (any guessed); inferred leads need human verification before outreach.

Close with record cost (UnifAPI billing metadata or best estimate) and the watch phrases used, so the run is re-runnable.

Worked example

Watch phrase "alternative to Calendly" surfaces a 2-day-old X post via x/tweets/search/recent: "anyone got a Calendly alternative that does round-robin without the enterprise upsell?" x/users/by/username/{username} shows bio "Head of RevOps @Acme," 4k followers. Operator sells a scheduling tool with round-robin on the mid tier. Score: strength 3 (explicit ask + competitor named), fit 3 (RevOps at an ICP-size SaaS), recency 3 (2 days) → 27, Hot, confirmed. Angle: "Saw your note on round-robin without the enterprise jump — that's exactly the tier line we drew; happy to show how it's set up."

Guardrails

  • Read-only research. It surfaces public signals and drafts openers; it never sends connection requests, DMs, replies, or any message — the operator sends from their own accounts.
  • Public data only. Reads LinkedIn's public surface via URL slug, never private, logged-in, or connection-gated data; never scrapes behind auth and never touches the operator's own accounts.
  • Confirmed vs inferred: intent inferred from a public post is a hypothesis, not a confirmed need. Quote the source verbatim, cite date and link, and flag inferred (vs. explicit) signals so they are verified before any outreach.
  • A public post is not consent to be contacted. The operator owns compliance with each platform's rules and applicable outreach law.
  • Dated snapshots: reaction counts and follower numbers vary by session and region — treat reach figures as dated, directional estimates, not precise audience sizing. The watch phrases make the run re-runnable.
  • linkedin-account-research (Lead Company Research Agent): build the full account brief once a signal names a worthwhile account.
  • account-news-signals (Lead Company Research Agent): turn news/funding/leadership events into timely hooks for a flagged account.
  • unifapi: the shared data skill — connect MCP and discover the X/LinkedIn/news operations above.

© unifapi-agent, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/social-selling-agent/buying-signal-monitor of unifapi-agent/agents.

  • SKILL.md
  • README.md
  • references/signal-taxonomy.md

Open the folder on GitHubat commit fb53247

Compare with similar skills

Buying Signal Monitor 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.

Buying Signal Monitor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Buying Signal Monitor this skillunifapi-agent/agents589—~2.4kAutomated safety check: PassMIT
Business Contact and Social Links Finderbrowser-act/skills6.1k1 repos~1.6kAutomated safety check: PassMIT
Social Listeninggooseworks-ai/goose-skills1.2k1 repos~1.1kAutomated safety check: PassMIT
Socialcoreyhaines31/marketingskills54k4 repos~4.5kAutomated safety check: PassMIT
Banner Design Systemnextlevelbuilder/ui-ux-pro-max-skill135k1 repos~1.8kAutomated safety check: PassMIT
Social Media Managementmanojbajaj95/claude-gtm-plugin1051 repos~3.9kAutomated safety check: PassMIT

Similar skills

  • Business Contact and Social Links Finder

    browser-act/skills

    Finds a company's official website and social profiles from its name, or collects social links from a website URL, using BrowserAct templates run by a Python script.

    6.1k GitHub starsUsed in 1 repo~1.6k tokens
    Marketing & SEOAuto-check passed

  • Social Listening

    gooseworks-ai/goose-skills

    Monitor brand mentions, competitor activity, and industry conversations across social media and the web

    1.2k GitHub starsUsed in 1 repo~1.1k tokens
    Marketing & SEOAuto-check passed

  • Social

    coreyhaines31/marketingskills

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.

    54k GitHub starsUsed in 4 repos~4.5k tokens
    Writing & ContentAuto-check passed

  • Banner Design System

    nextlevelbuilder/ui-ux-pro-max-skill

    Walks through designing a banner for social media, ads, a website hero or print, from gathering requirements to building 2 or 3 art-direction options in HTML and CSS.

    135k GitHub starsUsed in 1 repo~1.8k tokens
    Frontend & DesignAuto-check passed

  • Social Media Management

    manojbajaj95/claude-gtm-plugin

    Comprehensive social media management for all platforms (LinkedIn, Twitter/X, Instagram, TikTok, Facebook, Pinterest, YouTube).

    105 GitHub starsUsed in 1 repo~3.9k tokens
    Writing & ContentAuto-check passed

  • Ads

    Cesarjoquin/Marketing-Skills

    When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms.

    202 GitHub starsUsed in 1 repo~3.5k tokens
    Marketing & SEOAuto-check passed

More from unifapi-agent/agents

All 47 skills in this repo

  • LLM Mention Tracking

    unifapi-agent/agents

    When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of prompts, and how that share of voice compares to named competitors over…

    589 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Customer Research

    unifapi-agent/agents

    When the user wants to research customers from public communities, or synthesize customer language, pains, and objections.

    589 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Keyword Research

    unifapi-agent/agents

    When the user wants to research keywords, find keyword opportunities, run a keyword gap analysis, build topic clusters, or compare what competitors rank for.

    589 GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Schema

    unifapi-agent/agents

    When the user wants to add, fix, or optimize schema markup and structured data on their site.

    589 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed

  • SEO Audit

    unifapi-agent/agents

    When the user wants to audit, review, or diagnose SEO issues on their site.

    589 GitHub stars~3.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Unifapi

    unifapi-agent/agents

    A skill your agent uses when working with UnifAPI public-data APIs or the UnifAPI MCP server: connecting OAuth MCP clients, discovering operations, calling social/search/scrape/news APIs…

    589 GitHub stars~741 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Buying Signal Monitor

What does Buying Signal Monitor do?

When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that…. Buying Signal Monitor is an agent skill from unifapi-agent/agents. When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that implies a need.

When should I use Buying Signal Monitor?

Buying Signal Monitor fits situations like: find prospects on Twitter/LinkedIn; monitor for sales triggers. Reads public posts only — read-only research; the operator sends from their own accounts.

How do I install Buying Signal Monitor in Claude Code?

Run `npx skills add unifapi-agent/agents --skill buying-signal-monitor -a claude-code`. Or copy the skill folder (skills/social-selling-agent/buying-signal-monitor in unifapi-agent/agents) into .claude/skills/buying-signal-monitor in your project. Claude Code loads it when a task matches its description.

How do I install Buying Signal Monitor in Codex?

Run `npx skills add unifapi-agent/agents --skill buying-signal-monitor -a codex`. Or copy the skill folder (skills/social-selling-agent/buying-signal-monitor in unifapi-agent/agents) into .agents/skills/buying-signal-monitor in your project. Codex loads it when a task matches its description.

Can I use Buying Signal Monitor 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 unifapi-agent/agents --skill buying-signal-monitor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/buying-signal-monitor, .gemini/skills/buying-signal-monitor, .github/skills/buying-signal-monitor and .opencode/skills/buying-signal-monitor in your project.

What does Buying Signal Monitor need to run?

SKILL.md names no scripts, command-line tools or credentials: Buying Signal Monitor is instructions for the agent only.

Does Buying Signal Monitor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Buying Signal Monitor 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 Buying Signal Monitor use?

Buying Signal Monitor 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 Buying Signal Monitor use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Buying Signal Monitor?

Skills that share tags, products or a category with Buying Signal Monitor: Business Contact and Social Links Finder (browser-act/skills, 6.1k stars), Social Listening (gooseworks-ai/goose-skills, 1.2k stars), Social (coreyhaines31/marketingskills, 54k stars) and Banner Design System (nextlevelbuilder/ui-ux-pro-max-skill, 135k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Buying Signal Monitor?

unifapi-agent (a GitHub organization) maintains it in unifapi-agent/agents, which has 589 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on September 5, 2026.

Source: unifapi-agent/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.