Agent skill

Ringer Consumer Tasks

by CALLE-AI in CALLE-AI/awesome-phone-call-agents

Handle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into…

MITAuto-check passed

Install Ringer Consumer Tasks

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill ringer-consumer-tasks -a claude-code

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

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents ringer-consumer-tasks --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/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ringer-consumer-tasks .claude/skills/ringer-consumer-tasks && 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
ringer-consumer-tasks
GitHub stars
107
Token cost
~2.5k tokens
SKILL.md length
1,093 words
Files
6 (incl. scripts, references)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Handle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into…

  • Works in 7 steps: Confirm the user actually wants a real… → Collect the playbook's required fields… → Compose the call with build-task.mjs… → …
  • SKILL.md covers When To Use, When Not To Use, Playbooks and Workflow, plus 5 more sections
  • Runs JavaScript scripts from its folder; calls node; needs CALLE_API_KEY

What it does

Ringer Consumer Tasks is an agent skill from CALLE-AI/awesome-phone-call-agents. Handle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into a precise CALL-E task and a strict structured-result schema, previewing as a dry run, and placing the call only with explicit consent. Includes a Quote Shootout batch mode that calls several businesses and returns per-business results plus a ranked comparison.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/examples.md`, `references/playbooks.md` and `references/safety.md`).

The repository describes itself as: Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents. The licence is MIT.

Example prompts

  • “/ringer-consumer-tasks”

Requirements

  • Node.js
  • A credential in CALLE_API_KEY

Workflow steps

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

  1. Confirm the user actually wants a real phone call placed, and identify the
  2. Collect the playbook's required fields plus any helpful optional ones. Get the
  3. Compose the call with build-task.mjs (below). It returns the exact task
  4. Dry-run preview with place-call.mjs (no --execute). Show the user the
  5. Get explicit consent to place the call. For negotiate-bill and
  6. Place the call with place-call.mjs --execute (requires CALLE_API_KEY). Add
  7. Report the structured result verbatim from the schema fields, plus CALL-E's

What it can do on your machine

Read from SKILL.md and the folder at commit 38d4118. 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

    Ships 2 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    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 these keys or tokens, usually read from environment variables:

    • CALLE_API_KEY

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

Context cost

Ringer Consumer Tasks loads about 2.5k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 1,093 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.4k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 1,093 words, ~2,462 tokens.

Download SKILL.mdSave it as .claude/skills/ringer-consumer-tasks/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
ringer-consumer-tasks
description
Handle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into a precise CALL-E task and a strict structured-result schema, previewing as a dry run, and placing the call only with explicit consent. Includes a Quote Shootout batch mode that calls several businesses and returns per-business results plus a ranked comparison.
license
MIT

Ringer Consumer Tasks

Use this skill when a person wants an AI agent to make a real-world consumer phone call on their behalf and hand back a clean, structured outcome — the new monthly price, a cancellation confirmation number, the booked time, the refund amount, the quote. It packages the prompt-engineering and the structured-output contract for six common, high-friction call types plus a free-form one.

This is a composition + safety skill. It does not create a phone provider, does not manage provider-side recurring schedules, and does not call arbitrary numbers it scraped. It turns a chosen playbook + a few user-supplied fields into a reviewed, consent-gated CALL-E call with a strict result_schema.

When To Use

Use this skill for:

  • negotiating or lowering a bill, waiving a fee, or matching a competitor offer
  • cancelling a subscription or membership past the retention runaround
  • chasing a stuck refund or disputing a charge
  • booking an appointment (dental, restaurant, service) by phone
  • getting a price quote — including calling several businesses to compare (Quote Shootout)
  • asking a business a specific question (hours, stock, policy)
  • a free-form "call X and find out / do Y" task with a custom result contract
  • previewing exactly what an agent will say and return, before any call is placed

When Not To Use

Do not use this skill to:

  • place calls to numbers the user did not provide, or guess/repair phone numbers
  • infer country codes, region, or language — require explicit E.164 and region
  • make a legally binding commitment on the user's behalf without their approval
  • give medical, legal, financial, or emergency advice during a call
  • run mass/robo outreach, sales spam, or anything the recipient has not consented to
  • impersonate the account holder using invented PII, PINs, or card numbers

Playbooks

idGoalRequired fieldsBatch
negotiate-billLower a rate, waive a fee, match/extend a promocompany, goal—
cancel-subscriptionCancel cleanly, get a confirmation numbercompany—
chase-refundRecover a refund/credit or dispute a chargecompany, issue—
book-appointmentBook a slot that fits the user's constraintsbusiness, purpose✓
get-quoteCollect a real price; Quote Shootout ranks manybusiness, service✓
general-inquiryGet straight answers to specific questionsbusiness, question✓
customAny call, with a user-defined result contracttask✓

Run node scripts/build-task.mjs --list for the machine-readable catalog. Field semantics (goal, walkAway, approvalMode, resolution, declineOffers, preferredTimes, collect, …) and every result schema are in references/playbooks.md.

Workflow

  1. Confirm the user actually wants a real phone call placed, and identify the single playbook that fits. If none fit, use custom.
  2. Collect the playbook's required fields plus any helpful optional ones. Get the recipient's phone number in E.164 (e.g. +14155550123) and the region — ask; never guess. Optionally collect the caller's name and a callback number.
  3. Compose the call with build-task.mjs (below). It returns the exact task text, a strict result_schema, and missing_required. If missing_required is non-empty, go back and collect those fields.
  4. Dry-run preview with place-call.mjs (no --execute). Show the user the masked recipient, the task the agent will follow, and the fields it will bring back. This is the default and must happen before any real call.
  5. Get explicit consent to place the call. For negotiate-bill and cancel-subscription, confirm the decision-authority stance (the agent captures offers but does not commit unless the user set an auto-accept limit).
  6. Place the call with place-call.mjs --execute (requires CALLE_API_KEY). Add --poll to wait for the structured result; calls can take minutes.
  7. Report the structured result verbatim from the schema fields, plus CALL-E's completion_confidence and a one-line summary. If it did not resolve, offer a single escalated follow-up rather than looping.
Show full SKILL.md (502 more words)Show less

Scripts

Compose the task + strict schema (pure, offline, never dials):

bash
node scripts/build-task.mjs \
  --playbook negotiate-bill \
  --values '{"company":"Xfinity","currentAmount":"95","goal":"lower","leverage":"AT&T Fiber offers $55/mo for the same speed; 4-year customer","walkAway":"yes","approvalMode":"ask"}' \
  --caller "Alex Rivera" --callback "+14155550100" > plan.json

For Quote Shootout, add --batch on a batchable playbook to get a per-business recipient_result_schema plus an aggregate call-level result_schema (cheapest business, potential savings):

bash
node scripts/build-task.mjs --playbook get-quote \
  --values '{"service":"front brake pads + rotors, 2018 Honda Civic; out-the-door price","timeframe":"this week"}' \
  --batch > plan.json

For a non-English call, add --language (e.g. --language Spanish) so the task instructs the agent to run the whole conversation in that language, and pass the matching CALL-E --region/--locale to place-call.mjs (e.g. --region MX --locale es-MX). CALL-E supports English plus Hindi, Arabic, Vietnamese, German, Japanese, French, Spanish, and Portuguese in their respective regions.

Preview, then place (dry-run by default; --execute places the real call):

bash
# 1) Dry run — prints the plan with masked numbers, places NO call:
node scripts/place-call.mjs --body plan.json --to-phone +14155550123

# 2) After consent — place it and wait for the structured result:
CALLE_API_KEY=calle_live_… \
node scripts/place-call.mjs --body plan.json --to-phone +14155550123 --execute --poll

# Quote Shootout: repeat --to-phone per business (batch is auto-detected):
CALLE_API_KEY=calle_live_… node scripts/place-call.mjs --body plan.json \
  --to-phone +14155550123 --to-phone +14155550188 --to-phone +14155550190 --execute --poll

Alternative placement: for a quick goal-only call without a custom schema, the CALL-E CLI works too — calle call start --to-phone +14155550123 --goal "<task>" then calle call status --run-id <run_id>. Use place-call.mjs (the API path) whenever you want the strict structured result this skill's schemas define.

Provider Boundary

This skill prepares and optionally executes CALL-E create-call requests of this shape (one call task; one or more recipients for batch):

json
{
  "task": "Composed from the playbook + user fields…",
  "recipients": [{ "phones": ["+14155550123"], "region": "US", "locale": "en-US" }],
  "result_schema": { "type": "object", "additionalProperties": false, "required": ["outcome"], "properties": { "…": {} } },
  "recipient_result_schema": { "…": "present only in batch / Quote Shootout" }
}

Result schemas are strict: CALL-E rejects any property not declared in properties before returning structured_result, so the output is always exactly the contract above.

Decision Authority (human-in-the-loop)

The negotiate-bill and cancel-subscription tasks encode who may say yes:

  • Ask me (default): the agent may negotiate and capture the exact best offer but must not commit — it tells the rep the user will confirm shortly.
  • Autonomous under a limit (approvalMode: "auto", autoAcceptBelow: <n>): the agent may accept an offer at or below the stated monthly amount.

Never place an autonomous-commit call without the user explicitly choosing it and setting the limit.

Safety Rules

Read references/safety.md for the full contract. Always:

  • Treat a phone call as a real-world side effect; require explicit user intent.
  • Require caller-provided E.164 numbers and region; never guess or repair them.
  • Every generated task opens with a fixed AI disclosure (build-task.mjs states the agent must disclose it is an AI assistant at the start); do not remove or weaken it.
  • Dry-run first; place a real call only after the user consents to that exact plan.
  • Never invent account numbers, PINs, card numbers, or personal details; if asked for something not provided, the agent says it does not have it on hand.
  • Do not make a binding commitment unless the user granted decision authority.
  • Mask phone numbers in summaries; do not expose API keys or full numbers. The key is sent only to CALL-E's official host: place-call.mjs allowlists CALLE_BASE_URL (official *.heycall-e.com or localhost) and refuses to send the bearer token to any other origin.
  • A live create carries a content-bound Idempotency-Key (a hash of the recipients + task + schema), so a lost response + rerun of --execute dedups instead of placing a second call.
  • Do not claim a call happened or a result was achieved unless CALL-E returned it.
  • Do not give medical, legal, financial, or emergency advice on the call.

References

  • references/playbooks.md: every playbook's fields, option values, and result schema.
  • references/safety.md: consent, PII, decision-authority, and phone-number rules.
  • references/examples.md: worked end-to-end examples (compose → dry-run → execute) with sample structured results.

© CALLE-AI, 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 5 other files (scripts, references) in skills/ringer-consumer-tasks of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/examples.md
  • references/playbooks.md
  • references/safety.md
  • scripts/build-task.mjs
  • scripts/place-call.mjs

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Ringer Consumer Tasks 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.

Ringer Consumer Tasks compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ringer Consumer Tasks this skillCALLE-AI/awesome-phone-call-agents107—~2.5kAutomated safety check: PassMIT
Error Handlingaffaan-m/ECC277k1 repos~2.7kAutomated safety check: PassMIT
Billing Automationwshobson/agents40k13 repos~473Automated safety check: PassMIT
Error Handlingthedaviddias/Front-End-Checklist74k—~416Automated safety check: PassMIT
Error Handlingaffaan-m/ECC276k—~2.4kAutomated safety check: PassMIT
Customer Billing Opsaffaan-m/ECC277k2 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Error Handling

    affaan-m/ECC

    Patterns for robust error handling across TypeScript, Python, and Go.

    277k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • Billing Automation

    wshobson/agents

    Covers building subscription billing: billing cycles, subscription states, invoice generation, proration, tax handling and dunning for failed payments.

    40k GitHub starsUsed in 13 repos~473 tokens
    Backend & APIsAuto-check passed
  • Error Handling

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Implement proper error handling.

    74k GitHub stars~416 tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Error Handling

    affaan-m/ECC

    TypeScript、Python、Goにわたる堅牢なエラー処理のパターン。型付きエラー、エラー境界、リトライ、サーキットブレーカー、ユーザー向けエラーメッセージをカバーします。

    276k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Operate customer billing workflows such as subscriptions, refunds, churn triage, billing-portal recovery, and plan analysis using connected billing tools like Stripe.

    277k GitHub starsUsed in 2 repos~1.1k tokens
    Backend & APIsAuto-check passed
  • Python Error Handling

    wshobson/agents

    Python error handling patterns including input validation, exception hierarchies, and partial failure handling.

    40k GitHub stars~1.5k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

More from CALLE-AI/awesome-phone-call-agents

All 101 skills in this repo
  • Accessible Outing Verifier

    CALLE-AI/awesome-phone-call-agents

    Demonstrates advisory accessibility-planning checks with offline fixtures and a proposed bounded CALL-E workflow; use for exploring unknown or qualified venue claims without making calls.

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Ground Truth Gate

    CALLE-AI/awesome-phone-call-agents

    A skill your agent uses when an agent holds some evidence for a physical-world claim but the evidence is broader, narrower, or older than the exact question asked, and it must first decide whether a…

    107 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Is It Accessible

    CALLE-AI/awesome-phone-call-agents

    Call a venue and ask the accessibility questions that matter to one specific person — step-free entry, hearing loop, guide dogs, quiet hours, changing places — then return a per-need verdict backed…

    107 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed
  • Landmark Navigation Assist

    CALLE-AI/awesome-phone-call-agents

    Turns a pre-written, building-level location config into a CALL-E outbound phone-call task that guides a delivery driver through the last few hundred metres to a specific building using landmarks…

    107 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Research Gap Call Verifier

    CALLE-AI/awesome-phone-call-agents

    Turn cited business research into a bounded, approval-gated phone-call plan that asks only unresolved factual questions, then reconcile CALL-E-compatible results without treating voicemail, refusal…

    107 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • Structured Outcome Followup Call

    CALLE-AI/awesome-phone-call-agents

    Place a goal-driven CALL-E call that collects specific structured answers, score those answers against a deterministic rubric you supply, and conditionally trigger a follow-up action — all runnable…

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Ringer Consumer Tasks

What does Ringer Consumer Tasks do?

Handle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into…. Ringer Consumer Tasks is an agent skill from CALLE-AI/awesome-phone-call-agents. Handle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into a precise CALL-E task and a strict structured-result schema, previewing as a dry run, and placing the call only with explicit consent.

How do I install Ringer Consumer Tasks in Claude Code?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill ringer-consumer-tasks -a claude-code`. Or copy the skill folder (skills/ringer-consumer-tasks in CALLE-AI/awesome-phone-call-agents) into .claude/skills/ringer-consumer-tasks in your project. Claude Code loads it when a task matches its description.

How do I install Ringer Consumer Tasks in Codex?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill ringer-consumer-tasks -a codex`. Or copy the skill folder (skills/ringer-consumer-tasks in CALLE-AI/awesome-phone-call-agents) into .agents/skills/ringer-consumer-tasks in your project. Codex loads it when a task matches its description.

Can I use Ringer Consumer Tasks 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 CALLE-AI/awesome-phone-call-agents --skill ringer-consumer-tasks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ringer-consumer-tasks, .gemini/skills/ringer-consumer-tasks, .github/skills/ringer-consumer-tasks and .opencode/skills/ringer-consumer-tasks in your project.

What does Ringer Consumer Tasks need to run?

Going by SKILL.md and its folder, Ringer Consumer Tasks needs JavaScript for the scripts in its folder, the command-line tools its instructions call (node) and credentials named CALLE_API_KEY. Our summary lists: Node.js; A credential in CALLE_API_KEY.

Does Ringer Consumer Tasks 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 Ringer Consumer Tasks 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ringer Consumer Tasks use?

Ringer Consumer Tasks 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 Ringer Consumer Tasks use?

About 2.5k tokens (SKILL.md is roughly 9.8k 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 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Ringer Consumer Tasks?

Skills that share tags, products or a category with Ringer Consumer Tasks: Error Handling (affaan-m/ECC, 277k stars), Billing Automation (wshobson/agents, 40k stars), Error Handling (thedaviddias/Front-End-Checklist, 74k stars) and Error Handling (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ringer Consumer Tasks?

CALLE-AI (a GitHub organization) maintains it in CALLE-AI/awesome-phone-call-agents, which has 107 GitHub stars. The repository holds 101 skills in this directory. The repository was last updated on October 10, 2026.

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