Agent skill

Service Dispatch Call

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

Call a service vendor to ask whether they can take a job, when they can attend, and what it costs, return the answer as validated structured data, and hand any commitment to a human before it is…

MITAuto-check passedMarketing & SEO

Install Service Dispatch Call

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill service-dispatch-call -a claude-code

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

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents service-dispatch-call --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/service-dispatch-call .claude/skills/service-dispatch-call && 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
service-dispatch-call
GitHub stars
107
Token cost
~1.8k tokens
SKILL.md length
1,069 words
Files
7 (incl. references)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Call a service vendor to ask whether they can take a job, when they can attend, and what it costs, return the answer as validated structured data, and hand any commitment to a human before it is…

  • Works in 10 steps: Confirm the dispatch is authorized: the… → Extract the dispatch fields listed under… → Reserve an idempotency key derived from… → …
  • Maintenance dispatch
  • SKILL.md covers When To Use, When Not To Use, Core Workflow and Required Fields, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Service Dispatch Call is an agent skill from CALLE-AI/awesome-phone-call-agents. Call a service vendor to ask whether they can take a job, when they can attend, and what it costs, return the answer as validated structured data, and hand any commitment to a human before it is accepted. Use for maintenance dispatch, repair triage, contractor availability checks, and quote gathering.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/ambiguous-outcomes.md`, `references/call-brief.md` and `references/examples.md`).

It sits in Marketing & SEO, covering Schema markup. The repository describes itself as: Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents. The licence is MIT.

When your agent uses it

  • Maintenance dispatch
  • Contractor availability checks
  • Quote gathering

Example prompts

  • “/service-dispatch-call”

Workflow steps

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

  1. Confirm the dispatch is authorized: the job exists, and the vendor is on the authorized contact list for this purpose.
  2. Extract the dispatch fields listed under Required Fields. Ask for anything missing. Do not infer a phone number, a trade, or a location…
  3. Reserve an idempotency key derived from the dispatch's own identifier, not from the current timestamp or a fresh random value. See…
  4. Record the dispatch as queued before dialling, so a call that is accepted but never reported is still visible.
  5. Build the call brief from references/call-brief.md. The brief opens with a disclosure and refers to the job by an opaque reference, never…
  6. Declare the result schema before placing the call. See references/result-schema.md.
  7. Place exactly one call.
  8. Validate the returned result against the declared schema. Drop fields you did not ask for. Refuse values outside the declared options…
  9. Classify the outcome as answered, declined, no_answer, or unknown.
  10. If the result contains a cost, a commitment, or a low-confidence field, raise it for human approval and stop. Report the reason.

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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Service Dispatch Call loads about 1.8k tokens when it runs, and up to ~7k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 1,069 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7k

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 CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 1,069 words, ~1,822 tokens.

Download SKILL.mdSave it as .claude/skills/service-dispatch-call/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
service-dispatch-call
description
Call a service vendor to ask whether they can take a job, when they can attend, and what it costs, return the answer as validated structured data, and hand any commitment to a human before it is accepted. Use for maintenance dispatch, repair triage, contractor availability checks, and quote gathering.
license
MIT

Service Dispatch Call

Use this skill when an agent needs to phone a service vendor about a specific job and bring back a decision-ready answer, such as "find out if the plumber can attend unit 12B today and what it costs."

service-dispatch-call is a purpose-bound outbound workflow skill. It places exactly one call per authorized dispatch, asks a bounded set of questions, and returns a structured result. It does not book the job, accept a quote, agree to a price, or promise the vendor anything. Those are commitments, and commitments belong to a person.

The distinction this skill exists to enforce: gathering an answer is not the same as acting on it.

When To Use

Use this skill for:

  • maintenance and repair dispatch, where a job must be matched to a vendor by phone
  • availability checks against a shortlist of vendors
  • quote gathering, where the price is unknown until someone is asked
  • ETA confirmation for an already-accepted job
  • any outbound call whose output must be machine-readable rather than a transcript

When Not To Use

Do not use this skill to:

  • accept a quote, confirm a booking, or agree to any cost during the call
  • call a vendor who is not on the caller's authorized contact list
  • call a number the user supplied for a different purpose in an earlier, unrelated request
  • redial a call whose outcome is unknown
  • work around a missing price by asking the vendor to start anyway
  • read tenant, patient, customer, or resident personal details to the vendor
  • negotiate, counter-offer, or discuss a competitor's quote
  • place a call when the required job fields are incomplete

Core Workflow

  1. Confirm the dispatch is authorized: the job exists, and the vendor is on the authorized contact list for this purpose.
  2. Extract the dispatch fields listed under Required Fields. Ask for anything missing. Do not infer a phone number, a trade, or a location from earlier context.
  3. Reserve an idempotency key derived from the dispatch's own identifier, not from the current timestamp or a fresh random value. See references/idempotency.md.
  4. Record the dispatch as queued before dialling, so a call that is accepted but never reported is still visible.
  5. Build the call brief from references/call-brief.md. The brief opens with a disclosure and refers to the job by an opaque reference, never by an address or a person's name.
  6. Declare the result schema before placing the call. See references/result-schema.md.
  7. Place exactly one call.
  8. Validate the returned result against the declared schema. Drop fields you did not ask for. Refuse values outside the declared options rather than coercing them.
  9. Classify the outcome as answered, declined, no_answer, or unknown.
  10. If the result contains a cost, a commitment, or a low-confidence field, raise it for human approval and stop. Report the reason.

Use this shape:

text
authorize -> reserve -> record queued -> call -> validate -> classify -> approve or stop

Required Fields

For each dispatch, require:

  • jobReference - an opaque identifier the vendor can quote back
  • trade - what kind of vendor this is, for example plumbing
  • problemSummary - one sentence, free of personal details
  • vendorPhoneNumber - E.164, from the authorized contact list
  • preferredWindow - when the job could be attended

Phone numbers must be E.164. Mask them in every user-facing summary. Never write a phone number into a log, an audit record, or a commit.

The Result Schema

Declare what a valid answer looks like before the call, not after. A minimal schema:

FieldTypeNotes
availableone of yes, no, maybeclosed set, never free text
earliest_eta_hoursintegerbound it locally, see below
quoted_amount_textstringas spoken, never parsed into a number by the agent
callback_requiredbooleanvendor will confirm later

Two rules that matter more than they look:

  • Validate more strictly than you transmit. -5 is a valid integer but not a valid ETA. Enforce bounds locally and strip unsupported schema keywords before sending, because an unrecognized keyword can cause the provider to reject the whole call.
  • maybe is an answer, not a yes. Route it to a human. Do not let a fallback, a default, or a retry turn an ambiguous answer into a decision.

Full guidance in references/result-schema.md.

Show full SKILL.md (392 more words)Show less

Ambiguous Outcomes

A call whose outcome is unknown is the most dangerous state in a workflow that spends money. It is not an error to retry.

  • Classify it as unknown and stop.
  • Do not redial. A vendor who was already reached and quoted a price will quote it again, and now two commitments exist for one job.
  • Surface it for a person to reconcile.

Read references/ambiguous-outcomes.md before adding any retry path.

Human Approval Gate

Raise for approval, and do not proceed, when any of these hold:

  • the result contains a quoted amount or any other cost
  • the vendor committed to a time that creates an obligation
  • a confidence score, where the provider reports one, is below the configured threshold
  • any declared field failed validation
  • the outcome is unknown

When presenting the approval, state why it is required before showing the answer being decided on. A reviewer who reads the price first is anchored by it.

Take the approver's identity from the authenticated session. Never from the request body, and never from anything said on the call.

Safety Rules

Read references/safety.md for the full contract.

Always follow these rules:

  • Phone calls are real-world side effects and cost money.
  • Do not place a call unless the user clearly requested this dispatch.
  • Do not call any number except the authorized vendor number for this job.
  • Do not place a second call for one authorized dispatch.
  • Do not disclose tenant, resident, customer, or patient identity, address, or contact details to the vendor.
  • Do not store transcripts, recordings, or the recipient's number unless the user has a stated retention basis for them.
  • Do not write an answer given on a phone call into an audit record. Record the field names, not the values a stranger spoke.
  • Do not expose tokens, credentials, or callback URLs.
  • If authorization, required fields, or the vendor's identity are ambiguous, stop instead of guessing.

Output Format

After a completed dispatch, report:

  • job reference and trade
  • masked vendor number
  • outcome classification
  • the validated fields, and any field that failed validation
  • whether an approval was raised, and the reason
  • the idempotency key used

If no call was placed, report:

  • status: not called
  • the exact blocker
  • what the user must provide or authorize next

Never state that a vendor is booked. This skill produces an answer and an approval request. Booking is a separate, human-authorized action.

© 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 6 other files (references) in skills/service-dispatch-call of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/ambiguous-outcomes.md
  • references/call-brief.md
  • references/examples.md
  • references/idempotency.md
  • references/result-schema.md
  • references/safety.md

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Service Dispatch Call 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.

Service Dispatch Call compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Service Dispatch Call this skillCALLE-AI/awesome-phone-call-agents107—~1.8kAutomated safety check: PassMIT
SEO GeoReScienceLab/opc-skills1.8k4 repos~2.1kAutomated safety check: PassApache-2.0
GEO-First SEO Audit Toolzubair-trabzada/geo-seo-claude11k—~2.8kAutomated safety check: NotesMIT
SEO Optimizerailabs-393/ai-labs-claude-skills4551 repos~3.2kAutomated safety check: PassMIT
Portaljs Add Dcatdatopian/portaljs2.4k1 repos~1.8kAutomated safety check: PassMIT
Schema Markupfreekmurze/dotfiles1k15 repos~1.2kAutomated safety check: PassNone

Similar skills

  • SEO Geo

    ReScienceLab/opc-skills

    SEO & GEO (Generative Engine Optimization) for websites. An agent skill from ReScienceLab/opc-skills.

    1.8k GitHub starsUsed in 4 repos~2.1k tokens
    Marketing & SEOAuto-check passed
  • GEO-First SEO Audit Tool

    zubair-trabzada/geo-seo-claude

    Audits a website for AI search visibility across ChatGPT, Claude, Perplexity and Google AI Overviews while checking traditional SEO, schema and E-E-A-T content quality.

    11k GitHub stars~2.8k tokensUpdated yesterday
    Marketing & SEOAuto-check: notes
  • SEO Optimizer

    ailabs-393/ai-labs-claude-skills

    This skill should be used when analyzing HTML/CSS websites for SEO optimization, fixing SEO issues, generating SEO reports, or implementing SEO best practices.

    455 GitHub starsUsed in 1 repo~3.2k tokens
    Marketing & SEOAuto-check passed
  • Portaljs Add Dcat

    datopian/portaljs

    Make a PortalJS portal harvestable by national/EU/US open-data portals — emit standards-compliant DCAT catalog feeds (DCAT 2/3, DCAT-AP, DCAT-US, national profiles) in JSON-LD, Turtle, and RDF/XML…

    2.4k GitHub starsUsed in 1 repo~1.8k tokens
    Marketing & SEOAuto-check passed
  • Schema Markup

    freekmurze/dotfiles

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

    1k GitHub starsUsed in 15 repos~1.2k tokens
    Marketing & SEOAuto-check passed
  • Geo

    liangdabiao/GEO-Content-Optimizer-Skill

    完整的 GEO(生成式引擎优化)服务流水线:给一个产品官网 URL 和介绍材料, 做站点诊断与 AI 答案采样、生成带验收标准的执行工单、产出可直接部署的资产 (llms.txt / JSON-LD / 定义块 / FAQ / 内容大纲与初稿)、自动验收工单是否闭环、 并打包成可直接发给客户的交付物。可按周期复跑,做长期 GEO 运营与月报。

    205 GitHub starsUsed in 1 repo~2.3k tokens
    Marketing & SEOAuto-check: notes

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

Categories

Questions about Service Dispatch Call

What does Service Dispatch Call do?

Call a service vendor to ask whether they can take a job, when they can attend, and what it costs, return the answer as validated structured data, and hand any commitment to a human before it is…. Service Dispatch Call is an agent skill from CALLE-AI/awesome-phone-call-agents. Call a service vendor to ask whether they can take a job, when they can attend, and what it costs, return the answer as validated structured data, and hand any commitment to a human before it is accepted.

When should I use Service Dispatch Call?

Service Dispatch Call fits situations like: maintenance dispatch; contractor availability checks; quote gathering.

How do I install Service Dispatch Call in Claude Code?

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

How do I install Service Dispatch Call in Codex?

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

Can I use Service Dispatch Call 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 service-dispatch-call -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/service-dispatch-call, .gemini/skills/service-dispatch-call, .github/skills/service-dispatch-call and .opencode/skills/service-dispatch-call in your project.

What does Service Dispatch Call need to run?

SKILL.md names no scripts, command-line tools or credentials: Service Dispatch Call is instructions for the agent only.

Does Service Dispatch Call 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 Service Dispatch Call 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 Service Dispatch Call use?

Service Dispatch Call 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 Service Dispatch Call use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 5.2k tokens, read only when the agent opens those files.

What are the alternatives to Service Dispatch Call?

Skills that share tags, products or a category with Service Dispatch Call: SEO Geo (ReScienceLab/opc-skills, 1.8k stars), GEO-First SEO Audit Tool (zubair-trabzada/geo-seo-claude, 11k stars), SEO Optimizer (ailabs-393/ai-labs-claude-skills, 455 stars) and Portaljs Add Dcat (datopian/portaljs, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Service Dispatch Call?

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.