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

Exception Resolver

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

Resolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval.

MITAuto-check passedBackend & APIs

Install Exception Resolver

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

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

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents exception-resolver --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/exception-resolver .claude/skills/exception-resolver && 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
exception-resolver
GitHub stars
106
Token cost
~1.6k tokens
SKILL.md length
804 words
Files
4 (incl. references)
Skills in repo
98
Repo updated
First seen
Licence
MIT

At a glance

Resolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval.

  • Works in 12 steps: Identify the operational exception and… → Determine what information is missing. → Establish explicit per-run intent for… → …
  • Tasks that involve GraphQL
  • SKILL.md covers Purpose, Workflow, Per-run intent and Phone-number requirements, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Exception Resolver is an agent skill from CALLE-AI/awesome-phone-call-agents. Resolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval. Use when an AI agent encounters a supported operational exception that cannot be resolved from available system data and requires information from an authorized person.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/examples.md`, `references/resolution-workflow.md` and `references/safety.md`).

It sits in Backend & APIs, covering GraphQL. 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

  • Tasks that involve GraphQL

Example prompts

  • “/exception-resolver”

Workflow steps

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

  1. Identify the operational exception and available context.
  2. Determine what information is missing.
  3. Establish explicit per-run intent for the proposed call.
  4. Confirm the destination is an authorized contact and the phone number is valid strict E.164 format.
  5. Check that the call is not a duplicate and that no unresolved prior call already covers the same exception and intent.
  6. Decide whether a phone call is necessary.
  7. Place a CALL-E call only after the required safety checks pass.
  8. Gather the information required to understand the exception.
  9. Treat uncertain, incomplete, failed, cancelled, refused, or ambiguous outcomes as unresolved.
  10. Return the call outcome as structured operational data with masked phone output.
  11. Present the proposed resolution to a human decision-maker.
  12. Apply the resolution only after human approval.

What it can do on your machine

Read from SKILL.md and the folder at commit ae5f78f. 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

Exception Resolver loads about 1.6k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 804 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.6k

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 CALLE-AI/awesome-phone-call-agents at commit ae5f78f, republished under its MIT licence (© CALLE-AI). 804 words, ~1,613 tokens.

Download SKILL.mdSave it as .claude/skills/exception-resolver/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
exception-resolver
description
Resolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval. Use when an AI agent encounters a supported operational exception that cannot be resolved from available system data and requires information from an authorized person.

Exception Resolver

Resolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval.

Purpose

Use this skill when an AI agent detects a supported operational exception that cannot be resolved from available system data and requires information from an authorized person.

Read references/resolution-workflow.md for the detailed exception-resolution workflow and safety requirements.

Workflow

  1. Identify the operational exception and available context.
  2. Determine what information is missing.
  3. Establish explicit per-run intent for the proposed call.
  4. Confirm the destination is an authorized contact and the phone number is valid strict E.164 format.
  5. Check that the call is not a duplicate and that no unresolved prior call already covers the same exception and intent.
  6. Decide whether a phone call is necessary.
  7. Place a CALL-E call only after the required safety checks pass.
  8. Gather the information required to understand the exception.
  9. Treat uncertain, incomplete, failed, cancelled, refused, or ambiguous outcomes as unresolved.
  10. Return the call outcome as structured operational data with masked phone output.
  11. Present the proposed resolution to a human decision-maker.
  12. Apply the resolution only after human approval.

Per-run intent

Before placing a call, the agent MUST have explicit intent for that specific run.

The intent must identify:

  • the exception being resolved
  • the operational objective of the call
  • the authorized party or role to contact
  • the information the agent is permitted to request or disclose
  • the expected resolution or decision
  • whether the call may create an external side effect

Do not infer permission to call merely because an exception exists.

If intent is missing, ambiguous, unauthorized, or outside this skill's supported workflow, do not place the call.

Phone-number requirements

Outbound phone numbers MUST be supplied in strict E.164 format.

Example of valid format:

+14155550123

Do not accept or silently reinterpret local, punctuation-formatted, or whitespace-formatted numbers as E.164.

Examples that must be rejected:

  • 4155550123
  • (415) 555-0123
  • 415-555-0123
  • +1 415 555 0123

Use only authorized contact information.

Phone numbers shown in user-facing output, examples, logs, and status summaries MUST be masked unless the complete number is strictly required for the actual call operation.

Duplicate-call stopping

Before initiating a call, check for an existing active, pending, or recently completed call for the same exception and operational intent.

If a duplicate is detected:

  • do not place another call
  • return a clear duplicate/stopped status
  • preserve the existing call result
  • require explicit new authorization before another call is initiated

Do not repeatedly call a person because an exception remains unresolved.

Ambiguous-outcome stopping

Never treat an ambiguous call outcome as a successful resolution.

Treat these outcomes as unresolved:

  • unknown
  • interrupted
  • contradictory
  • incomplete
  • unavailable
  • unclear
  • missing required confirmation
  • refused
  • failed

When an outcome is ambiguous:

  1. stop the automated resolution workflow
  2. do not invent or infer a resolution
  3. do not automatically repeat the call
  4. return an unresolved/ambiguous status
  5. require human or explicitly authorized workflow review
Show full SKILL.md (316 more words)Show less

Cancellation

A pending call workflow must be cancellable before execution.

If a supported CALL-E cancellation mechanism is available for an active call, use it.

After cancellation:

  • mark the workflow as cancelled
  • do not automatically restart it
  • preserve the cancellation state
  • require explicit new authorization before another call

Safety

  • Use only authorized contact information.
  • Do not expose credentials, secrets, or unnecessary sensitive information during a call.
  • Clearly disclose AI involvement when required.
  • Treat uncertain, incomplete, refused, cancelled, failed, or ambiguous call results as unresolved.
  • Do not allow the phone conversation alone to authorize consequential actions.
  • Keep final resolution decisions under human control.
  • Do not claim that a phone conversation by itself proves identity, consent, authorization, or legal validity.
  • Use fictional or masked phone numbers in examples.

High-stakes boundaries

Do not autonomously make or resolve calls involving high-stakes decisions or actions such as:

  • medical care or treatment decisions
  • emergency response
  • legal decisions or legal representation
  • financial transactions or financial decisions
  • safety-critical operational decisions
  • identity or security verification where a phone call alone is insufficient
  • disclosure of sensitive personal information without appropriate authorization

When high-stakes content is detected:

  1. stop the automated resolution workflow
  2. do not make an unauthorized call
  3. surface the issue to a human/operator
  4. preserve the exception context needed for human review
  5. require explicit authorization before any permitted next action

Example Use Cases

  • Shipment exception follow-up
  • SLA risk investigation
  • Vendor delay clarification
  • Service disruption follow-up
  • Missing operational information

Examples must use fictional or masked phone numbers and must demonstrate authorization, safety checks, cancellation, duplicate stopping, and ambiguous-outcome handling.

Result

The skill should return structured information describing:

  • exception
  • information gathered
  • call outcome
  • proposed resolution
  • confidence
  • human approval status
  • next action

Phone numbers in normal result output should be masked.

References

  • references/resolution-workflow.md
  • Repository safety reference covering consent, E.164 phone-number handling, credential boundaries, cancellation, duplicate-job prevention, and high-stakes boundaries
  • Repository examples/reference patterns for safe phone-call workflows

© 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 3 other files (references) in skills/exception-resolver of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/examples.md
  • references/resolution-workflow.md
  • references/safety.md

Open the folder on GitHubat commit ae5f78f

Compare with similar skills

Exception Resolver 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.

Exception Resolver compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Exception Resolver this skillCALLE-AI/awesome-phone-call-agents106—~1.6kAutomated safety check: PassMIT
API DesignerJeffallan/claude-skills12k2 repos~2kAutomated safety check: PassMIT
Nodejs Backend Patternsever-works/ever-works15818 repos~4kAutomated safety check: PassAGPL-3.0
GraphQL Operations with CodegenChrisWiles/claude-code-showcase6.1k3 repos~1.5kAutomated safety check: PassNone
API Design Principlesjh941213/my-cc-harness12620 repos~3.4kAutomated safety check: PassNone
Supabasecurvenote/curvenote1695 repos~2.2kAutomated safety check: PassCustom licence

Similar skills

  • API Designer

    Jeffallan/claude-skills

    Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.

    12k GitHub starsUsed in 2 repos~2k tokens
    Backend & APIsAuto-check passed

  • Nodejs Backend Patterns

    ever-works/ever-works

    Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices.

    158 GitHub starsUsed in 18 repos~4k tokens
    Backend & APIsAuto-check passed

  • GraphQL Operations with Codegen

    ChrisWiles/claude-code-showcase

    Sets the rules for writing GraphQL queries and mutations in .gql files, running codegen, and using generated Apollo hooks with proper error and loading handling.

    6.1k GitHub starsUsed in 3 repos~1.5k tokens
    Backend & APIsAuto-check passed

  • API Design Principles

    jh941213/my-cc-harness

    REST 및 GraphQL API 설계 원칙 가이드. An agent skill from jh941213/my-cc-harness.

    126 GitHub starsUsed in 20 repos~3.4k tokens
    Backend & APIsAuto-check passed

  • Supabase

    curvenote/curvenote

    A skill your agent uses when doing ANY task involving Supabase.

    169 GitHub starsUsed in 5 repos~2.2k tokens
    Backend & APIsAuto-check passed

  • API And Interface Design

    dzhalaevd/Donatello

    Guides stable API and interface design. An agent skill from dzhalaevd/Donatello.

    135 GitHub starsUsed in 9 repos~2.6k tokens
    Backend & APIsAuto-check passed

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

All 98 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.

    106 GitHub stars~1.4k tokensUpdated today
    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…

    106 GitHub stars~3.3k tokensUpdated today
    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…

    106 GitHub stars~4.3k tokensUpdated today
    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…

    106 GitHub stars~1.6k tokensUpdated today
    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…

    106 GitHub stars~1.7k tokensUpdated today
    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…

    106 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Exception Resolver

What does Exception Resolver do?

Resolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval. Exception Resolver is an agent skill from CALLE-AI/awesome-phone-call-agents. Resolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval.

When should I use Exception Resolver?

Exception Resolver fits situations like: tasks that involve GraphQL.

How do I install Exception Resolver in Claude Code?

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

How do I install Exception Resolver in Codex?

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

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

What does Exception Resolver need to run?

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

Does Exception Resolver 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 Exception Resolver 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 Exception Resolver use?

Exception Resolver is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Exception Resolver use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 Exception Resolver?

Skills that share tags, products or a category with Exception Resolver: API Designer (Jeffallan/claude-skills, 12k stars), Nodejs Backend Patterns (ever-works/ever-works, 158 stars), GraphQL Operations with Codegen (ChrisWiles/claude-code-showcase, 6.1k stars) and API Design Principles (jh941213/my-cc-harness, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Exception Resolver?

CALLE-AI (a GitHub organization) maintains it in CALLE-AI/awesome-phone-call-agents, which has 106 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 8, 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.