Agent skill

Call Fraud Shield

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

Post-call fraud detection skill. An agent skill from CALLE-AI/awesome-phone-call-agents.

Install Call Fraud Shield

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-fraud-shield -a claude-code

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

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents call-fraud-shield --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/call-fraud-shield .claude/skills/call-fraud-shield && 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/

Paste into Claude Code

Install the "call-fraud-shield" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-fraud-shield into .claude/skills/call-fraud-shield/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-fraud-shield", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-fraud-shield

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-fraud-shield -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents call-fraud-shield --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/call-fraud-shield .agents/skills/call-fraud-shield && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "call-fraud-shield" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-fraud-shield into .agents/skills/call-fraud-shield/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-fraud-shield", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-fraud-shield -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents call-fraud-shield --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/call-fraud-shield .cursor/skills/call-fraud-shield && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "call-fraud-shield" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-fraud-shield into .cursor/skills/call-fraud-shield/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-fraud-shield", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/CALLE-AI/awesome-phone-call-agents.git --path skills/call-fraud-shield

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-fraud-shield -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents call-fraud-shield --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/call-fraud-shield .gemini/skills/call-fraud-shield && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "call-fraud-shield" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-fraud-shield into .gemini/skills/call-fraud-shield/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-fraud-shield", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents call-fraud-shield

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-fraud-shield -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/call-fraud-shield .github/skills/call-fraud-shield && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "call-fraud-shield" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-fraud-shield into .github/skills/call-fraud-shield/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-fraud-shield", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-fraud-shield -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents call-fraud-shield --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/call-fraud-shield .opencode/skills/call-fraud-shield && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "call-fraud-shield" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-fraud-shield into .opencode/skills/call-fraud-shield/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-fraud-shield", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: call-fraud-shield
GitHub stars: 107
Token cost: ~2.7k tokens
SKILL.md length: 728 words
Files: 9 (incl. scripts, references)
Skills in repo: 101
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Post-call fraud detection skill. An agent skill from CALLE-AI/awesome-phone-call-agents.

Tasks that involve Academic paper search
SKILL.md covers Why This Skill Exists, Scientific Foundation, Quick Start and Input, plus 10 more sections
Runs Python scripts from its folder; calls python3
Tasks that involve Anomaly detection

What it does

Call Fraud Shield is an agent skill from CALLE-AI/awesome-phone-call-agents. Post-call fraud detection skill. Analyses a CALL-E transcript for vishing, spam, social engineering, and scam-script patterns using conversational trajectory analysis and a curated scam archetype library. Returns a structured risk card with XAI-explained evidence spans, threat category classification, an escalation-direction assessment, and a recommended action. Grounded in peer-reviewed vishing-detection and adversarial-evasion research (arXiv:2502.03964, arXiv:2609.07151, arXiv:2507.16291).

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `references/example-transcript.json`, `references/examples.md` and `references/research-papers.md`).

It sits in Research & Science, covering Academic paper search and Anomaly detection. It works with arXiv. 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 Academic paper search
Tasks that involve Anomaly detection

Example prompts

“/call-fraud-shield”

Requirements

Python 3

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 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
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

Call Fraud Shield loads about 2.7k tokens when it runs, and up to ~6.3k if it reads all its reference files. Until then it costs about 129 tokens; SKILL.md has 728 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~129
When it runs · the whole SKILL.md, loaded when a task matches: ~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~6.3k

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). 728 words, ~2,705 tokens.

Download SKILL.mdSave it as .claude/skills/call-fraud-shield/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.

name: call-fraud-shield
description: Post-call fraud detection skill. Analyses a CALL-E transcript for vishing, spam, social engineering, and scam-script patterns using conversational trajectory analysis and a curated scam archetype library. Returns a structured risk card with XAI-explained evidence spans, threat category classification, an escalation-direction assessment, and a recommended action. Grounded in peer-reviewed vishing-detection and adversarial-evasion research (arXiv:2502.03964, arXiv:2609.07151, arXiv:2507.16291).
license: MIT

call-fraud-shield

Detect fraud from the transcript — before the damage compounds.

Stop vishing, spam, and scam calls before they extract credentials or money. This skill analyses a call transcript for multi-layered fraud signals — urgency language, authority impersonation, credential extraction attempts, fear induction, and scam-script patterns — then returns a structured risk card with a human-readable explanation and a clear recommended action.

Why This Skill Exists

Traditional keyword-filter fraud detection is fragile: sophisticated social engineering avoids blacklisted words. This skill takes a research-backed trajectory analysis approach — tracking how threat-signal density escalates over the course of a call — which is harder to evade with rephrased or LLM-generated vishing scripts than fixed keyword lists.

The analysis runs in heuristic mode only (labelled analysis_mode: "heuristic" in every output): pattern libraries, archetype matching, and trajectory aggregation, with no external model call. What sets it apart from a plain keyword screener:

4-category threat taxonomy (SPAM, VISHING, SOCIAL_ENGINEERING, SCAM_SCRIPT)
Trajectory analysis — escalation-density scoring across call halves
Scam archetype library — 8 documented scam patterns with harm trajectories
XAI evidence spans — per-signal evidence text plus a readable explanation
Mandatory false-positive disclaimer in every risk card

Scientific Foundation

Research	Relevance
"It Warned Me Just at the Right Moment" arXiv:2502.03964 (CHI EA 2025)	Real-time vishing detection; motivates trajectory-over-single-turn analysis
Vishing-Tactics-Bench arXiv:2609.07151 (2026)	Situation-awareness benchmark; harm-projection field design
Talking Like a Phisher arXiv:2507.16291 (2025)	Adversarial transcripts evade keyword classifiers — justifies low-confidence labelling for keyword heuristics
VishGPT (MIS Quarterly, 2025)	RL-tuned large audio model for vishing detection; reference architecture for a future model-assisted extension

Full citations: references/research-papers.md

Quick Start

Heuristic mode (no external dependencies)

bash

python3 scripts/detect_fraud.py \
  --transcript path/to/transcript.json \
  --dry-run \
  --out /tmp/risk_card.json

With a custom risk threshold

bash

python3 scripts/detect_fraud.py \
  --transcript path/to/transcript.json \
  --threshold 0.40 \
  --out /tmp/risk_card.json

Validate output schema

bash

python3 scripts/validate_risk_card.py --card /tmp/risk_card.json

Input

Any CALL-E transcript (same formats as other skills):

Format A — array of turns:

json

[
  {"call_id": "calle-001", "role": "caller", "text": "This is SecureBank fraud department..."},
  {"call_id": "calle-001", "role": "callee", "text": "What happened?"}
]

Format B — wrapper object:

json

{
  "call_id": "calle-001",
  "transcript": [...]
}

Output — Risk Card

json

{
  "call_id":               "calle-example-001",
  "analysis_timestamp":    "2026-09-15T09:00:00Z",
  "overall_risk_score":    1.0,
  "risk_level":            "CRITICAL",
  "threat_categories":     ["VISHING", "SOCIAL_ENGINEERING", "SCAM_SCRIPT"],

  "trigger_signals": [
    {
      "type":     "credential_request",
      "evidence": "one-time password",
      "weight":   0.55
    },
    {
      "type":     "authority_impersonation",
      "evidence": "Your account has been compromised",
      "weight":   0.40
    }
  ],

  "trajectory_assessment": "No significant escalation detected in conversational trajectory.",
  "harm_projection":       "If the call continues, the next moves likely escalate toward credential extraction or a payment request.",

  "recommended_action":       "TERMINATE_AND_ALERT",
  "xai_explanation":          "Risk level is CRITICAL. Signal 'credential_request' detected (weight 0.55): \"one-time password\". Signal 'authority_impersonation' detected (weight 0.40): \"Your account has been compromised\". Matches known scam-script archetype(s): bank_security_alert.",
  "false_positive_disclaimer":"This is a probabilistic risk signal, not a legal finding. A human must review before any adverse action is taken. Legitimate institutions do not request OTPs, gift cards, or wire transfers by phone.",

  "flags":          ["REQUIRES_HUMAN_REVIEW"],
  "analysis_mode":  "heuristic",
  "dry_run":        false,
  "schema_version": "1.0"
}

(Actual output of the bundled references/example-transcript.json; see references/examples.md for more scenarios.)

Threat Taxonomy

Category	Description	Example
`VISHING`	Voice phishing — caller impersonates a trusted authority	Bank fraud dept, IRS, police
`SPAM`	Unsolicited or consent-violating marketing	Robocalls, prize notifications
`SOCIAL_ENGINEERING`	Urgency, fear, or authority manipulation	"Act now or face arrest"
`SCAM_SCRIPT`	Matches a known documented scam pattern	Lottery, advance-fee, romance

Audio-deepfake (voice-cloning) detection is out of scope: the skill analyses transcript text only and never ingests audio.

Risk Levels & Recommended Actions

Risk Level	Score	Recommended Action	Meaning
`LOW`	< 0.35	`PROCEED`	No significant fraud signals detected
`MEDIUM`	0.35–0.49	`FLAG_FOR_REVIEW`	Weak signals — queue for human review
`HIGH`	0.50–0.84	`CAUTION_ADVISE_USER`	Strong signals — advise the user caution
`CRITICAL`	≥ 0.85	`TERMINATE_AND_ALERT`	Definitive fraud pattern — escalate immediately
`UNKNOWN`	n/a	`FLAG_FOR_REVIEW`	Fewer than 3 turns — the skill abstains rather than guess

Threshold for HIGH is configurable via --threshold (default: 0.50).

Show full SKILL.md (299 more words)Show less

Scam Archetype Library

Eight documented scam patterns ship with the skill (references/scam-archetypes.json):

Archetype	Category	Harm Trajectory
`bank_security_alert`	VISHING	authority → urgency → OTP/card extraction
`irs_tax_authority_scam`	VISHING	authority → fear → gift-card payment
`tech_support_scam`	VISHING	technical authority → fear → remote access
`lottery_prize_scam`	SCAM_SCRIPT	excitement → advance fee
`advance_fee_fraud`	SCAM_SCRIPT	wealth promise → trust → fee extraction
`utility_cutoff_scam`	VISHING	service threat → urgency → payment
`romance_scam`	SCAM_SCRIPT	emotional bond → emergency → money
`robocall_spam`	SPAM	unsolicited contact

Flags

Flag	Meaning
`REQUIRES_HUMAN_REVIEW`	Risk level is HIGH or CRITICAL — must not act without human review
`INSUFFICIENT_TURNS_LOW_CONFIDENCE`	Fewer than 3 turns — `risk_level` is `UNKNOWN` and the action is `FLAG_FOR_REVIEW`

Command-Line Reference

usage: detect_fraud.py [-h] --transcript TRANSCRIPT
                       [--archetypes ARCHETYPES]
                       [--threshold THRESHOLD]
                       [--dry-run]
                       [--out OUT]

options:
  --transcript   Path to the transcript JSON file (required)
  --archetypes   Path to the scam archetype library JSON
                 (default: references/scam-archetypes.json)
  --threshold    Risk score above which risk_level is HIGH
                 (default: 0.50; range: 0.0–1.0)
  --dry-run      Analyse without side effects
  --out          Write risk card JSON to this path (default: stdout)

Privacy & Safety

Recommended actions are advisory only. No call is terminated, no account is suspended, and no law enforcement is notified by this skill.
False positives exist. The false_positive_disclaimer is mandatory in every risk card. Legitimate banks, government agencies, and tech companies do make outbound calls.
Not a legal finding. The risk card must not be presented as evidence of fraud to law enforcement, courts, or regulators.
Transcript PII: validate_risk_card.py scans for raw phone numbers and email addresses in output and fails if any are found.
Retain transcripts responsibly: Operators must comply with applicable data-protection and wiretapping law (GDPR, CCPA, two-party consent) before processing or storing transcripts.

Full safety reference: references/safety.md

Files

skills/call-fraud-shield/
├── SKILL.md                              ← This file
├── scripts/
│   ├── detect_fraud.py                   ← Main analysis runner
│   ├── validate_risk_card.py             ← Output schema validator
│   └── test_fraud_shield.py              ← Test suite (90 tests)
└── references/
    ├── scam-archetypes.json              ← 8 documented scam patterns
    ├── example-transcript.json           ← Sample vishing transcript
    ├── examples.md                       ← Usage examples (4 scenarios)
    ├── research-papers.md                ← Scientific citations
    └── safety.md                         ← Ethics and legal reference

Running Tests

bash

# Run via pytest (recommended)
python3 -m pytest skills/call-fraud-shield/scripts/test_fraud_shield.py -v

# Or run directly
python3 skills/call-fraud-shield/scripts/test_fraud_shield.py

Expected: all tests pass — covers vishing (bank, IRS, tech support), spam, romance scam, lottery, utility cutoff, benign calls, empty/single-turn abstention, threshold variation, CLI, schema validation, and PII detection.

Integration with CALL-E

The shipped tool is a post-call transcript scanner (it reads a transcript JSON file; it does not stream turns or terminate calls itself):

[call ends] → [full transcript] → [detect_fraud.py] → [risk card logged]
                                                             ↓
                                     review queue / compliance audit trail

An integrator can also run it on partial transcripts at any point during a call to get an interim risk card — but the tool itself never acts: the recommended action is always advisory to a human operator.

Files

SKILL.md and 8 other files (scripts, references) in skills/call-fraud-shield of CALLE-AI/awesome-phone-call-agents.

SKILL.md
references/example-transcript.json
references/examples.md
references/research-papers.md
references/safety.md
references/scam-archetypes.json
scripts/detect_fraud.py
scripts/test_fraud_shield.py
scripts/validate_risk_card.py

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Call Fraud Shield 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.

Call Fraud Shield compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Call Fraud Shield this skillCALLE-AI/awesome-phone-call-agents	107	—	~2.7k	Automated safety check: Pass	MIT	yesterday
Read arXiv Paperkarpathy/nanochat	59k	1 repos	~494	Automated safety check: Pass	MIT	1 mo ago
Literature Reviewneflibata-feng/MyArxiv-Agent	126	20 repos	~5.9k	Automated safety check: Notes	MIT	today
Openalex Databaseneflibata-feng/MyArxiv-Agent	126	12 repos	~3k	Automated safety check: Pass	Custom licence	today
Citation ManagementK-Dense-AI/claude-scientific-writer	2.4k	2 repos	~3.9k	Automated safety check: Notes	MIT	2 days ago
Citation Managementneflibata-feng/MyArxiv-Agent	126	19 repos	~8.1k	Automated safety check: Notes	MIT	today

Similar skills

Read arXiv Paper
karpathy/nanochat
Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.
59k GitHub starsUsed in 1 repo~494 tokens
Research & ScienceAuto-check passed
Literature Review
neflibata-feng/MyArxiv-Agent
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
126 GitHub starsUsed in 20 repos~5.9k tokens
Research & ScienceAuto-check: notes
Openalex Database
neflibata-feng/MyArxiv-Agent
Query and analyze scholarly literature using the OpenAlex database.
126 GitHub starsUsed in 12 repos~3k tokens
Research & ScienceAuto-check passed
Citation Management
K-Dense-AI/claude-scientific-writer
Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.
2.4k GitHub starsUsed in 2 repos~3.9k tokens
Research & ScienceAuto-check: notes
Citation Management
neflibata-feng/MyArxiv-Agent
Comprehensive citation management for academic research. An agent skill from neflibata-feng/MyArxiv-Agent.
126 GitHub starsUsed in 19 repos~8.1k tokens
Research & ScienceAuto-check: notes
Systematic Literature Review Builder
bytedance/deer-flow
Searches arXiv across many papers on one topic, extracts each paper's methodology and findings in parallel, and synthesizes a cited literature review.
84k GitHub starsUsed in 2 repos~4.3k tokens
Research & ScienceAuto-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

Works with

arXiv

Questions about Call Fraud Shield

What does Call Fraud Shield do?

Post-call fraud detection skill. An agent skill from CALLE-AI/awesome-phone-call-agents. Call Fraud Shield is an agent skill from CALLE-AI/awesome-phone-call-agents. Post-call fraud detection skill.

When should I use Call Fraud Shield?

Call Fraud Shield fits situations like: tasks that involve Academic paper search; tasks that involve Anomaly detection.

How do I install Call Fraud Shield in Claude Code?

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

How do I install Call Fraud Shield in Codex?

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

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

What does Call Fraud Shield need to run?

Going by SKILL.md and its folder, Call Fraud Shield needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Call Fraud Shield 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 Call Fraud Shield 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 Call Fraud Shield use?

Call Fraud Shield 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 Call Fraud Shield use?

About 2.7k tokens (SKILL.md is roughly 11k 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 3.6k tokens, read only when the agent opens those files.

What are the alternatives to Call Fraud Shield?

Skills that share tags, products or a category with Call Fraud Shield: Read arXiv Paper (karpathy/nanochat, 59k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Openalex Database (neflibata-feng/MyArxiv-Agent, 126 stars) and Citation Management (K-Dense-AI/claude-scientific-writer, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Call Fraud Shield?

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.

Install Call Fraud Shield

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

call-fraud-shield

Why This Skill Exists

Scientific Foundation

Quick Start

Heuristic mode (no external dependencies)

With a custom risk threshold

Validate output schema

Input

Output — Risk Card

Threat Taxonomy

Risk Levels & Recommended Actions

Scam Archetype Library

Flags

Command-Line Reference

Privacy & Safety

Files

Running Tests

Integration with CALL-E

Files

Compare with similar skills

Similar skills

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

Related

Questions about Call Fraud Shield