Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents.
This repository also configures its own agents. See what awesome-phone-call-agents tells them →
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental English/Spanish lexicon helper for phone-workflow demonstrations. Returns a code-mixing ratio and suggested style; no ASR or LLM prompt integration is included.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Pre-call strategy engine and post-call debrief for negotiation calls. Implements BATNA/ZOPA/Dual Concern Model + DISC-matched tactics.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental phone-workflow helper that compares supplied prosodic features and suggests bounded TTS parameter changes. Use for synthetic demonstrations and host integration planning.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental post-call feedback scorer using supplied ratings and text heuristics. Use to demonstrate advisory review suggestions; no LLM inference, RLHF training, or memory integration is included.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Heuristic legal and regulatory compliance auditor for AI phone call scripts. Scans for required disclosures and prohibited high-pressure tactics.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental text-turn helper for phone scam-review demonstrations. Extracts candidate IoCs and suggests bait responses; it does not place, intercept, or answer calls.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental pattern checks on supplied call metadata and text, returning advisory synthetic-voice hints without certifying identity or switching live protocols.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental scorer of supplied acoustic features for phone-workflow demonstrations. Returns heuristic review suggestions, not caller authentication or a deployed deepfake detector.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental reference that calculates pause-duration trends from synthetic call metadata for human review; not a cognitive assessment or diagnosis.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental spoken-code coordination illustration for CALL-E workflows. Generates a nonce and HMAC-derived short code from an environment-variable secret, then fuzzy-matches a supplied transcript against the supplied expected code. An optional local JSONL ledger flags recorded nonce reuse. This is not…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental QA helper for CALL-E relay transcripts. Compares English urgency-marker levels in source and relay-agent text; both inputs must be English or operator-prepared English translations. Returns advisory lexical drift labels and suggested relay wording, without translating, measuring emotional state…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that compares recognized callee confirmation phrases with detected sensitive-disclosure keywords. Returns advisory right-party signals, an ordering flag and a suggested verification-first goal. It does not verify identity, certify compliance, authorize disclosure or place…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Post-call cooperation skill. Classifies callee turns in a CALL-E transcript as backchannels ("mm-hmm", "right, okay"), frustration barge-ins ("wait", "hold on", "slow down"), or substantive answers - disambiguating answers from backchannels via the preceding agent question - and computes pacing metrics including…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper using English irony markers and complaint-context scoring. Returns advisory evidence spans, illustrative confidence buckets or abstention, and suggested de-escalation wording. It does not establish a person's intent, authorize another call or perform consequential actions.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Build or debug application integrations with the CALL-E Developer API and TypeScript or Python SDKs, including call payloads, structured results, recovery and webhooks. Use for application code, not for operating calls through the calle CLI.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that flags agent statements of specific values absent from the goal facts and callee turns (over-assertion) and goal facts spoken with hedges but no source attribution (over-hedging), plus a three-tier calibrated-wording goal template. It is not proof the agent invented…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that grades whether the agent disclosed being an AI, whether the disclosure came before business content, whether a comprehension question was asked, and whether an acknowledgment was captured, plus a disclosure-first goal template. It is not legal advice…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E helper that compares amounts, dates, and times stated by the agent across two finished calls to the same destination and grades each fact kind CONSISTENT, CONTRADICTED, or ONLYSTATED, plus a consistency-guarded goal template. It is not proof either call lied, a record of truth, or…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that detects callee-initiated repair sequences (huh, can you repeat, did you say X), localizes and profiles the trouble-source agent turn, classifies how the agent handled each repair, and crafts chunked redial goals. It does not measure comprehension conclusively…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that detects pushback against goal-grounded facts and classifies the agent's response (HOLDS, CAPITULATES, VERIFIES, UNADDRESSED), flags capitulated values that tainted the final confirmation, and crafts anti-capitulation goals. It is not a measure of the agent's intent…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript auditor that grades a returned transcript RELIABLE, SUSPECT, or UNUSABLE from text-visible ASR-hallucination symptoms before anything acts on it, and crafts ASR-risk-aware goals. It is not proof of hallucination, not a transcription accuracy certificate, and not authorization to…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline heuristic CALL-E phone call transcript skill that extracts and classifies agent Commissive Speech Acts — promises, follow-up pledges, and delegation statements — into WITHDEADLINE, WITHOUTDEADLINE, and CONDITIONAL buckets, then emits a verification follow-up call goal. It is not proof a commitment was broken…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline heuristic CALL-E transcript skill that measures filled-pause, self-repair, repetition, and hesitation-opener rates per speaker side to detect callee stress and agent knowledge-gap hesitancy, then emits a reassurance-paced follow-up call goal. It is not a clinical stress assessment, a proof of speaker intent…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline heuristic CALL-E transcript skill that compares the original call goal against the agent's actual turns to measure on-topic ratio, detect off-topic spans, and determine whether the goal was achieved in the closing — then emits a tighter, bounded goal for the next plancall. It is not a compliance ruling, a…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: