CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex needs its repo
Call a government service counter to find out exactly what a person must bring before they travel there, and return it as a validated checklist. Use when published requirements are incomplete or contradicted at the window and the only reliable source is the office's phone line. Returns required documents, total fee…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline heuristic CALL-E transcript skill that detects callee grievances and grades the agent's response against the six-component apology effectiveness taxonomy (acknowledgment, repair, explanation, regret, forbearance, forgiveness request) with rote/empathic/explanatory typology, plus an apology-protocol goal…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline heuristic CALL-E transcript skill that audits the call's closing window for conversation-analytic completeness - pre-closing summary, arrangement for next steps, completed terminal exchange, dangling callee questions, business after the farewell, abrupt ends - and emits a clean-closing goal template. It is not…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline heuristic CALL-E phone call transcript skill that classifies agent questions into leading forms (tag questions, negative interrogatives, presupposition triggers, coercive framing), flags values affirmed under leading forms as tainted elicitation, and emits a neutral-elicitation goal template. It is not proof…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that grades agent answers to callee direct questions (identity, yes-no, information) as CLEAR, PARTIALLYCLEAR or EVASIVE with dodge mechanisms, and crafts answer-first goal templates. It is not intent detection, proof of deceit, or authorization to act.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that audits whether the agent requests only the personal data the goal file requires, flagging out-of-scope PII asks, redundant re-asks and full-datum echo-backs, plus a minimal-collection goal template. It is not a legal determination, proof of unlawful collection, or…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that detects the commitment question, locates the callee's consent, and grades whether the total price, recurring terms, and fees or restrictions were disclosed before that consent, flagging drip-pricing reveals that surface only after it, plus a transparent-offer goal…
CALLE-AI/awesome-phone-call-agents
Agent Claude Code
MUST BE USED before every real-call test run, before demo runs, and before any batch of Round 1 or Round 2 calls is triggered. Invoke by providing the number of leads in the current campaign and the remaining call budget. Verifies projected call count, business-hours gating, and retry bounds.
CALLE-AI/awesome-phone-call-agents
Agent Claude Code
MUST BE USED before any Round 1 call batch is written or executed. Audits every code path that could place a call and verifies the pre-Round-1 consent/approval gate is enforced. Use this after implementing the client-approval flow and again after any change to main.py or caller.py that touches call dispatch.
CALLE-AI/awesome-phone-call-agents
Agent Claude Code
MUST BE USED after implementing the Script Generator module and after adding any client-edit UI. Also invoke after any change that touches how OSM data or CALL-E API response fields flow into goals or prompts. Checks for prompt injection paths from untrusted external content.
CALLE-AI/awesome-phone-call-agents
Agent Claude Code
MUST BE USED after capturing a real calle call status JSON sample, and again after writing R1 classification or R2 extraction code. Invoke by pasting the real raw JSON into the prompt. Checks every code path that parses CALL-E output against what the API actually returns.
CALLE-AI/awesome-phone-call-agents
Agent Claude Code
Use only near submission time (target: 48 hours before the September 14 2026 deadline). Re-fetches all official rules fresh — do not rely on cached knowledge. Checks the full submission package against every requirement and reports pass/fail per item. Do not invoke this during development — save it for the final…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex needs its repo
Book restaurant tables or medical appointments via CALL-E AI voice calls. Load when the user wants to book, reserve, or schedule anything over the phone.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that detects callee requests for a human agent (transfer intent plus human role, or bare manager/supervisor demands) and grades the agent response window HONORED, DEFLECTED, IGNORED, or FALSEHUMANCLAIM, plus an escalation-honesty goal template. It is not proof a transfer…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E helper that decomposes the agent postsummary into atomic claims and anchors each against the transcript, flagging unsupported and outcome-contradicted statements before automation acts on them, plus a faithful-summary goal template. It is not semantic entailment, proof of lying, or…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E transcript helper that resolves every time reference in the agent's turns against the call timestamp, flagging relative-only commitments, meridiem-less clocks, dialect-dependent weekday phrases, and weekday-date calendar conflicts, plus an absolute-time goal template. It is not proof the…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex needs its repo
Research real-world businesses by phone. Use when the user needs to compare places by real-time availability, pricing, or features that only a phone call can verify.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Runs an evening round of confirm-then-backfill phone calls for a clinic's tomorrow appointments — confirms each patient, retries a no-answer once, frees the slot on cancellation or reschedule, then calls the waitlist in order until every freed slot is refilled.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E helper that tracks agent self-corrections mid-call ("Sorry, I said Tuesday; I meant Thursday"), follows each correction chain, and verifies the corrected value - not the superseded one - reached the postsummary, flagging stale values before automation acts; not semantic repair analysis…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E helper that codes agent turns in health-behavior calls against MITI-4.2.1-inspired lexical categories (reflections, open questions, permission-gated advice, confrontation) and grades MI adherence, abstaining honestly when no change talk is present; not certified MI coding, a clinical…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental CALL-E helper that grades agent request phrasing against Stanford-politeness strategy markers, flagging bald imperatives ("Give me your date of birth.") and condescension markers, with a softened-request goal template; not a rudeness judgment, a content-scope check, or authorization to act.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Autonomous voice AI agent skill that dispatches parallel phone calls to local service providers via CALL-E, negotiates competitive trade quotes, extracts structured pricing and availability schemas, and generates comparison dossiers for human closing.
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Run one outbound CALL-E call (mock by default, live only with explicit confirmation) on behalf of a user, capture the conversation, and return a structured brief. AfterHold owns the safety layer, the workspace, and the mission state machine; CALL-E owns the call and the conversation runtime. This skill is a portable…
CALLE-AI/awesome-phone-call-agents
Skill Claude CodeCodex
Offline experimental transcript auditor that detects cancellation requests in CALL-E call transcripts and grades the agent response CANCELLATIONHONORED, SOFTRETENTION, RETENTIONDARKPATTERN, CANCELLATIONIGNORED, or REQUESTUNRESOLVED, plus a cancellation-respect goal crafter; not a legal determination, proof of 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: