CALLE-AI
- 102 skills
- 0 followers
- 113 repo stars
- last month last updated
- ▌ Calle 4 · calle-ai bundleUse CALL-E from Codex through the calle CLI. Use for CALL-E setup checks, authentication recovery, phone call planning, planned call execution, and call status checks.
- ▌ Calle 2 · calle-ai bundleUse CALL-E from Claude Code through the calle CLI. Use for CALL-E setup checks, authentication recovery, phone call planning, planned call execution, and call status checks.
- ▌ Calle 3 · calle-ai bundleUse CALL-E from Cursor for setup checks, authentication recovery, phone call planning, planned call execution, and call status checks.
- ▌ Incident Escalation Call 2 · calle-ai bundleEscalate a production incident by phone until a person commits to owning it. Places one CALL-E call per on-call engineer in ladder order, requires a spoken owner and an ETA, then verifies the acknowledgement over a second transport before reporting it. Use when a page must end with a human on the hook, not a notification marked as sent.
- ▌ Outcome Completion Agent 2 · calle-ai bundleOwn one goal across as many CALL-E calls as it takes, when who to call next depends on what the last call said — read every call as structured evidence, reject offers that break the user's stated limits, follow referrals to parties the user never supplied, and gate the single call that commits the user.
- ▌ Verity Verification Core 2 · calle-ai bundleGate a CALL-E phone task's task_completed claim behind an independent transcript read-back before any real-world action. Use after a confirm, reschedule, or book call to decide ALLOW or BLOCK, catch a mid-sentence self-correction, a voicemail, or a value the caller never actually confirmed, and get the exact value to re-confirm on a second channel. Deterministic, no network, fail-closed.
- ▌ Adherence Memory Callback 2 · calle-ai bundleRun a consent-based outbound CALL-E medication-adherence phone check-in that remembers each caller across calls, learns side-effect patterns across many callers behind a corroboration gate, and honors "call me back later" by opening the next call with that context.
- ▌ Capacity Backfill Cascade 2 · calle-ai bundleConfirm bookings and backfill freed capacity from a waitlist using CALL-E phone calls. Use when an agent needs to recover cancelled reservations, fill released slots, or run consent-based confirm-then-cascade call workflows safely.
- ▌ Research Gap Call Verifier 2 · calle-ai bundleTurn 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, ambiguity, or failure as confirmation. Use when web research has produced a shortlist but availability, pricing, policies, or scheduling still require a disclosed call to a published business number.
- ▌ Candidate Availability Call 2 · calle-ai bundleRecruiting coordination phone-call skill that confirms candidate interview availability, captures evidence-backed time windows, and keeps final scheduling under human control.
- ▌ Outbound Call Skill Creator 2 · calle-ai bundleCreate directly usable outbound phone-call Agent Skills that bind source and durable result-output contracts at the right level, connect data such as Google Forms, TikTok Ads, Notion, Airtable, local CSV, or custom systems to an MCP one-off call provider route, compile per-record call goals, enforce safety rules, and configure source writeback, source-adjacent result artifacts, or new local result CSV output.
- ▌ Dollar Consent First Callback 2 · calle-ai bundlePlace one consent-first CALL-E callback after a local safety gate has already blocked an extreme-risk developer action, so a known project owner can say stop or request normal review without granting the agent destructive permission.
- ▌ Procurecall Supplier Sourcing 2 · calle-ai bundleSource and qualify suppliers by phone for a buyer's procurement request, collect structured quotes, and return supplier comparisons for human approval.
- ▌ Structured Outcome Followup Call 2 · calle-ai bundlePlace 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 in mock mode with zero live calls or credentials.
- ▌ Forgerelay Supplier Clarification 2 · calle-ai bundleUse CALL-E to collect missing manufacturing RFQ details from an authorized supplier contact through a bounded, approval-gated phone call, then return structured answers without negotiating or making commitments.
- ▌ Invoice Exception Manager Briefing 2 · calle-ai bundlePrepare a controlled, one-time CALL-E briefing for an authorized manager about an invoice exception, while keeping the human decision in the existing review application.
- ▌ Standby 2 · calle-ai bundleFill one open shift by calling a standby roster strictly one person at a time and stopping at the first acceptance, for no-show cover, on-call escalation, and shift-swap requests where calling everyone at once would double-book the slot.
- ▌ Mobilize 2 · calle-ai bundleGet a required number of confirmed responses from a consented pool of people within a deadline by calling multiple candidates in parallel waves via CALL-E, stopping as soon as the need is met. Use for urgent mobilization tasks like "find 3 donors in the next hour" or "get 2 volunteers by 5pm" from a registry of people who opted in to be contacted.
- ▌ Accesscall 2 · calle-ai bundleConduct phone-based accessibility intake interviews for users who cannot complete web-based accessibility audit forms (screen reader fatigue, motor impairment, low vision, cognitive load), and produce a structured result mapped to VPAT 2.4 / Section 508 conformance reporting fields.
- ▌ Scope Signal 2 · calle-ai bundlePrepare and reconcile one explicitly authorized CALL-E phone call that verifies a prospective client's project brief for a freelancer or small agency, while leaving negotiation and acceptance to a human.
- ▌ Call Reminder 2 · calle-ai bundleSchedule recurring CALL-E phone-call reminders, scheduled CALL-E calls, call-me-at-a-time requests, and remind-me-by-phone workflows by wrapping the existing one-off CALL-E call workflow in the current client's scheduler or automation system.
- ▌ Call Rehearsal 2 · calle-ai bundleRehearse a phone call plan against every realistic ending of the call before dialling anyone, and refuse a plan whose automation acts on a call that never reached a consenting human.
- ▌ Call Summarizer 2 · calle-ai bundleTurn a finished CALL-E phone-call transcript into a structured post-call brief with a one-line outcome, a masked summary, extracted action items with owners and due dates, caller sentiment, and a redacted caller fingerprint. Use after any CALL-E call when an agent or operator needs an actionable, reviewable record of what was said without re-reading the whole transcript or re-playing the recording.
- ▌ Recall Outreach 2 · calle-ai bundleContact affected customers about a product recall or corrective notice with CALL-E. Relays only organisation-approved wording, dispatches a wave as one batch with a strict per-recipient result schema, routes every unapproved question to a human, and never treats a completed call as a completed recall.
- ▌ Verify By Phone 2 · calle-ai bundleVerify a directory listing, database record, or any published claim about an organization by placing one disclosed CALL-E phone call and returning a span-grounded structured answer with a calibrated confidence or an explicit abstention. Use when stored information about a business must be checked against reality by phone, such as provider directory entries, accepting-new-patients status, insurance participation, hours, or availability, and when a wrong answer is more costly than no answer.
- ▌ Voice Preflight 2 · calle-ai bundleHear a CALL-E phone call task spoken by your own text-to-speech provider before a real person does, then refuse a script whose critical line would not survive being spoken.
- ▌ Exception Resolver 2 · calle-ai bundleResolve 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.
- ▌ Linecanary Monitor 2 · calle-ai bundleMonitor business phone lines and deployed voice agents with LineCanary — scheduled CALL-E test calls that walk the caller journey, assert structured results, diff against baselines and alert on regressions. Use when the user asks whether a phone line or voice agent still works, wants ongoing phone-line monitoring, or wants a post-deploy phone smoke test in CI.
- ▌ Appointment Confirm 2 · calle-ai bundleConfirm one existing appointment by phone with CALL-E, capture yes/no and time as structured JSON, and leave calendar changes to a human. Dry-run and fixture modes by default.
- ▌ Rdn Intake Referral 2 · calle-ai bundleConducts a consent-based nutrition support intake by phone and returns a structured summary for Registered Dietitian Nutritionist referral and human follow-up.
- ▌ Call Boundary Probes 2 · calle-ai bundleCheck a phone-call workflow's static scope-containment policy against a versioned offline probe corpus before integrating any agent or provider.
- ▌ Calle Script Advisor 2 · calle-ai bundleDraft and check CALL-E phone-call task text and result schemas for clarity, safety, and extraction quality before any call is placed.
- ▌ Callparity Claimkill 2 · calle-ai bundleCompile the next CALL-E call as a leak-scored refute of a quoted freight claim, merge Party B quotes into a claim graph, and preview from fixtures with zero live calls.
- ▌ Concord Policy Audit 2 · calle-ai bundleAudit what your own branches tell callers by phone, judge each answer against written policy, and return a branch-level gap register that is deliberately unusable as a staff performance record.
- ▌ Google Form Callback 2 · calle-ai bundleTurn Google Form lead or callback responses into safe one-off AI-agent phone calls with template-driven goals, scheduled runs, and result writeback.
- ▌ Language Bridge Call 2 · calle-ai bundleCross-language relay call skill for CALL-E - places one call in the recipient's language to capture a structured answer, then one call back to the requester in their language, and returns an agreed outcome or a fail-closed handoff.
- ▌ Pharmacy Stock Check 2 · calle-ai bundleCall a list of pharmacies to find out which one has a specific medication in stock, at what price, and whether they will hold it. Use when someone needs to locate a medication nearby and would otherwise ring round manually. Returns one structured record per pharmacy with a confidence score and the call transcript as evidence.
- ▌ Verify Contact Claim 2 · calle-ai bundleCheck whether an institution really did contact somebody. Places one CALL-E phone call to the number printed on the customer's own card or bill and asks whether they made contact in the last hour, then reports the verdict with the words the person on the line actually said. Use after a suspicious call, a voicemail or a text that asks for a call back.
- ▌ Confirmcall Day Board 2 · calle-ai bundleConfirm a full day's existing appointments by phone with CALL-E. Plans one disclosed confirmation call per booking, captures yes/no/reschedule as structured JSON, and leaves calendar writes to a human. Fixture/dry-run by default.
- ▌ Human Context Handoff 2 · calle-ai bundleAsk a verified, consenting human one bounded question by phone when an agent is blocked on missing context, then resume only from a structured terminal result. Use for ordinary product, workflow, preference, and operations choices, not identity proof or authorization for irreversible action.
- ▌ Ringer Consumer Tasks 2 · calle-ai bundleHandle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into a precise CALL-E task and a strict structured-result schema, previewing as a dry run, and placing the call only with explicit consent. Includes a Quote Shootout batch mode that calls several businesses and returns per-business results plus a ranked comparison.
- ▌ Service Dispatch Call 2 · calle-ai bundleCall 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.
- ▌ Partline Part Sourcing 2 · calle-ai bundleSafely source an exact industrial replacement part by calling approved suppliers with CALL-E and returning an evidence-backed comparison for human purchase approval.
- ▌ Labline Critical Result 2 · calle-ai bundleSafety-bounded CALL-E workflow for closed-loop communication of an approved critical laboratory result to an authorized clinical recipient. Verifies the recipient before disclosure, requires exact read-back, fails closed on wrong recipient or voicemail, and never interprets the result or recommends treatment.
- ▌ Metapelet Elder Checkin 2 · calle-ai bundlePlace one consent-based outbound CALL-E phone check-in for an older adult using the MetaPelet warm-companion persona (non-medical emotional support), then return structured mood, topics, and repeat-call interest for a family member or coordinator.
- ▌ Priority Call Waterfall 2 · calle-ai bundleFill one open opportunity by calling a priority-ordered candidate list with CALL-E, one candidate at a time, until someone accepts — waitlist backfill, shift coverage, on-call escalation, and service dispatch workflows.
- ▌ Appointment Call Confirm 2 · calle-ai bundlePlaces outbound CALL-E confirmation calls for a batch of upcoming appointments or bookings and returns a structured confirmed / needs-reschedule / declined / no-answer result per recipient, so a business can close its next-day no-show gap without a staff member manually dialing down the list.
- ▌ Customer Onboarding Call 2 · calle-ai bundlePlace a one-off welcome and onboarding call to a customer who just signed up, capture a structured result such as business type, goal, pain points, sentiment, and activation status, then write that result back to a CRM and queue a human follow-up task when the customer asks for one.
- ▌ Deployment Approval Call 2 · calle-ai bundlePlace one CALL-E phone call to get a spoken, code-verified human approval before an agent or a pipeline does something irreversible, such as a production deploy, a database restore, a bulk refund or a migration. Use when the approver is away from a keyboard and the action cannot be undone.
- ▌ Standby · calle-ai bundleFill one open shift by calling a standby roster strictly one person at a time and stopping at the first acceptance, for no-show cover, on-call escalation, and shift-swap requests where calling everyone at once would double-book the slot.
- ▌ Mobilize · calle-ai bundleGet a required number of confirmed responses from a consented pool of people within a deadline by calling multiple candidates in parallel waves via CALL-E, stopping as soon as the need is met. Use for urgent mobilization tasks like "find 3 donors in the next hour" or "get 2 volunteers by 5pm" from a registry of people who opted in to be contacted.
- ▌ Accesscall · calle-ai bundleConduct phone-based accessibility intake interviews for users who cannot complete web-based accessibility audit forms (screen reader fatigue, motor impairment, low vision, cognitive load), and produce a structured result mapped to VPAT 2.4 / Section 508 conformance reporting fields.
- ▌ Scope Signal · calle-ai bundlePrepare and reconcile one explicitly authorized CALL-E phone call that verifies a prospective client's project brief for a freelancer or small agency, while leaving negotiation and acceptance to a human.
- ▌ Call Reminder · calle-ai bundleSchedule recurring CALL-E phone-call reminders, scheduled CALL-E calls, call-me-at-a-time requests, and remind-me-by-phone workflows by wrapping the existing one-off CALL-E call workflow in the current client's scheduler or automation system.
- ▌ Call Rehearsal · calle-ai bundleRehearse a phone call plan against every realistic ending of the call before dialling anyone, and refuse a plan whose automation acts on a call that never reached a consenting human.
- ▌ Call Summarizer · calle-ai bundleTurn a finished CALL-E phone-call transcript into a structured post-call brief with a one-line outcome, a masked summary, extracted action items with owners and due dates, caller sentiment, and a redacted caller fingerprint. Use after any CALL-E call when an agent or operator needs an actionable, reviewable record of what was said without re-reading the whole transcript or re-playing the recording.
- ▌ Recall Outreach · calle-ai bundleContact affected customers about a product recall or corrective notice with CALL-E. Relays only organisation-approved wording, dispatches a wave as one batch with a strict per-recipient result schema, routes every unapproved question to a human, and never treats a completed call as a completed recall.
- ▌ Verify By Phone · calle-ai bundleVerify a directory listing, database record, or any published claim about an organization by placing one disclosed CALL-E phone call and returning a span-grounded structured answer with a calibrated confidence or an explicit abstention. Use when stored information about a business must be checked against reality by phone, such as provider directory entries, accepting-new-patients status, insurance participation, hours, or availability, and when a wrong answer is more costly than no answer.
- ▌ Voice Preflight · calle-ai bundleHear a CALL-E phone call task spoken by your own text-to-speech provider before a real person does, then refuse a script whose critical line would not survive being spoken.
- ▌ Exception Resolver · calle-ai bundleResolve 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.
- ▌ Linecanary Monitor · calle-ai bundleMonitor business phone lines and deployed voice agents with LineCanary — scheduled CALL-E test calls that walk the caller journey, assert structured results, diff against baselines and alert on regressions. Use when the user asks whether a phone line or voice agent still works, wants ongoing phone-line monitoring, or wants a post-deploy phone smoke test in CI.
- ▌ Appointment Confirm · calle-ai bundleConfirm one existing appointment by phone with CALL-E, capture yes/no and time as structured JSON, and leave calendar changes to a human. Dry-run and fixture modes by default.
- ▌ Rdn Intake Referral · calle-ai bundleConducts a consent-based nutrition support intake by phone and returns a structured summary for Registered Dietitian Nutritionist referral and human follow-up.
- ▌ Call Boundary Probes · calle-ai bundleCheck a phone-call workflow's static scope-containment policy against a versioned offline probe corpus before integrating any agent or provider.
- ▌ Calle Script Advisor · calle-ai bundleDraft and check CALL-E phone-call task text and result schemas for clarity, safety, and extraction quality before any call is placed.
- ▌ Callparity Claimkill · calle-ai bundleCompile the next CALL-E call as a leak-scored refute of a quoted freight claim, merge Party B quotes into a claim graph, and preview from fixtures with zero live calls.
- ▌ Concord Policy Audit · calle-ai bundleAudit what your own branches tell callers by phone, judge each answer against written policy, and return a branch-level gap register that is deliberately unusable as a staff performance record.
- ▌ Google Form Callback · calle-ai bundleTurn Google Form lead or callback responses into safe one-off AI-agent phone calls with template-driven goals, scheduled runs, and result writeback.
- ▌ Language Bridge Call · calle-ai bundleCross-language relay call skill for CALL-E - places one call in the recipient's language to capture a structured answer, then one call back to the requester in their language, and returns an agreed outcome or a fail-closed handoff.
- ▌ Pharmacy Stock Check · calle-ai bundleCall a list of pharmacies to find out which one has a specific medication in stock, at what price, and whether they will hold it. Use when someone needs to locate a medication nearby and would otherwise ring round manually. Returns one structured record per pharmacy with a confidence score and the call transcript as evidence.
- ▌ Verify Contact Claim · calle-ai bundleCheck whether an institution really did contact somebody. Places one CALL-E phone call to the number printed on the customer's own card or bill and asks whether they made contact in the last hour, then reports the verdict with the words the person on the line actually said. Use after a suspicious call, a voicemail or a text that asks for a call back.
- ▌ Confirmcall Day Board · calle-ai bundleConfirm a full day's existing appointments by phone with CALL-E. Plans one disclosed confirmation call per booking, captures yes/no/reschedule as structured JSON, and leaves calendar writes to a human. Fixture/dry-run by default.
- ▌ Human Context Handoff · calle-ai bundleAsk a verified, consenting human one bounded question by phone when an agent is blocked on missing context, then resume only from a structured terminal result. Use for ordinary product, workflow, preference, and operations choices, not identity proof or authorization for irreversible action.
- ▌ Ringer Consumer Tasks · calle-ai bundleHandle the dreaded consumer phone calls — negotiate a bill, cancel a subscription, chase a refund, book an appointment, get a price quote, or ask a business a question — by turning a few fields into a precise CALL-E task and a strict structured-result schema, previewing as a dry run, and placing the call only with explicit consent. Includes a Quote Shootout batch mode that calls several businesses and returns per-business results plus a ranked comparison.
- ▌ Service Dispatch Call · calle-ai bundleCall 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.
- ▌ Partline Part Sourcing · calle-ai bundleSafely source an exact industrial replacement part by calling approved suppliers with CALL-E and returning an evidence-backed comparison for human purchase approval.
- ▌ Labline Critical Result · calle-ai bundleSafety-bounded CALL-E workflow for closed-loop communication of an approved critical laboratory result to an authorized clinical recipient. Verifies the recipient before disclosure, requires exact read-back, fails closed on wrong recipient or voicemail, and never interprets the result or recommends treatment.
- ▌ Metapelet Elder Checkin · calle-ai bundlePlace one consent-based outbound CALL-E phone check-in for an older adult using the MetaPelet warm-companion persona (non-medical emotional support), then return structured mood, topics, and repeat-call interest for a family member or coordinator.
- ▌ Priority Call Waterfall · calle-ai bundleFill one open opportunity by calling a priority-ordered candidate list with CALL-E, one candidate at a time, until someone accepts — waitlist backfill, shift coverage, on-call escalation, and service dispatch workflows.
- ▌ Appointment Call Confirm · calle-ai bundlePlaces outbound CALL-E confirmation calls for a batch of upcoming appointments or bookings and returns a structured confirmed / needs-reschedule / declined / no-answer result per recipient, so a business can close its next-day no-show gap without a staff member manually dialing down the list.
- ▌ Customer Onboarding Call · calle-ai bundlePlace a one-off welcome and onboarding call to a customer who just signed up, capture a structured result such as business type, goal, pain points, sentiment, and activation status, then write that result back to a CRM and queue a human follow-up task when the customer asks for one.
- ▌ Deployment Approval Call · calle-ai bundlePlace one CALL-E phone call to get a spoken, code-verified human approval before an agent or a pipeline does something irreversible, such as a production deploy, a database restore, a bulk refund or a migration. Use when the approver is away from a keyboard and the action cannot be undone.
- ▌ Incident Escalation Call · calle-ai bundleEscalate a production incident by phone until a person commits to owning it. Places one CALL-E call per on-call engineer in ladder order, requires a spoken owner and an ETA, then verifies the acknowledgement over a second transport before reporting it. Use when a page must end with a human on the hook, not a notification marked as sent.
- ▌ Outcome Completion Agent · calle-ai bundleOwn one goal across as many CALL-E calls as it takes, when who to call next depends on what the last call said — read every call as structured evidence, reject offers that break the user's stated limits, follow referrals to parties the user never supplied, and gate the single call that commits the user.
- ▌ Verity Verification Core · calle-ai bundleGate a CALL-E phone task's task_completed claim behind an independent transcript read-back before any real-world action. Use after a confirm, reschedule, or book call to decide ALLOW or BLOCK, catch a mid-sentence self-correction, a voicemail, or a value the caller never actually confirmed, and get the exact value to re-confirm on a second channel. Deterministic, no network, fail-closed.
- ▌ Adherence Memory Callback · calle-ai bundleRun a consent-based outbound CALL-E medication-adherence phone check-in that remembers each caller across calls, learns side-effect patterns across many callers behind a corroboration gate, and honors "call me back later" by opening the next call with that context.
- ▌ Capacity Backfill Cascade · calle-ai bundleConfirm bookings and backfill freed capacity from a waitlist using CALL-E phone calls. Use when an agent needs to recover cancelled reservations, fill released slots, or run consent-based confirm-then-cascade call workflows safely.
- ▌ Research Gap Call Verifier · calle-ai bundleTurn 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, ambiguity, or failure as confirmation. Use when web research has produced a shortlist but availability, pricing, policies, or scheduling still require a disclosed call to a published business number.
- ▌ Candidate Availability Call · calle-ai bundleRecruiting coordination phone-call skill that confirms candidate interview availability, captures evidence-backed time windows, and keeps final scheduling under human control.
- ▌ Outbound Call Skill Creator · calle-ai bundleCreate directly usable outbound phone-call Agent Skills that bind source and durable result-output contracts at the right level, connect data such as Google Forms, TikTok Ads, Notion, Airtable, local CSV, or custom systems to an MCP one-off call provider route, compile per-record call goals, enforce safety rules, and configure source writeback, source-adjacent result artifacts, or new local result CSV output.
- ▌ Dollar Consent First Callback · calle-ai bundlePlace one consent-first CALL-E callback after a local safety gate has already blocked an extreme-risk developer action, so a known project owner can say stop or request normal review without granting the agent destructive permission.
- ▌ Procurecall Supplier Sourcing · calle-ai bundleSource and qualify suppliers by phone for a buyer's procurement request, collect structured quotes, and return supplier comparisons for human approval.
- ▌ Structured Outcome Followup Call · calle-ai bundlePlace 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 in mock mode with zero live calls or credentials.
- ▌ Forgerelay Supplier Clarification · calle-ai bundleUse CALL-E to collect missing manufacturing RFQ details from an authorized supplier contact through a bounded, approval-gated phone call, then return structured answers without negotiating or making commitments.
- ▌ Invoice Exception Manager Briefing · calle-ai bundlePrepare a controlled, one-time CALL-E briefing for an authorized manager about an invoice exception, while keeping the human decision in the existing review application.
- ▌ Handoff · calle-ai bundleCreate concise, forwardable handoffs for Coding Agent work, blockers, reviews, escalations, or context transfers. Use when Codex needs to package current state, decisions, evidence, file references, command outputs, risks, and next steps into a Markdown artifact that another person or agent can continue from.
- ▌ Github CI Triage · calle-aiUse this project-local skill when the user asks Codex to inspect, diagnose, summarize, rerun, or fix GitHub Actions CI, release, test, deploy, or workflow failures for this repository.
- ▌ Release Decision · calle-aiUse this project-local skill when deciding whether a CALL-E Integrations change needs a package version release, changeset, or maintainer release decision, especially before finishing code, docs, marketplace, plugin, package metadata, or install-flow changes.
- ▌ Change Review Agent · calle-aiUse this project-local skill when the user asks Codex to start, spawn, launch, or use an agent/subagent to review current code changes, implementation, diff, or completed modifications in this repository with read-only review, readiness checks, conflict checks, impact analysis, evidence-backed findings, escalation notes, and P0-P3 severity ratings.
- ▌ Claude Plugin Reinstall · calle-aiUse this project-local skill when the user asks Codex to reinstall, refresh, update, debug, remove, delete, uninstall, or locally test the CALL-E Claude Code plugin, especially after editing packages/claude-plugin/plugin, renaming the Claude skill, or seeing Claude plugin scope/cache errors.