accesscall
Conduct 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.
CALLE-AI · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add CALLE-AI/awesome-phone-call-agents --skill accesscall技能说明
name: accesscall description: Conduct 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. license: MIT
AccessCall
Use this skill when a user wants to conduct an accessibility intake interview by phone instead of a web form, typically to support a Section 508 or WCAG conformance audit (VPAT 2.4).
Accessibility intake forms are themselves often inaccessible: screen reader fatigue, motor impairment, low vision, or cognitive load can all block someone from completing the exact form meant to capture their barrier report. AccessCall places a short phone call instead, conducts a structured verbal interview, and returns a result that maps onto standard VPAT 2.4 conformance report fields.
When To Use
Use this skill for:
- accessibility intake for someone who cannot use a web-based audit form
- gathering verbal barrier reports to populate a VPAT 2.4 / Section 508 audit report
- "call and ask about accessibility issues" or similar one-off outbound intake requests
When Not To Use
Do not use this skill to:
- place a call without the user explicitly confirming the recipient and their intent first
- guess a phone number's country code or region; ask if ambiguous
- call a third party who is not the requesting user without documented prior consent from that person
- auto-populate a VPAT row when the follow-up contact was never confirmed back to the caller (see Safety Rules)
- treat the auto-selected WCAG criterion row as final without human review; matching is done at the WCAG principle level (Perceivable / Operable / Understandable / Robust), not the specific success criterion
Setup
scripts/format-to-vpat.js depends on docx, jszip, and xml-js (declared in package.json). Run npm install inside skills/accesscall/ before using it — without this step it fails immediately with Cannot find module 'jszip'. scripts/parse-recap.js and scripts/phone-utils.js have no external dependencies and need no install step.
Core Workflow
- Confirm required inputs: recipient phone number, product or site name being audited, preferred language (default English, US). Ask for anything missing; do not fabricate a phone number or product name.
- Validate the phone number against E.164 (
scripts/phone-utils.js,isE164/assertE164) before callingplan_call. If it does not match E.164 format, reject it and ask the user to correct it — do not reformat, guess a country code, or silently pass a malformed number through toplan_call. - Call
plan_callwith the goal built fromreferences/call-task-template.md, filling inrecipient_nameandproduct_or_site_name. Do not forward the user's full latest message verbatim viauser_inputby default — that field exists onplan_callfor resolving an ambiguous/malformed phone number, not as a general passthrough. Only populateuser_inputwhen there's an actual number to disambiguate, and even then pass just the relevant phone-number text, not the user's entire message. Thegoalstring alone carriesrecipient_name/product_or_site_name/language into the call. - Show the
confirm_summaryto the user and wait for explicit confirmation. Do not callrun_calluntil the user confirms. - Immediately before calling
run_call, acquire the dispatch lock (scripts/call-lock.js,acquireLock) keyed on the recipient's phone number, the purpose"accesscall-intake", and this specificplan_id— every lock is owned by theplan_idthat acquired it. If a call to this recipient is already locked by a differentplan_id— including on a retry after a crash or timeout, which will see the same lock a first attempt wrote — refuse to place another and ask the user to explicitly confirm an override before retrying.acquireLockalso refuses unconditionally (even with override) if this exactplan_idwas already dispatched before, per its durable dispatch history — aplan_idmust never be replayed. The lock does not expire on a timer; it is only released in step 7, once a confirmed terminal status exists.- Before ever passing
override: runscripts/call-lock.js'scheckLockfirst and show the human the current owningplan_idandgeneration— never override from memory or a stale earlier check. Overriding requires passing that exactgenerationasexpectedGeneration;acquireLockre-verifies inside the same atomic critical section that the on-disk generation still matches before writing, and refuses with a clear "state has changed" error if it doesn't (e.g. a different override already went through in the meantime). This exists because the per-recipient mutex alone only serializes writes against each other — it does not stop two separately, legitimately approved overrides (each based on what looked like current state at approval time) from both eventually succeeding one after the other against state that changed in between. Never retry an override with the sameexpectedGenerationafter a mismatch; re-check and decide again.
- Before ever passing
- Call
run_callwith theconfirm_tokenexactly as received. Never call it more than once for the sameplan_id. - Poll
get_call_runevery 1-3 seconds while the run is active, then slow down, until a terminal status. As soon as one ofCOMPLETED/FAILED/NO_ANSWER/DECLINED/CANCELED/CANCELLED/VOICEMAIL/BUSY/EXPIREDis confirmed, callscripts/call-lock.js'sreleaseLockwith that sameplan_idand status to release the dispatch lock from step 5.releaseLockis compare-and-delete: it only releases if theplan_idgiven still matches the lock's current owner, so a delayed/late result for