本文へ移動
cccskills
無料GitHub で公開

assemblyai-local-dev-loop

Build an AssemblyAI local loop with synthetic fixtures, recorded contracts, and an optional bounded live lane. Use when developing without exposing audio or uncontrolled credits. Trigger with "AssemblyAI local dev" or "mock AssemblyAI".

インストール方法を見る

含まれるファイル(2)

  • SKILL.md4.1 KB
  • references/official-docs.md1.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

AssemblyAI Deterministic Local Development

Overview

Build an AssemblyAI local loop with synthetic fixtures, recorded contracts, and an optional bounded live lane. Treat live audio, transcript content, credentials, spend, and destructive state as separately governed boundaries.

Prerequisites

  • The target repository or integration path and the requested operator outcome.
  • The AssemblyAI project, environment, region, data classification, and accountable owner.
  • Current first-party documentation plus credentials only for a narrowly approved live check.

Current Contract

Ordinary development stays offline. Fixtures model REST job states, Streaming v3 messages, both webhook families, LLM Gateway outputs, throttling, duplicates, and termination. A public tunnel and live API call are explicit exposure and cost boundaries.

Authentication

For live work, inject ASSEMBLYAI_API_KEY from an approved secret manager and send the raw value only in the AssemblyAI Authorization header to the configured first-party host. Never print, commit, place in a URL, or expose it to an untrusted client. Callback secrets and temporary streaming tokens are separate credentials.

Instructions

  1. Map the adapter surfaces actually used.
  2. Create synthetic audio and content-free response fixtures.
  3. Inject a fake clock, deterministic jitter, and bounded queues.
  4. Cover delayed polling, 429, duplicates, malformed events, and disconnects.
  5. Protect live tests behind a separate flag and secret context.
  6. Review recorded-contract diffs against current first-party schemas.

Tool Discipline

Use Read, Glob, and Grep to inspect repository code, configuration, fixtures, and evidence. Use Write and Edit only for approved implementation or documentation changes. Do not call AssemblyAI, upload audio, open a streaming session, mint a token, replay a callback, deploy, rotate a key, or delete a transcript merely because this skill was invoked.

Approval Boundaries

Require an accountable owner before live audio processing, production credential or endpoint changes, paid model or capacity changes, content retention, callback replay, deployment, or deletion. Read-only repository inspection and synthetic offline validation do not authorize live vendor actions.

Failure Modes

  • A default test that needs a live key is not deterministic.
  • Real transcript text does not belong in golden fixtures.
  • A tunnel must be authenticated, disposable, and explicitly approved.

Output

Return the operation scope, environment, region, contract surface, authorization class, model and feature decisions, deterministic validation results, content-free identifiers, risks, cleanup or rollback state, and a concise pass/fail receipt. Exclude credentials, signed URLs, audio, transcript text, prompts, and customer-derived content.

Example

  • Start with the named environment, approved regional host, synthetic fixture identity, and bounded operation budget.
  • Finish with safe IDs, contract and assertion counts, terminal state, cleanup status, and the decision owner; never reproduce speech content.

Validation

Rerun the smallest relevant deterministic check, compare actual state with the requested outcome and current first-party contract, verify sensitive fields are absent from evidence, and confirm rollback, termination, or deletion state before reporting success.

References

Review the dated first-party evidence map before relying on any model, parameter, limit, price, region, or lifecycle claim.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Build a synthetic-data CI gate for customer-controlled Abridge integration code without calling undocumented vendor interfaces. Use when adding regression checks to an Abridge deployment repository. Trigger with "test the Abridge integration".

日本語の概要は準備中です。原文の説明を表示しています。

jeremylongshore/tons-of-skills-marketplace2,8322026年10月12日 更新

Triage Abridge recording, note-review, Epic handoff, and access failures from observed evidence without inventing vendor error codes. Use when an Abridge clinical workflow is degraded. Trigger with "diagnose this Abridge issue".

日本語の概要は準備中です。原文の説明を表示しています。

jeremylongshore/tons-of-skills-marketplace2,8322026年10月12日 更新

Design and verify the clinician workflow from consent through recording, draft review, Linked Evidence, and final note disposition. Use when implementing or auditing an Abridge clinical documentation pathway. Trigger with "map the Abridge note workflow".

日本語の概要は準備中です。原文の説明を表示しています。

jeremylongshore/tons-of-skills-marketplace2,8322026年10月12日 更新

Verify the approved handoff of clinician-reviewed Abridge note sections into Epic templates and downstream workflows. Use when configuring or auditing Abridge-to-Epic documentation flow. Trigger with "verify the Abridge Epic handoff".

日本語の概要は準備中です。原文の説明を表示しています。

jeremylongshore/tons-of-skills-marketplace2,8322026年10月12日 更新

Evaluate Abridge adoption, workflow value, and avoidable operational friction without inventing prices or vendor billing meters. Use when reviewing an Abridge rollout or renewal. Trigger with "analyze Abridge value".

日本語の概要は準備中です。原文の説明を表示しています。

jeremylongshore/tons-of-skills-marketplace2,8322026年10月12日 更新

Produce a PHI-minimized Abridge support bundle with provenance, redaction, and protected escalation boundaries. Use when support needs reproducible evidence for an Abridge issue. Trigger with "build an Abridge debug bundle".

日本語の概要は準備中です。原文の説明を表示しています。

jeremylongshore/tons-of-skills-marketplace2,8322026年10月12日 更新

jeremylongshore のスキルをすべて見る

このスキルの問題を報告する