网有NETHAVE
AGENT SKILL

callstack-agent-device-roi

Steal high-ROI Callstack agent-device patterns (proxy, PR runtime evidence) for native Random Timer without RN/Expo spend.

使用场景Skill与智能体开发
License 许可
MIT
最近更新
2026-11-09
Stars
★ 1
Forks
0

01 前言 Front Matter

name
callstack-agent-device-roi
description
Steal high-ROI Callstack agent-device patterns (proxy, PR runtime evidence) for native Random Timer without RN/Expo spend.

02 资源文件 3

03 SKILL.md 正文

Callstack agent-device ROI (Random Timer)

Source: Callstack Incubator Aug 2026 dispatch (~/Downloads/callstack.pdf, 2026-09-14).

Random Timer is native Kotlin/Swift — skip RN/Rozenite/Margelo/React Navigation. Implement only transferable agent infrastructure.

Do (high ROI, $0)

  1. Runtime evidence before UI "done":
    python3 scripts/agent_device_doctor.py --json
./scripts/device-tests/agent-device-pr-evidence.sh
  2. Self-host proxy on a Mac with Simulator (prefer SSH -L / Tailscale; not paid ngrok):
    ./scripts/device-tests/agent-device-proxy-host.sh
# agent machine:
ssh -L 4310:127.0.0.1:4310 <device-host>
export AGENT_DEVICE_DAEMON_AUTH_TOKEN=...
export AGENT_DEVICE_DAEMON_BASE_URL=http://127.0.0.1:4310/agent-device
./scripts/device-tests/agent-device-proxy-connect.sh
  3. Rule: green unit CI ≠ mobile still works (Callstack blog theme). Cite screenshot + snapshot paths in PRs.

Do not (low ROI / budget)

  • Expo EAS cloud simulators waitlist
  • Paid Apex GA / Agent Conf tickets
  • React Native 0.87 upgrades, Rozenite plugins, Nitro/MMKV

Related

  • docs/DEVICE_E2E_TESTS.md
  • scripts/agent_device_doctor.py
  • Existing CI lane: scripts/device-tests/ci-maestro-ios.sh

04 同仓库更多 Skills

IgorGanapolsky
IgorGanapolsky/Random-Timer

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

内容创作者写作与文案
★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

workflow-economics-lite

Escape AI pilot purgatory: require completion-loop workflows with one owner, baseline, economic metric, system-of-record integration, and audit trail. Block orphan chatbots and interest-as-ROI claims.

Skill与智能体开发
★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

value-center-lite

Apply InfoQ Rohrer value-center / VSM five questions (agency + coherence). Use when planning work, shipping releases, or auditing agent autonomy claims. Fail closed on product-only slogans without WQTU/paywall value.

★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

★ 1