jev-assist
Use when a short issue report or message would benefit from an optional second opinion on intent, information completeness, or message type.
Skill by williamnie
Chalk Labs
Need help deploying jev-assist?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/williamnie-jev-assist
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 2
api.typesafe.ai· found in codecodeload.github.com· found in install command
Files it touches
~/.claude/skills/jev-assist
What's inside
- Skill name
jev-assist- Description
- Use when a short issue report or message would benefit from an optional second opinion on intent, information completeness, or message type. Requires the available jev_classify_report tool; continue normally without it when unavailable.
- License
- Apache-2.0
- Instructions
- 14 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- server.mjs · scripts/
SKILL.md (first lines)
# Jev 辅助判断 仅在结构化分类有助于当前任务时，按需调用 `jev_classify_report`。已有充分上下文、简单回复、审批、验收或复杂规划不需要先调用此技能。 - 输入为当前任务相关的短报告：`title`、`body`，可选 `latest_message`。只传需要分类的片段，不发送完整历史、代码、日志或凭据。 - 工具只判断报告意图、信息完整性、消息类型；分类不证明 Bug，也不代表用户授权。 - `observed` 且 `reason=advisory` 时，可结合原始内容参考 `advice`；仍由当前 Agent 决定下一步。 - `shadow_only` 只表示完成观察，不提供决策建议。不要根据它改变流程。 - 工具缺失、关闭、未授权、超时、返回 `unavailable` 或低置信度时，使用已有原始上下文继续任务；不要反复重试、要求用户必须配置 Jev，或把辅助失败升级为任务失败。 - 权限、审批、Evidence 和 Handoff 继续通过玄武既有流程；不得用分类结果跳过检查。 技能配置位于玄武「Skills → Jev」；Key 由宿主在实际调用时注入，不读取用户凭据文件或通过 shell 自行请求服务。
From williamnie/xuanwu, Apache-2.0.
More from williamnie/xuanwu
- 0.614score
xuanwu
williamnie
Create, enqueue, inspect, retry, cancel, delete, or finish local Xuanwu issues from Codex or Claude Code.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
fixture-domain
williamnie
Use when fixture attention inbox items should become action proposals.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
pi-domain-proposal
williamnie
Use when PI Assistant needs to turn an Attention Inbox item into approval-gated action proposals.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
pi-llm-intake
williamnie
Use when PI Assistant needs to classify a context bundle into attention inbox items or ignored groups.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
fixture-intake
williamnie
Use when fixture context bundles should be classified into attention inbox items or ignored groups.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 28, 2026 (1 month ago)
- Last release
- Oct 12, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/williamnie/xuanwu
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from williamnie
- 0.614score
xuanwu
williamnie
Create, enqueue, inspect, retry, cancel, delete, or finish local Xuanwu issues from Codex or Claude Code.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
fixture-domain
williamnie
Use when fixture attention inbox items should become action proposals.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
pi-domain-proposal
williamnie
Use when PI Assistant needs to turn an Attention Inbox item into approval-gated action proposals.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
pi-llm-intake
williamnie
Use when PI Assistant needs to classify a context bundle into attention inbox items or ignored groups.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
fixture-intake
williamnie
Use when fixture context bundles should be classified into attention inbox items or ignored groups.
SkillAFreshness: A★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get jev-assist running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
jev-assist skill. Agent Mart. https://agentmart.dev/skills/williamnie-jev-assist (last updated 2026-10-24)