Agent skill

Loongsuite Pilot Insight

by alibaba in alibaba/loongsuite-pilot

基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。

Apache-2.0Auto-check passedDevOps & Cloud

Install Loongsuite Pilot Insight

skills CLI
$ npx skills add alibaba/loongsuite-pilot --skill loongsuite-pilot-insight -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alibaba/loongsuite-pilot loongsuite-pilot-insight --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alibaba/loongsuite-pilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/solutions/loongsuite-pilot-sls-dashboard/.agents/skills/loongsuite-pilot-insight .claude/skills/loongsuite-pilot-insight && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
loongsuite-pilot-insight
GitHub stars
201
Token cost
~944 tokens
SKILL.md length
222 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。

  • Works in 6 steps: 确定 ,读取或创建… → 读取 schema.md,确认 Data Source… → 解析… → …
  • Tasks that involve Observability
  • SKILL.md covers Purpose, Boundaries, Inputs And Outputs and Workflow, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Loongsuite Pilot Insight is an agent skill from alibaba/loongsuite-pilot. 基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `schema.md`).

It sits in DevOps & Cloud, covering Observability. It works with OpenTelemetry, TypeScript and macOS. The repository describes itself as: Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Observability

Example prompts

  • “/loongsuite-pilot-insight”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 确定 ,读取或创建 cases/loongsuite-pilot-insight/input/-spec.md`。
  2. 读取 schema.md,确认 Data Source Bindings、字段语义、公共 CTE、指标可加性和风险点。
  3. 解析 spec,将自然语言需求转成视图清单:指标、SQL、图表类型、布局、筛选器和说明块。
  4. 使用 sls-dashboard-builder 生成或更新 cases/loongsuite-pilot-insight/output/-dashboard.json。
  5. 调用 sls-dashboard-builder.render-report,以 cases/loongsuite-pilot-insight 为 case-dir,生成 cases/loongsuite-pilot-insight/output/-report.html。
  6. 用户确认预览没问题后,再 create 或 update 线上 SLS 报表;不要跳过预览直接发布。

What it can do on your machine

Read from SKILL.md and the folder at commit 94cb9d4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Loongsuite Pilot Insight loads about 944 tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 222 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~944

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alibaba/loongsuite-pilot at commit 94cb9d4, republished under its Apache-2.0 licence (© alibaba). 222 words, ~944 tokens.

Download SKILL.mdSave it as .claude/skills/loongsuite-pilot-insight/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
loongsuite-pilot-insight
description
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、dept_user 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。

LoongSuite Pilot Insight

Purpose

将 LoongSuite Pilot / AI Coding Agent 日志转化为可复用的报表语义。用户应直接使用本 skill;本 skill 负责业务数据语义、指标口径和场景需求解释,再调用 sls-dashboard-builder 的通用能力生成或修改 SLS dashboard JSON。

Boundaries

  • 业务语义放在本 skill:schema.md、cases/loongsuite-pilot-insight/input/<scenario>-spec.md、业务脚本。
  • 通用 SLS dashboard JSON 结构、图表配方、布局和校验规则来自 sls-dashboard-builder。
  • 生成产物只写入 cases/loongsuite-pilot-insight/output/,不要写入 skill 目录。
  • *-report.html 是 dashboard JSON 生成后的固定本地预览产物,不作为独立 spec。
  • 不要把 LoongSuite Pilot 业务 schema、CTE、脚本或产物写进 sls-dashboard-builder。

Inputs And Outputs

  • 默认需求入口:cases/loongsuite-pilot-insight/input/<scenario>-spec.md
  • 默认 dashboard 输出:cases/loongsuite-pilot-insight/output/<scenario>-dashboard.json
  • 默认预览输出:cases/loongsuite-pilot-insight/output/<scenario>-report.html
  • 数据语义入口:schema.md

若用户只给自然语言需求,先选择或创建一个清晰的 <scenario>-spec.md,再按标准流程生成 dashboard 和预览。

Workflow

  1. 确定 <scenario>,读取或创建 cases/loongsuite-pilot-insight/input/<scenario>-spec.md。
  2. 读取 schema.md,确认 Data Source Bindings、字段语义、公共 CTE、指标可加性和风险点。
  3. 解析 spec,将自然语言需求转成视图清单:指标、SQL、图表类型、布局、筛选器和说明块。
  4. 使用 sls-dashboard-builder 生成或更新 cases/loongsuite-pilot-insight/output/<scenario>-dashboard.json。
  5. 调用 sls-dashboard-builder.render-report,以 cases/loongsuite-pilot-insight 为 case-dir,生成 cases/loongsuite-pilot-insight/output/<scenario>-report.html。
  6. 用户确认预览没问题后,再 create 或 update 线上 SLS 报表;不要跳过预览直接发布。

新增同类报表时只新增 cases/loongsuite-pilot-insight/input/<scenario>-spec.md,不要新增 skill。真实 project、region、logstore 统一维护在 schema.md。

Dashboard Spec

spec 用来描述某一次 dashboard 报表需求,结构与 cases/loongsuite-pilot-insight/input/*-spec.md 保持一致。详细业务口径写在 spec 正文或 schema.md,不要塞进 SKILL.md。

最小骨架:

markdown
---
output: dashboard
dashboard:
  name: <stable-dashboard-name>
  displayName: "<dashboard display name>"
  defaultTimeRange: "-604800s"
  layout: grid
data:
  sources:
    - ai_coding_events
---

# <dashboard display name>

用自然语言描述业务目标、数据范围和全局口径。

## Section: <module name>

### <chart/control/text title>

```yaml
intent: <stat-card|line|bar|pie|top-table|filter|text>
type: <sls-chart-type>
size: <w>x<h>
```

规则:

  • data.sources 引用 schema.md 中的 logical source,例如 ai_coding_events、dept_roster。
  • dashboard.name 是生成 SLS dashboard JSON 的稳定名称,dashboard.displayName 是大盘展示名。
  • dashboard.defaultTimeRange 使用 SLS 相对时间,例如 -604800s、-86400s、-2592000s。
  • dashboard.layout 默认使用 grid。
  • 不在 spec 中重复维护真实 project、region、logstore;这些放在 schema.md 的 Data Source Bindings。
  • 不为构建归档、HTML 预览等后续产物维护独立 spec。
  • dashboard 模块统一使用 ## Section:;筛选器、静态说明块和普通图表都放在 section 下。
  • 图表元信息优先写 intent、type、size,按需补 format、unit、orientation、key、filterType、globalFilter。

Preview

生成本地预览时调用 sls-dashboard-builder.render-report,case-dir 使用 cases/loongsuite-pilot-insight;修改已有 dashboard 时带 --with-diff 生成 HTML SQL / 结果 diff;如报表 SQL 使用 token 参数,通过 --var key=value 传入本地预览值。若查询失败,应修复查询、凭据或网络问题后重新生成预览。

Guardrails

  • 不编造不存在的字段或 logstore。
  • 生成任何部门、团队或覆盖率类报表前,必须读取 schema.md。
  • dept_user 是部门类报表的关键语义;生成部门类报表前必须确认 schema.md 中的定义。
  • 当 spec 的 data.sources 只有 ai_coding_events 时,不要生成总在册人数、覆盖率、未产生日志员工列表、部门或团队 TopN;这些都需要 dept_roster 或客户自定义外表。
  • 部门维表只依赖 department 的 work_no、name、dept_name 三个索引字段。
  • Skill 统计使用 schema.md 中从 gen_ai.tool.call.arguments 的 file_path 动态解析出的 skill_name,不要使用 gen_ai.skill.name。
  • 跨表 JOIN 使用 dept_user 时,不要直接使用 compare() 做同比;按 sls-dashboard-builder 中的手动时间窗口规则处理。
  • active_user 中的 token、events 可加;去重类指标不要对预聚合结果求和。
  • 图表标题、图例、表头默认使用中文。

© alibaba, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in solutions/loongsuite-pilot-sls-dashboard/.agents/skills/loongsuite-pilot-insight of alibaba/loongsuite-pilot.

  • SKILL.md
  • schema.md

Open the folder on GitHubat commit 94cb9d4

Compare with similar skills

Loongsuite Pilot Insight next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Loongsuite Pilot Insight compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Loongsuite Pilot Insight this skillalibaba/loongsuite-pilot201—~944Automated safety check: PassApache-2.0
Logfire Instrumentationbasicmachines-co/basic-memory4.1k—~2.3kAutomated safety check: PassAGPL-3.0
Azure Monitor Opentelemetry TSmicrosoft/skills3.1k5 repos~2.2kAutomated safety check: PassMIT
Quality Codevvedantb/eva1011 repos~797Automated safety check: PassMIT
Otel JSollygarden/opentelemetry-agent-skills106—~655Automated safety check: PassApache-2.0
Golem Enable Otlp TSgolemcloud/golem1.5k—~2kAutomated safety check: PassCustom licence

Similar skills

  • Logfire Instrumentation

    basicmachines-co/basic-memory

    Adds Pydantic Logfire tracing, logging and metrics to Python, JavaScript or TypeScript and Rust projects, with the correct setup order and library extras.

    4.1k GitHub stars~2.3k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Official

    Instrument applications with Azure Monitor and OpenTelemetry for JavaScript (@azure/monitor-opentelemetry).

    3.1k GitHub starsUsed in 5 repos~2.2k tokens
    DevOps & CloudAuto-check passed
  • Quality Code

    vvedantb/eva

    A skill your agent uses when writing or reviewing TypeScript/full-stack code.

    101 GitHub starsUsed in 1 repo~797 tokens
    DevOps & CloudAuto-check passed
  • Otel JS

    ollygarden/opentelemetry-agent-skills

    OpenTelemetry in Node.js / JavaScript / TypeScript — NodeSDK, declarative YAML configuration, auto-instrumentations, ESM vs CJS import patterns.

    106 GitHub stars~655 tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Golem Enable Otlp TS

    golemcloud/golem

    Enabling the OpenTelemetry (OTLP) plugin for a TypeScript Golem agent — exporting traces, logs, and metrics to an OTLP collector, adding custom spans with the invocation context API or…

    1.5k GitHub stars~2k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and…

    12k GitHub stars~370 tokensUpdated yesterday
    Testing & QAAuto-check passed

More from alibaba/loongsuite-pilot

  • Sls Dashboard Builder

    alibaba/loongsuite-pilot

    当任务需要创建、修改、扩展或重组阿里云 SLS 的 dashboard JSON 或可导入的大盘配置时使用;尤其适用于线上大盘、强对比的分析看板、已校验的查询包,或需要专业中文标签与指标定义的运维向大盘。

    201 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

Questions about Loongsuite Pilot Insight

What does Loongsuite Pilot Insight do?

基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。. Loongsuite Pilot Insight is an agent skill from alibaba/loongsuite-pilot.

When should I use Loongsuite Pilot Insight?

Loongsuite Pilot Insight fits situations like: tasks that involve Observability.

How do I install Loongsuite Pilot Insight in Claude Code?

Run `npx skills add alibaba/loongsuite-pilot --skill loongsuite-pilot-insight -a claude-code`. Or copy the skill folder (solutions/loongsuite-pilot-sls-dashboard/.agents/skills/loongsuite-pilot-insight in alibaba/loongsuite-pilot) into .claude/skills/loongsuite-pilot-insight in your project. Claude Code loads it when a task matches its description.

How do I install Loongsuite Pilot Insight in Codex?

Run `npx skills add alibaba/loongsuite-pilot --skill loongsuite-pilot-insight -a codex`. Or copy the skill folder (solutions/loongsuite-pilot-sls-dashboard/.agents/skills/loongsuite-pilot-insight in alibaba/loongsuite-pilot) into .agents/skills/loongsuite-pilot-insight in your project. Codex loads it when a task matches its description.

Can I use Loongsuite Pilot Insight in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alibaba/loongsuite-pilot --skill loongsuite-pilot-insight -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loongsuite-pilot-insight, .gemini/skills/loongsuite-pilot-insight, .github/skills/loongsuite-pilot-insight and .opencode/skills/loongsuite-pilot-insight in your project.

What does Loongsuite Pilot Insight need to run?

SKILL.md names no scripts, command-line tools or credentials: Loongsuite Pilot Insight is instructions for the agent only.

Does Loongsuite Pilot Insight access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Loongsuite Pilot Insight safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Loongsuite Pilot Insight use?

Loongsuite Pilot Insight is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Loongsuite Pilot Insight use?

About 944 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Loongsuite Pilot Insight?

Skills that share tags, products or a category with Loongsuite Pilot Insight: Logfire Instrumentation (basicmachines-co/basic-memory, 4.1k stars), Azure Monitor Opentelemetry TS (microsoft/skills, 3.1k stars), Quality Code (vvedantb/eva, 101 stars) and Otel JS (ollygarden/opentelemetry-agent-skills, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Loongsuite Pilot Insight?

alibaba (a GitHub organization) maintains it in alibaba/loongsuite-pilot, which has 201 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.

Source: alibaba/loongsuite-pilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.