New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Rudder Data Path Diagnostician Maintainer

by Undertone0809 in Undertone0809/rudder

A skill your agent uses when Rudder pages or product surfaces show missing, stale, sparse, empty, slow, or wrong data, including Calendar, runs, issues, dashboard counts, chat output, prod/local org…

Apache-2.0Auto-check passedDevelopment

Install Rudder Data Path Diagnostician Maintainer

skills CLI
$ npx skills add Undertone0809/rudder --skill rudder-data-path-diagnostician-maintainer -a claude-code

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

GitHub CLI
$ gh skill install Undertone0809/rudder rudder-data-path-diagnostician-maintainer --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/Undertone0809/rudder.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-skills-bak/maintainer/rudder-data-path-diagnostician-maintainer .claude/skills/rudder-data-path-diagnostician-maintainer && 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
rudder-data-path-diagnostician-maintainer
GitHub stars
292
Token cost
~1.9k tokens
SKILL.md length
994 words
Files
2 (incl. references)
Skills in repo
30
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when Rudder pages or product surfaces show missing, stale, sparse, empty, slow, or wrong data, including Calendar, runs, issues, dashboard counts, chat output, prod/local org…

  • Works in 6 steps: Confirm the symptom and target environment → Identify the UI data request → Inspect the API and service chain → …
  • Product surfaces show missing
  • SKILL.md covers Use When, Do Not Use When, Default Workflow and Output Shape, plus 2 more sections
  • Calls curl

What it does

Rudder Data Path Diagnostician Maintainer is an agent skill from Undertone0809/rudder. Use when Rudder pages or product surfaces show missing, stale, sparse, empty, slow, or wrong data, including Calendar, runs, issues, dashboard counts, chat output, prod/local org data, API/UI/DB mismatches, or “这个数据从哪来”.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/runbook.md`).

It sits in Development. The repository describes itself as: Open-source local Agent harness for self-improving agent teams: run agents, review work, and turn feedback into reusable skills. The licence is Apache-2.0.

When your agent uses it

  • Product surfaces show missing
  • Including Calendar
  • Dashboard counts
  • Prod/local org data

Example prompts

  • “这个数据从哪来”
  • “/rudder-data-path-diagnostician-maintainer”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Confirm the symptom and target environment
  2. Identify the UI data request
  3. Inspect the API and service chain
  4. Read source data safely
  5. Classify the root cause
  6. Recommend or implement the fix

What it can do on your machine

Read from SKILL.md and the folder at commit 2676a5c. 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

    Shell commands in SKILL.md call:

    • curl

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

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    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

Rudder Data Path Diagnostician Maintainer loads about 1.9k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 994 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.8k

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 Undertone0809/rudder at commit 2676a5c, republished under its Apache-2.0 licence (© Undertone0809). 994 words, ~1,891 tokens.

Download SKILL.mdSave it as .claude/skills/rudder-data-path-diagnostician-maintainer/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
rudder-data-path-diagnostician-maintainer
description
Use when Rudder pages or product surfaces show missing, stale, sparse, empty, slow, or wrong data, including Calendar, runs, issues, dashboard counts, chat output, prod/local org data, API/UI/DB mismatches, or “这个数据从哪来”.

Rudder Data Path Diagnostician Maintainer

Use this skill when the user's real problem is that a Rudder surface does not show the data they expected.

The goal is to produce an evidence-backed data lineage and root cause, not to guess from the screenshot. Most failures in this class are caused by one of:

  • wrong runtime or organization
  • empty source records
  • filtering or date-window mismatch
  • derived data that is not generated from the records the user expected
  • API/service aggregation gap
  • UI rendering or state merge bug
  • stale seed/demo assumptions

This skill also has an explanation mode. When the user asks "这个数据从哪来" or "现在的渲染逻辑是怎样的" and the data is no longer missing, explain the lineage from UI query to API route, service aggregation, derived records, and rendering states. In explanation mode, read-only source tracing may be enough; do not force database inspection when code and API contracts already answer the question.

Use When

Use this skill for questions like:

  • "为什么 Calendar 没数据"
  • "这个 Dashboard 怎么是空的"
  • "prod z studio 下这里怎么没有 run / issue / calendar"
  • "这个 UI 的数据从哪里来"
  • "看起来应该有数据，但页面没有显示"
  • "这个数字和数据库/API 对不上"
  • "是不是 seed 数据没有写进去"

This skill is useful across dev, prod-local Desktop, worktree previews, and local production-style instances.

Do Not Use When

Do not use this skill for:

  • a single agent run transcript failure; use debug-run-transcript-maintainer
  • creating demo or screenshot data from scratch; use mock-data-maintainer
  • pure UI polish where the data is already known; use rudder-ui-polish-maintainer
  • CI, release, npm, Desktop packaging, or Chrome automation infrastructure
  • destructive cleanup of organizations or databases unless the user explicitly authorizes that separate operation

Default Workflow

1. Confirm the symptom and target environment

Start by pinning down:

  • surface: page, route, tab, card, chart, or screenshot region
  • expected data: what the user believes should appear
  • actual data: what is visible or returned
  • runtime: dev, prod-local Desktop, worktree preview, or remote deployment
  • organization: org id, URL key, display name, or selected org
  • date window, filters, and selected project/agent when relevant

Classify the mode before deep inspection:

  • diagnosis: expected data is missing, stale, sparse, or wrong.
  • explanation: the user wants the rendering or derivation logic after the visible symptom is resolved.

In explanation mode, keep the answer focused on the current code path and source hierarchy. Still name any assumptions about runtime, org, or date window when those affect the answer.

Verify the live target before trusting assumptions:

bash
curl -sS <base-url>/api/health
curl -sS <base-url>/api/orgs

For prod-local or Desktop investigations, require evidence that the active runtime is the expected local environment before inspecting or writing data.

2. Identify the UI data request

Find the component and data hook or API client that feeds the surface. Record:

  • query key or effect dependency
  • endpoint path and parameters
  • selected org/project/agent/date filters
  • fallback, loading, error, and empty-state behavior
  • client-side merge or normalization logic

Do not stop at "the component renders an empty array." Trace where that array comes from.

3. Inspect the API and service chain

Follow the endpoint into server code:

  • route path and auth/org access checks
  • request validators and default date windows
  • service function and aggregation logic
  • derived sources such as heartbeat runs, automation runs, activity, messenger context snapshots, calendar projections, cost rows, or external sync tables
  • response shape and filtering rules

Compare route behavior to the UI expectation. Many bugs are not missing rows; they are mismatched assumptions about which source is authoritative.

4. Read source data safely

Use read-only API calls or SQL queries first. Verify:

  • records exist for the selected organization
  • timestamps fall inside the UI date window
  • statuses match the service filters
  • linked ids are present and point to the expected issue, agent, project, run, automation, or conversation
  • soft-deleted, archived, hidden, or permission-gated rows are not being mistaken for visible data

Keep every query organization-scoped. Do not write, reseed, or delete data while diagnosing unless the user explicitly changes the task from diagnosis to repair.

Show full SKILL.md (368 more words)Show less
5. Classify the root cause

Use one primary classification:

  • wrong-target: the browser or process is pointed at the wrong instance or org
  • source-empty: the source table/API has no matching records
  • filter-window: data exists but the selected date/status/project/agent window excludes it
  • derived-gap: source records exist but the derived feed is not generated or linked
  • contract-gap: API response lacks data the UI needs
  • render-gap: API response is correct but UI state/rendering hides it
  • seed-gap: demo or fixture data was expected but not seeded into this target
  • sync-gap: external provider or import has not produced local records

If multiple causes contribute, identify the first broken boundary and the downstream symptoms separately.

6. Recommend or implement the fix

By default, report the diagnosis and fix options. Implement only when the user asked to fix it or the next safe code change is obvious.

Fix choices should match the cause:

  • wrong target: point the browser/process at the right runtime and verify
  • source empty or seed gap: use mock-data-maintainer or a scoped seed path
  • filter-window: adjust UI defaults or make filters visible
  • derived gap: fix service aggregation or generation logic
  • contract gap: sync shared/server/UI contract and tests
  • render gap: fix component state/rendering and verify visually
  • sync gap: repair provider sync or report external prerequisite

For user-visible behavior changes, add or update E2E coverage when the repo rules require it.

Output Shape

Keep the final answer concrete:

markdown
Root cause: <classification and one-sentence cause>

Evidence:
- UI requested ...
- API returned ...
- Source data shows ...
- Service logic does ...

Fix:
- ...

Validation:
- ...

When useful, include a short lineage:

text
Calendar page -> GET /api/orgs/:orgId/calendar/events
  -> calendar_events rows
  -> heartbeat_runs projections
  -> projected heartbeat schedules

Safety Rules

  • Diagnosis is read-only by default.
  • Verify runtime and organization before any write.
  • Never use unscoped SQL against production-like data.
  • Do not invent demo records to make a bug disappear.
  • Do not conflate "no persisted rows" with "no product data" when the surface intentionally derives events from runs, schedules, or activity.
  • If the user provides a screenshot, use it to locate the symptom, not as proof of the backend state.

Handoff Rules

If code changed, follow normal Rudder validation, commit, and push rules. Stage only files changed for this task and keep unrelated dirty worktree changes out of the commit.

If no code changed, hand off the exact current state and next repair command or file path. Do not claim the issue is fixed when only the data lineage was explained.

© Undertone0809, 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 (references) in agent-skills-bak/maintainer/rudder-data-path-diagnostician-maintainer of Undertone0809/rudder.

  • SKILL.md
  • references/runbook.md

Open the folder on GitHubat commit 2676a5c

Compare with similar skills

Rudder Data Path Diagnostician Maintainer 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.

Rudder Data Path Diagnostician Maintainer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rudder Data Path Diagnostician Maintainer this skillUndertone0809/rudder292—~1.9kAutomated safety check: PassApache-2.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from Undertone0809/rudder

All 30 skills in this repo

  • Conversation To Skill

    Undertone0809/rudder

    Turn the current conversation's workflow into a reusable agent skill.

    292 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed

  • Rudder Worktree Preview Maintainer

    Undertone0809/rudder

    A skill your agent uses when starting the current Rudder checkout as a temporary managed local preview with a stable URL, readiness check, logs, stop command, and cleanup path for manual inspection…

    292 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed

  • Stop Rudder Dev Maintainer

    Undertone0809/rudder

    A skill your agent uses when the user explicitly asks to stop, restart, kill, or clean Rudder repo-local pnpm dev processes or local dev runtime residue, including “把 pnpm dev 停了”, “重启 dev”, or “清掉…

    292 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Deep Research

    Undertone0809/rudder

    Conducts enterprise-grade research with multi-source synthesis, citation tracking, and verification.

    292 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Rudder Workspace Hygiene Maintainer

    Undertone0809/rudder

    A skill your agent uses to audit or clean Rudder worktrees, generated artifacts, logs, caches, and repo-owned processes without deleting active work, user data, or unrelated machine state.

    292 GitHub stars~664 tokensUpdated yesterday
    Auto-check passed

  • Visualize

    Undertone0809/rudder

    Create safe inline visual explanations in Rudder Chat. An agent skill from Undertone0809/rudder.

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

Categories

Questions about Rudder Data Path Diagnostician Maintainer

What does Rudder Data Path Diagnostician Maintainer do?

A skill your agent uses when Rudder pages or product surfaces show missing, stale, sparse, empty, slow, or wrong data, including Calendar, runs, issues, dashboard counts, chat output, prod/local org…. Rudder Data Path Diagnostician Maintainer is an agent skill from Undertone0809/rudder. Use when Rudder pages or product surfaces show missing, stale, sparse, empty, slow, or wrong data, including Calendar, runs, issues, dashboard counts, chat output, prod/local org data, API/UI/DB mismatches, or “这个数据从哪来”.

When should I use Rudder Data Path Diagnostician Maintainer?

Rudder Data Path Diagnostician Maintainer fits situations like: product surfaces show missing; including Calendar; dashboard counts; prod/local org data.

How do I install Rudder Data Path Diagnostician Maintainer in Claude Code?

Run `npx skills add Undertone0809/rudder --skill rudder-data-path-diagnostician-maintainer -a claude-code`. Or copy the skill folder (agent-skills-bak/maintainer/rudder-data-path-diagnostician-maintainer in Undertone0809/rudder) into .claude/skills/rudder-data-path-diagnostician-maintainer in your project. Claude Code loads it when a task matches its description.

How do I install Rudder Data Path Diagnostician Maintainer in Codex?

Run `npx skills add Undertone0809/rudder --skill rudder-data-path-diagnostician-maintainer -a codex`. Or copy the skill folder (agent-skills-bak/maintainer/rudder-data-path-diagnostician-maintainer in Undertone0809/rudder) into .agents/skills/rudder-data-path-diagnostician-maintainer in your project. Codex loads it when a task matches its description.

Can I use Rudder Data Path Diagnostician Maintainer 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 Undertone0809/rudder --skill rudder-data-path-diagnostician-maintainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rudder-data-path-diagnostician-maintainer, .gemini/skills/rudder-data-path-diagnostician-maintainer, .github/skills/rudder-data-path-diagnostician-maintainer and .opencode/skills/rudder-data-path-diagnostician-maintainer in your project.

What does Rudder Data Path Diagnostician Maintainer need to run?

Going by SKILL.md and its folder, Rudder Data Path Diagnostician Maintainer needs the command-line tools its instructions call (curl).

Does Rudder Data Path Diagnostician Maintainer access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Rudder Data Path Diagnostician Maintainer 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 Rudder Data Path Diagnostician Maintainer use?

Rudder Data Path Diagnostician Maintainer 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 Rudder Data Path Diagnostician Maintainer use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Rudder Data Path Diagnostician Maintainer?

Skills that share tags, products or a category with Rudder Data Path Diagnostician Maintainer: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rudder Data Path Diagnostician Maintainer?

Undertone0809 (a GitHub user) maintains it in Undertone0809/rudder, which has 292 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 10, 2026.

Source: Undertone0809/rudder on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.