Agent skill

Debug With Sentry

by superset-sh in superset-sh/superset

Root-cause a production error with Sentry's evidence before touching code — pull the issue, read the stack trace and breadcrumbs, and separate the crash from its trigger.

Custom licenceAuto-check passedDevelopment

Install Debug With Sentry

skills CLI
$ npx skills add superset-sh/superset --skill debug-with-sentry -a claude-code

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

GitHub CLI
$ gh skill install superset-sh/superset debug-with-sentry --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/superset-sh/superset.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/sentry/skills/debug-with-sentry .claude/skills/debug-with-sentry && 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
debug-with-sentry
GitHub stars
15k
Token cost
~828 tokens
SKILL.md length
426 words
Files
1
Skills in repo
47
Repo updated
First seen
Licence
Custom licence

At a glance

Root-cause a production error with Sentry's evidence before touching code — pull the issue, read the stack trace and breadcrumbs, and separate the crash from its trigger.

  • Works in 4 steps: Get the real issue, not the search hit → Read the stack trace like a diff → Use the distribution before the theory → …
  • The user pastes a Sentry link
  • SKILL.md covers 1. Get the real issue, not the…, 2. Read the stack trace like a…, 3. Use the distribution before… and 4. Report cause, scope, and…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Debug With Sentry is an agent skill from superset-sh/superset. Root-cause a production error with Sentry's evidence before touching code — pull the issue, read the stack trace and breadcrumbs, and separate the crash from its trigger. Use when the user pastes a Sentry link or issue ID, reports a production error, or asks why something is crashing for users.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging and Root cause analysis. It works with Sentry. The repository describes itself as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

When your agent uses it

  • The user pastes a Sentry link
  • Reports a production error
  • Asks why something is crashing for users

Example prompts

  • “/debug-with-sentry”

Requirements

  • Pre-approved tools (allowed-tools): mcp__sentry__get_issue_details, mcp__sentry__get_event_stacktrace, mcp__sentry__get_issue_breadcrumbs, mcp__sentry__get_issue_tag_values, mcp__sentry__search_issues, mcp__sentry__search_events, mcp__sentry__find_releases, mcp__sentry__analyze_issue_with_seer, mcp__sentry__update_issue

Workflow steps

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

  1. Get the real issue, not the search hit
  2. Read the stack trace like a diff
  3. Use the distribution before the theory
  4. Report cause, scope, and blast radius

What it can do on your machine

Read from SKILL.md and the folder at commit 2e47842. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • mcp__sentry__get_issue_details
    • mcp__sentry__get_event_stacktrace
    • mcp__sentry__get_issue_breadcrumbs
    • mcp__sentry__get_issue_tag_values
    • mcp__sentry__search_issues
    • mcp__sentry__search_events
    • mcp__sentry__find_releases
    • mcp__sentry__analyze_issue_with_seer
    • mcp__sentry__update_issue

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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

Debug With Sentry loads about 828 tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 426 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~828

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 426 words (~828 tokens).

“A Sentry issue is a claim about what broke. The job is to turn it into a claim about why it broke, backed by the event data, before anyone edits code.”

— opening of SKILL.md by superset-sh, Custom licence
name
debug-with-sentry
allowed-tools
mcp__sentry__get_issue_details, mcp__sentry__get_event_stacktrace, mcp__sentry__get_issue_breadcrumbs, mcp__sentry__get_issue_tag_values, mcp__sentry__search_issues, mcp__sentry__search_events, mcp__sentry__find_releases, mcp__sentry__analyze_issue_with_seer, mcp__sentry__update_issue
argument-hint
the Sentry issue URL, short ID, or a description of the error

Read the full SKILL.md on GitHub

Files

Just SKILL.md in plugins/sentry/skills/debug-with-sentry of superset-sh/superset.

Open the folder on GitHubat commit 2e47842

Compare with similar skills

Debug With Sentry 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.

Debug With Sentry compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Debug With Sentry this skillsuperset-sh/superset15k—~828Automated safety check: PassCustom licence
Sentry Issue Fix Looptixl3d/tixl5.1k—~2.1kAutomated safety check: NotesMIT
Sentrymitsuhiko/agent-stuff3.2k—~1.8kAutomated safety check: PassApache-2.0
Production Error Huntdifferent-ai/openwork24k—~803Automated safety check: PassCustom licence
Sentry Fix Issuesgetsentry/sentry-for-ai2683 repos~1.9kAutomated safety check: PassApache-2.0
Sentry Debug Issuegetsentry/sentry-for-ai268—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • Walks through open Sentry issues for the tooll3 project, latest first, proposing a fix for each and committing them one at a time with your review between.

    5.1k GitHub stars~2.1k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Sentry

    mitsuhiko/agent-stuff

    Fetch and analyze Sentry issues, events, transactions, and logs.

    3.2k GitHub stars~1.8k tokensUpdated 11 days ago
    DevelopmentAuto-check passed
  • Production Error Hunt

    different-ai/openwork

    Traces an opaque production error in an OpenWork build to its cause using local server logs and Sentry, names the regressing PR and files a report.

    24k GitHub stars~803 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Sentry Fix Issues

    getsentry/sentry-for-ai

    Official

    Find and fix issues from Sentry using MCP. An agent skill from getsentry/sentry-for-ai.

    268 GitHub starsUsed in 3 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Sentry Debug Issue

    getsentry/sentry-for-ai

    Official

    Debug and fix a Sentry issue — find it (by link, ID, or search), pull full context (stack trace, breadcrumbs, trace, logs), optionally run Seer root-cause / autofix, apply the code fix, and resolve…

    268 GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Axiom SRE Investigator

    openclaw/clawhub

    Investigates incidents and production problems with hypothesis-driven debugging, queries Axiom observability data when available, and keeps secrets out of commands and output.

    9.5k GitHub stars~7.1k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from superset-sh/superset

All 47 skills in this repo
  • Mobile Demo Film Editor

    superset-sh/superset

    Edits real mobile screen recordings into a configurable demo video with phone framing, title cards, cutaways and an end card, using a bundled renderer.

    15k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Superset Agent Standup

    superset-sh/superset

    Sweeps every Superset workspace, task and agent terminal to report what finished, what needs review and what is blocked, read-only, and can publish the digest as a page.

    15k GitHub stars~712 tokensUpdated yesterday
    Auto-check passed
  • Superset Browser Control

    superset-sh/superset

    Opens pages, takes screenshots, reads the console, clicks and types in the browser panes of a Superset workspace, with Browser Use as a fallback for other browsers.

    15k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • Superset Automate

    superset-sh/superset

    Turns a recurring chore into a scheduled or event-triggered Superset agent, drafting its prompt, picking a target and trigger, and reviewing the first run.

    15k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Generates a Drizzle migration on a fresh Neon branch and runs a production-safety checklist for table sizes, lock order and load rehearsal before the PR opens.

    15k GitHub stars~2k tokensUpdated yesterday
    Auto-check: notes
  • Superset Feedback Reporter

    superset-sh/superset

    Turns a bug report or feature request about Superset into a short, scannable write-up and submits it privately or as a public GitHub issue.

    15k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Debug With Sentry

What does Debug With Sentry do?

Root-cause a production error with Sentry's evidence before touching code — pull the issue, read the stack trace and breadcrumbs, and separate the crash from its trigger. Debug With Sentry is an agent skill from superset-sh/superset. Root-cause a production error with Sentry's evidence before touching code — pull the issue, read the stack trace and breadcrumbs, and separate the crash from its trigger.

When should I use Debug With Sentry?

Debug With Sentry fits situations like: the user pastes a Sentry link; reports a production error; asks why something is crashing for users.

How do I install Debug With Sentry in Claude Code?

Run `npx skills add superset-sh/superset --skill debug-with-sentry -a claude-code`. Or copy the skill folder (plugins/sentry/skills/debug-with-sentry in superset-sh/superset) into .claude/skills/debug-with-sentry in your project. Claude Code loads it when a task matches its description.

How do I install Debug With Sentry in Codex?

Run `npx skills add superset-sh/superset --skill debug-with-sentry -a codex`. Or copy the skill folder (plugins/sentry/skills/debug-with-sentry in superset-sh/superset) into .agents/skills/debug-with-sentry in your project. Codex loads it when a task matches its description.

Can I use Debug With Sentry 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 superset-sh/superset --skill debug-with-sentry -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/debug-with-sentry, .gemini/skills/debug-with-sentry, .github/skills/debug-with-sentry and .opencode/skills/debug-with-sentry in your project.

What does Debug With Sentry need to run?

SKILL.md names no scripts, command-line tools or credentials: Debug With Sentry is instructions for the agent only. Its frontmatter pre-approves these tools: mcp__sentry__get_issue_details, mcp__sentry__get_event_stacktrace, mcp__sentry__get_issue_breadcrumbs, mcp__sentry__get_issue_tag_values, mcp__sentry__search_issues, mcp__sentry__search_events, mcp__sentry__find_releases, mcp__sentry__analyze_issue_with_seer, mcp__sentry__update_issue.

Does Debug With Sentry 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 Debug With Sentry 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 Debug With Sentry use?

Debug With Sentry has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Debug With Sentry use?

About 828 tokens (SKILL.md is roughly 3.3k 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 Debug With Sentry?

Skills that share tags, products or a category with Debug With Sentry: Sentry Issue Fix Loop (tixl3d/tixl, 5.1k stars), Sentry (mitsuhiko/agent-stuff, 3.2k stars), Production Error Hunt (different-ai/openwork, 24k stars) and Sentry Fix Issues (getsentry/sentry-for-ai, 268 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Debug With Sentry?

superset-sh (a GitHub organization) maintains it in superset-sh/superset, which has 14,974 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 8, 2026.

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