Dotagents
getsentry/sentry-wizard
Manage agent skill dependencies with dotagents. An agent skill from getsentry/sentry-wizard.
A skill your agent uses when the user asks to triage user feedback collected on Sentry.
Install Sentry Triage Feedback
$ npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install isHarryh/Ark-Pets sentry-triage-feedback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/isHarryh/Ark-Pets.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/sentry-triage-feedback .claude/skills/sentry-triage-feedback && rm -rf skills-srcUse ~/.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/
Install the "sentry-triage-feedback" agent skill from https://github.com/isHarryh/Ark-Pets/tree/v3.x/.agents/skills/sentry-triage-feedback into .claude/skills/sentry-triage-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-triage-feedback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/isHarryh/Ark-Pets/tree/v3.x/.agents/skills/sentry-triage-feedbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install isHarryh/Ark-Pets sentry-triage-feedback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/isHarryh/Ark-Pets.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/sentry-triage-feedback .agents/skills/sentry-triage-feedback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sentry-triage-feedback" agent skill from https://github.com/isHarryh/Ark-Pets/tree/v3.x/.agents/skills/sentry-triage-feedback into .agents/skills/sentry-triage-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-triage-feedback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install isHarryh/Ark-Pets sentry-triage-feedback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/isHarryh/Ark-Pets.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/sentry-triage-feedback .cursor/skills/sentry-triage-feedback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sentry-triage-feedback" agent skill from https://github.com/isHarryh/Ark-Pets/tree/v3.x/.agents/skills/sentry-triage-feedback into .cursor/skills/sentry-triage-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-triage-feedback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/isHarryh/Ark-Pets.git --path .agents/skills/sentry-triage-feedback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install isHarryh/Ark-Pets sentry-triage-feedback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/isHarryh/Ark-Pets.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/sentry-triage-feedback .gemini/skills/sentry-triage-feedback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sentry-triage-feedback" agent skill from https://github.com/isHarryh/Ark-Pets/tree/v3.x/.agents/skills/sentry-triage-feedback into .gemini/skills/sentry-triage-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-triage-feedback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install isHarryh/Ark-Pets sentry-triage-feedbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/isHarryh/Ark-Pets.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/sentry-triage-feedback .github/skills/sentry-triage-feedback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sentry-triage-feedback" agent skill from https://github.com/isHarryh/Ark-Pets/tree/v3.x/.agents/skills/sentry-triage-feedback into .github/skills/sentry-triage-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-triage-feedback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install isHarryh/Ark-Pets sentry-triage-feedback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/isHarryh/Ark-Pets.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/sentry-triage-feedback .opencode/skills/sentry-triage-feedback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sentry-triage-feedback" agent skill from https://github.com/isHarryh/Ark-Pets/tree/v3.x/.agents/skills/sentry-triage-feedback into .opencode/skills/sentry-triage-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-triage-feedback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sentry-triage-feedback- GitHub stars
- 1.1k
- Token cost
- ~2.1k tokens
- SKILL.md length
- 839 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
A skill your agent uses when the user asks to triage user feedback collected on Sentry.
- Works in 6 steps: Confirm the time range with the user:… → Confirm write permission with the user:… → List the feedback using search_issues… → …
- The user asks to triage user feedback collected on Sentry
- SKILL.md covers Target Data, Master Workflow, Per-Issue Procedure and Tool Cheat Sheet
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Sentry Triage Feedback is an agent skill from isHarryh/Ark-Pets. Use this skill when the user asks to triage user feedback collected on Sentry. Requires the Sentry MCP server.
Its SKILL.md is about 2.1k 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 Agent Workflows. It works with Sentry and Model Context Protocol. The repository describes itself as: Arknights Desktop Pets | 明日方舟桌宠 (ArkPets). The licence is GPL-3.0.
When your agent uses it
- The user asks to triage user feedback collected on Sentry
Example prompts
- “/sentry-triage-feedback”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Confirm the time range with the user: 24h, 7d, 14d, 30d or 90d, together with the target organization,
- Confirm write permission with the user: whether posting comments and resolving issues are allowed.
- List the feedback using search_issues (see the tool cheat sheet) and count them.
- Dispatch the work
- Process every issue with the per-issue procedure, acting only under the granted write permission.
- Report the aggregated result (see below).
What it can do on your machine
Read from SKILL.md and the folder at commit d82d47b. 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.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
mcp.sentry.dev
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
Sentry Triage Feedback loads about 2.1k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 839 words of instructions outside code blocks.
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 isHarryh/Ark-Pets at commit d82d47b, republished under its GPL-3.0 licence (© isHarryh). 839 words, ~2,100 tokens.
Download SKILL.mdSave it as
.claude/skills/sentry-triage-feedback/SKILL.md (or your agent's skills folder).- name
- sentry-triage-feedback
- description
- Use this skill when the user asks to triage user feedback collected on Sentry. Requires the Sentry MCP server.
Skill: Feedback Triage
ArkPets users can upload their log files through the error dialog. Each upload is stored in Sentry as a feedback issue with the log files attached. This skill defines how to fetch, analyze and triage them.
Target Data
- Feedback issues are found with the search query
issue.category:feedback. - Attachments are logs:
desktop.<pid>.log, and optionallycore.<pid>.log/hs_err_pid<pid>.log. They are served astext/plain(inlined by the tool) or asapplication/octet-stream(no inline content). - Attachments follow the plan's retention period. Older feedback may have no attachments.
This skill requires the Sentry MCP server to be configured. If it is not available, you can remind the user to visit https://mcp.sentry.dev/ and do the setup.
Master Workflow
Steps
If you are not a subagent, follow this workflow.
- Confirm the time range with the user: 24h, 7d, 14d, 30d or 90d, together with the target organization, project and environment when the user did not state them explicitly.
- Confirm write permission with the user: whether posting comments and resolving issues are allowed. Read-only analysis is always allowed. Never perform any write operation without explicit approval.
- List the feedback using
search_issues(see the tool cheat sheet) and count them. - Dispatch the work:
- If there are 10 or fewer, process all of them in the current session by yourself.
- If there are more than 10, split the issue IDs into disjoint batches of at most 10 each, keep the number of issues per batch as balanced as possible, and dispatch one subagent per batch. Run at most 3 subagents in parallel and queue the remaining batches in order to avoid rate limiting.
- If the listing is truncated, tell the user and ask whether to narrow the time range or continue with further batches.
- Process every issue with the per-issue procedure, acting only under the granted write permission.
- Report the aggregated result (see below).
Subagent Dispatching
- Subagents start with a fresh context, so every subagent prompt must be self-contained: include its issue IDs, the time range, the scope and the write permission.
- Subagents must have the reference to this SKILL (
sentry-triage-feedback) and must understand that they are subagents. - If subagents are not available, you can process all of the issues by yourself.
Final Report Format
After all batches finish, report:
- The time range, the total number of feedback, and how many were commented/resolved.
- A table: Issue | First seen | Release | Classification | Action | Cause (one line).
- The issues that could not be classified (missing attachments, ambiguous content), listed for manual review.
Per-Issue Procedure
Steps
- Fetch the issue details and the latest event ID with
get_sentry_resource(withresourceType: "issue"). Note theStatus, the first-seen time and the event'srelease. - List the event's attachments with
get_event_attachment. Download eachtext/plainattachment by calling the tool again with itsattachmentId. If an attachment is stored asapplication/octet-stream, the tool returns no content, so fetch its signed download URL withcurlinstead. - Check the existing activity with
get_issue_activity(withincludeComments: true). If the issue is already resolved, or already carries the same comment, do not duplicate it. - Classify the issue by inspecting the log content, following the classification rules.
- Act only if write permission was granted: post exactly the comment required by the rules, with no extra text,
using
add_issue_note. Then resolve it withupdate_issue(status: "resolved") and withoutreason, sincereasonwould post a second comment. - Record the per-issue result for the final report.
Show full SKILL.md (264 more words)Show less
Classification Rules
Judge from the attachment content, not merely from the task name.
| Classification | Evidence in the logs | Action (only under write permission) |
|---|---|---|
| Network issue | A failure while downloading resources over the network: UnknownHostException, Socket*Exception, SSL handshake errors, target unreachable, and similar. | Comment Network issue. and resolve |
| Unzip issue | A failure while unpacking an already-downloaded archive: ZipException, unexpected EOF, truncated or corrupt zip, and similar. | Comment Unzip issue. and resolve |
| Other | Anything else, or logs unavailable (expired retention, empty upload) | No comment and no resolve; report only |
When a single log contains both kinds of failure, classify by the last failure before the feedback was uploaded, i.e. the one that prompted the user to report; do not reclassify because of earlier failures that were recovered from.
Tool Cheat Sheet
| Purpose | Tool | Key arguments |
|---|---|---|
| Search feedback | search_issues | query: "issue.category:feedback" (add is:unresolved to skip resolved ones) plus the scope filters (e.g. environment:... project:... period:...), limit: 100, sort: "date" |
| Issue details + latest event ID | get_sentry_resource | resourceType: "issue", organizationSlug: "...", resourceId: "..." |
| List / download attachments | get_event_attachment (via execute_sentry_tool) | organizationSlug: "...", projectSlug: "...", eventId, optional attachmentId |
| Read activity and comments | get_issue_activity (via execute_sentry_tool) | issueUrl, includeComments: true |
| Post a comment | add_issue_note (via execute_sentry_tool) | issueUrl, text |
| Resolve / reopen an issue | update_issue | issueUrl or organizationSlug + issueId, status: "resolved"/"unresolved" |
| Discover other tools | search_sentry_tools | keywords |
Client note: some tools may be exposed directly with a server-name prefix
(e.g. sentry_search_issues, sentry_get_sentry_resource).
The remaining catalog tools are reached through search_sentry_tools and execute_sentry_tool.
Always prefer the exposed variants when present.
In the table above, every ... should be replaced by the actual organization or resource,
either discovered or specified by the user.
© isHarryh, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/sentry-triage-feedback of isHarryh/Ark-Pets.
Open the folder on GitHubat commit d82d47b
Compare with similar skills
Sentry Triage Feedback 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Sentry Triage Feedback this skillisHarryh/Ark-Pets | 1.1k | — | ~2.1k | Automated safety check: Pass | GPL-3.0 | |
| Dotagentsgetsentry/sentry-wizard | 295 | — | ~900 | Automated safety check: Pass | Custom licence | |
| MCP QAgetsentry/toolkit | 918 | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| MCP ServersPostHog/code | 179 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Superset Integration Toolssuperset-sh/superset | 15k | — | ~1.6k | Automated safety check: Warn | Custom licence | |
| Sentry Crash Analysishyvanmielenpelit/GnollHack | 161 | — | ~222 | Automated safety check: Pass | Custom licence |
Similar skills
- Official
- Official
MCP QA
getsentry/toolkit
QA MCP tool changes with local CLI and real agent clients. An agent skill from getsentry/toolkit.
- Official
MCP Servers
PostHog/code
Install, configure, authenticate, and troubleshoot MCP (Model Context Protocol) servers for this agent.
Superset Integration Tools
superset-sh/superset
Lists and calls the tools of connected integrations such as Linear, GitHub, Sentry or Notion through the superset mcp command, without storing a token on the machine.
Sentry Crash Analysis
hyvanmielenpelit/GnollHack
Systematic methodology for diagnosing GnollHack crash reports from the Sentry MCP server.
Fix Sentry Issues
brianlovin/agent-config
Use Sentry MCP to discover, triage, and fix production issues with root-cause analysis.
More from isHarryh/Ark-Pets
Update Changelog
isHarryh/Ark-Pets
A skill your agent uses when you're requested to update the changelog file of this project.
Related
Works with
Categories
Questions about Sentry Triage Feedback
What does Sentry Triage Feedback do?
A skill your agent uses when the user asks to triage user feedback collected on Sentry. Sentry Triage Feedback is an agent skill from isHarryh/Ark-Pets. Use this skill when the user asks to triage user feedback collected on Sentry.
When should I use Sentry Triage Feedback?
Sentry Triage Feedback fits situations like: the user asks to triage user feedback collected on Sentry.
How do I install Sentry Triage Feedback in Claude Code?
Run `npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a claude-code`. Or copy the skill folder (.agents/skills/sentry-triage-feedback in isHarryh/Ark-Pets) into .claude/skills/sentry-triage-feedback in your project. Claude Code loads it when a task matches its description.
How do I install Sentry Triage Feedback in Codex?
Run `npx skills add isHarryh/Ark-Pets --skill sentry-triage-feedback -a codex`. Or copy the skill folder (.agents/skills/sentry-triage-feedback in isHarryh/Ark-Pets) into .agents/skills/sentry-triage-feedback in your project. Codex loads it when a task matches its description.
Can I use Sentry Triage Feedback 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 isHarryh/Ark-Pets --skill sentry-triage-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sentry-triage-feedback, .gemini/skills/sentry-triage-feedback, .github/skills/sentry-triage-feedback and .opencode/skills/sentry-triage-feedback in your project.
What does Sentry Triage Feedback need to run?
SKILL.md names no scripts, command-line tools or credentials: Sentry Triage Feedback is instructions for the agent only.
Does Sentry Triage Feedback access the network?
SKILL.md names 1 domain. As links in the text: mcp.sentry.dev. This is read from the text; nothing was executed.
Is Sentry Triage Feedback 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 Sentry Triage Feedback use?
Sentry Triage Feedback is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sentry Triage Feedback use?
About 2.1k tokens (SKILL.md is roughly 8.4k 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 Sentry Triage Feedback?
Skills that share tags, products or a category with Sentry Triage Feedback: Dotagents (getsentry/sentry-wizard, 295 stars), MCP QA (getsentry/toolkit, 918 stars), MCP Servers (PostHog/code, 179 stars) and Superset Integration Tools (superset-sh/superset, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sentry Triage Feedback?
isHarryh (a GitHub user) maintains it in isHarryh/Ark-Pets, which has 1,117 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 26, 2026.
Source: isHarryh/Ark-Pets on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.