sentry-triage
Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.
What this skill does
# Sentry Triage
Pull Sentry issues, events, and suspect commits straight into the agent via the [Composio CLI](https://docs.composio.dev/docs/cli). Skip the copy-paste-stack-trace dance.
## When to Use
- New Sentry alert and you want the agent to investigate, not just quote the subject line.
- Diagnosing a regression: find the releases, suspect commit, and affected files.
- Building a "top 10 unresolved issues" digest with reproduction hints.
## Prereqs
```bash
curl -fsSL https://composio.dev/install | bash
composio login
composio link sentry # auth token with event:read + project:read
```
## Discover Tools
```bash
composio search "get sentry issue" --toolkits sentry
composio search "list events for issue" --toolkits sentry
composio tools list sentry
```
Common slugs (verify with `--get-schema`):
- `SENTRY_GET_AN_ISSUE`
- `SENTRY_LIST_AN_ISSUES_EVENTS`
- `SENTRY_RETRIEVE_AN_EVENT_FOR_A_PROJECT`
- `SENTRY_LIST_A_PROJECTS_ISSUES`
- `SENTRY_UPDATE_AN_ISSUE`
## Diagnose a Single Issue
1. **Fetch the issue** (by short ID like `PROJ-1F4` or numeric ID):
```bash
composio execute SENTRY_GET_AN_ISSUE -d '{"issue_id":"PROJ-1F4"}'
```
2. **Grab the latest event** with full stack + breadcrumbs:
```bash
composio execute SENTRY_LIST_AN_ISSUES_EVENTS \
-d '{"issue_id":"PROJ-1F4","full":true,"limit":1}'
```
3. **Map each frame to local source.** For each `filename` + `lineno` in the stack, the agent opens the file and reads ±20 lines. No manual copy-paste.
4. **Check suspect commits** (Sentry attaches these when release tracking is set up) — open them with `git show <sha>` locally.
5. **Propose a fix** with a diff, run tests, and — once green — mark the issue resolved:
```bash
composio execute SENTRY_UPDATE_AN_ISSUE \
-d '{"issue_id":"PROJ-1F4","status":"resolved","statusDetails":{"inNextRelease":true}}'
```
## Triage a Batch
```bash
composio execute SENTRY_LIST_A_PROJECTS_ISSUES -d '{
"organization_slug":"acme",
"project_slug":"api",
"query":"is:unresolved age:-24h",
"sort":"freq",
"limit":20
}'
```
Pipe into `jq` for a ranked summary:
```bash
composio execute SENTRY_LIST_A_PROJECTS_ISSUES -d '{"organization_slug":"acme","project_slug":"api","query":"is:unresolved"}' \
| jq -r '.[] | "\(.count)\t\(.shortId)\t\(.title)"' | sort -rn | head
```
## Workflow File
`scripts/sentry-diag.ts`, run with `composio run --file scripts/sentry-diag.ts -- --id PROJ-1F4`:
```ts
const id = process.argv[process.argv.indexOf("--id") + 1];
const issue = await execute("SENTRY_GET_AN_ISSUE", { issue_id: id });
const [event] = await execute("SENTRY_LIST_AN_ISSUES_EVENTS", {
issue_id: id, full: true, limit: 1
});
const frames = (event?.entries ?? [])
.filter(e => e.type === "exception")
.flatMap(e => e.data.values.flatMap(v => v.stacktrace?.frames ?? []))
.filter(f => f.inApp)
.map(f => ({ file: f.filename, line: f.lineno, fn: f.function }));
console.log(JSON.stringify({ title: issue.title, culprit: issue.culprit, frames }, null, 2));
```
The agent then reads each `file` at `line ± 20` and drafts a patch.
## Route to Linear / Slack
Chain tools to open a ticket for the top unresolved issue:
```bash
composio run '
const [top] = await execute("SENTRY_LIST_A_PROJECTS_ISSUES", {
organization_slug: "acme", project_slug: "api",
query: "is:unresolved", sort: "freq", limit: 1
});
await execute("LINEAR_CREATE_ISSUE", {
teamId: "TEAM_ID",
title: `[Sentry] ${top.title}`,
description: `Short ID: ${top.shortId}\nPermalink: ${top.permalink}\nCount: ${top.count}`
});
'
```
## Troubleshooting
- **`404 on issue_id`** → use the short ID (`PROJ-1F4`), not the URL slug.
- **Empty events** → the issue was resolved/archived; query with `query:"is:resolved"` or bump `limit`.
- **Missing suspect commit** → release tracking isn't configured in Sentry; set up `sentry-cli releases` in CI.
- **No `inApp` frames** → source maps not uploaded; stack will only show vendor code.
Full CLI reference: [docs.composio.dev/docs/cli](https://docs.composio.dev/docs/cli)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.