sentry

Inspect Sentry issues, summarize production errors, and pull health data via the Sentry API (read-only). Use when user says "check Sentry", "what errors in production?", "summarize Sentry issues", "recent crashes", or "production error report". Requires SENTRY_AUTH_TOKEN. Do NOT use for setting up Sentry SDK, configuring alerts, or non-Sentry error monitoring.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable skill body built around a real bundled script, with clear sequencing of read-only Sentry tasks. Its main weaknesses are minor content duplication and the absence of explicit validation checkpoints in the workflow.

Suggestions

De-duplicate the defaults: state time range, environment, and limit once (either in Quick start or in Inputs and defaults) rather than repeating them across both sections.

Consider removing or trimming the "API requirements" endpoint list since the bundled script already owns those paths, or move it into the script as comments to reduce token overhead.

Add an explicit validation checkpoint early in the workflow, e.g., after setting SENTRY_AUTH_TOKEN run a low-cost list-issues call to confirm auth before proceeding to detail/events.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command/config reference with no concept explanations Claude already knows, but defaults are stated twice ("Quick start" and "Inputs and defaults") and the "API requirements" endpoint list duplicates what the bundled script already handles, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready `python3 "$SENTRY_API" ...` commands with concrete args for each task, backed by a real `scripts/sentry_api.py` that matches the documented subcommands.	3 / 3
Workflow Clarity	Tasks are numbered and sequenced (e.g., resolve short ID to issue ID, then use it for detail/events), but there are no explicit validation checkpoints such as confirming the token works or verifying non-empty results before drilling into detail.	2 / 3
Progressive Disclosure	A single well-sectioned SKILL.md points one level deep to the bundled `scripts/sentry_api.py` (a real file), with no nested references and clear section organization for navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities, provides natural trigger phrases, and explicitly scopes what the skill should and should not be used for. It uses third-person/imperative voice with no first- or second-person padding.

Dimension	Reasoning	Score
Specificity	"Inspect Sentry issues, summarize production errors, and pull health data via the Sentry API" lists multiple concrete actions, matching the score-3 anchor of several specific capabilities.	3 / 3
Completeness	It explicitly answers both what (inspect/summarize/pull) and when (an explicit "Use when..." clause with concrete triggers), meeting the score-3 anchor; not capped at 2 since the trigger guidance is present.	3 / 3
Trigger Term Quality	"Use when user says \"check Sentry\", \"what errors in production?\", \"summarize Sentry issues\", \"recent crashes\", or \"production error report\"" are natural phrases a user would actually say, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to Sentry read-only with explicit "Do NOT use for setting up Sentry SDK, configuring alerts, or non-Sentry error monitoring" exclusions, giving a clear niche unlikely to conflict.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(monitoring)/sentry/SKILL.md
Commit: 4beb507

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.