sentry

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

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%Weight 40%Scale 1-3

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

The body is actionable and well structured, leaning on a real bundled script with complete copy-paste commands and a clear section layout. Its main weaknesses are mild redundancy in token/setup guidance and a lack of explicit validation or error-recovery checkpoints in the workflow.

Suggestions

Consolidate the duplicated token-setup guidance (Quick start vs. the numbered steps) into one place to remove redundancy and trim tokens.

Add an explicit error-handling/validation checkpoint after commands (e.g., what to do when the API returns an empty result, a 401/403, or a missing org/project error) to lift workflow clarity.

Drop or condense the static 'API requirements' endpoint list since the bundled script already encodes these endpoints; keep it only if Claude is expected to call the API directly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the token-setup steps duplicate the Quick start guidance and the explicit endpoint list partly restates behavior the bundled script already implements, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready CLI commands with every flag, and the referenced bundled script (scripts/sentry_api.py) exists and exposes exactly the documented subcommands.	3 / 3
Workflow Clarity	Tasks are numbered and the short-ID-to-issue-ID flow is sequenced, but error-recovery and validation checkpoints are only implicit (e.g., how to react to HTTP failures or missing org/project beyond the script's own error) rather than explicitly called out.	2 / 3
Progressive Disclosure	A single well-organized SKILL.md with clearly labeled sections and one real bundled script; no nested multi-level references, which is appropriate for a skill of this size.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

The description is concise, specific, and provides an explicit trigger clause covering several natural user phrasings, while clearly scoping the skill to read-only Sentry API queries. Third-person voice is maintained throughout. Minor caveat: 'summarize recent production errors' is slightly broader than the documented issue/event commands, but the read-only framing keeps it defensible.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data', 'perform read-only queries with the bundled script'), matching the highest anchor.	3 / 3
Completeness	An explicit 'Use when' clause answers when, and the rest clearly states what (read-only Sentry API queries requiring SENTRY_AUTH_TOKEN), covering both.	3 / 3
Trigger Term Quality	Natural terms users would actually say are well covered ('Sentry issues', 'events', 'production errors', 'Sentry health data'), with good variation.	3 / 3
Distinctiveness Conflict Risk	A clear Sentry-only read-only niche with distinct, product-specific triggers that are unlikely to fire for other skills.	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: openai/plugins
Path: plugins/sentry/skills/sentry/SKILL.md
Commit: 11c74d6

Reviewed: 17 days 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.