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`.

2.04x

Quality

87%

Does it follow best practices?

Impact

94%

2.04x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

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

A well-structured, highly actionable read-only API skill body with executable commands and clear sequencing. Its main weakness is minor redundancy in stating defaults and inputs in two places.

Suggestions

Remove the duplicate 'Defaults:' line in Quick start since the same defaults are already covered in the 'Inputs and defaults' section.

Add a short validation/feedback note for the short-ID resolution step (e.g., confirm a matching issue was found before calling issue-detail) to strengthen the workflow's error-recovery loop.

Consider moving the 'API requirements' endpoint list into the bundled script's --help or a reference file to keep SKILL.md focused on usage.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable command blocks and tight sections, but defaults are stated twice (Quick start 'Defaults:' line and the 'Inputs and defaults' section) and the token-creation numbered list could be trimmed slightly.	4 / 5
Actionability	Provides copy-paste ready bash commands for every core task (list-issues, issue-detail, issue-events, event-detail) with explicit flags, script-path setup, and documented placeholder defaults.	5 / 5
Workflow Clarity	Clear numbered sequence with a prerequisite short-ID resolution step and an explicit 'if no results, state explicitly' checkpoint, but lacks an explicit error-recovery feedback loop beyond the script's single retry.	4 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level-deep reference to the bundled scripts/sentry_api.py (verified present), though the inline API-requirements and inputs sections carry minor redundancy rather than being split out.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 with an explicit 'Use when...' trigger clause and a clear read-only scope. It is third-person/imperative in voice and distinguishes itself clearly from neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'inspect Sentry issues or events', 'summarize recent production errors', 'pull basic Sentry health data', 'perform read-only queries with the bundled script' — giving comprehensive coverage of the read-only observability scope.	5 / 5
Completeness	Explicitly answers both what ('perform read-only queries with the bundled script and require SENTRY_AUTH_TOKEN') and when ('Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data').	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('Sentry issues or events', 'recent production errors', 'Sentry health data') but is missing some common synonyms/variants (e.g., 'alerts', 'error reports') that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	Sentry-specific niche with distinct triggers ('Sentry issues or events', 'Sentry API', 'SENTRY_AUTH_TOKEN') and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/sentry/SKILL.md
Commit: d5ae560

Reviewed: 2 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.