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

91%

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

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.

An actionable, well-organized read-only skill body with copy-paste commands backed by a real bundled script. The main gaps are mild redundancy in defaults and inline detail that could live in reference files.

Suggestions

Consolidate the defaults into a single section to remove the duplication between the Quick start 'Defaults:' bullet and the 'Inputs and defaults' block.

Consider moving the 'API requirements' endpoint list and 'Output formatting rules' into a reference file, leaving SKILL.md as a tighter overview that links one level deep.

Trim the AGENT_SKILLS_HOME installation explanation or relocate it to a setup reference, keeping the body focused on the API tasks themselves.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and free of concepts Claude already knows, but defaults appear twice (Quick start 'Defaults:' and the 'Inputs and defaults' section) and the AGENT_SKILLS_HOME install explanation adds minor padding; fits the 'efficient, minor trimmable instances' anchor rather than the fully-lean 5.	4 / 5
Actionability	Five copy-paste-ready commands invoking the real bundled scripts/sentry_api.py with concrete flags cover the common cases, matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	Tasks are clearly sequenced with an explicit short-ID resolution step, an auth checkpoint, and an 'If no results, state explicitly' verification note; it is read-only so the destructive/batch cap does not apply, but validation remains light enough to stop short of 5.	4 / 5
Progressive Disclosure	Sections are well organized and the bundled script (verified to exist at scripts/sentry_api.py) is a clear one-level reference, but at ~120 lines with API requirements and output-formatting rules inlined rather than split into reference files it fits the 'good structure, minor organization gaps' anchor rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

100%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, third-person description that pairs concrete capabilities with natural trigger phrases and an explicit exclusion boundary. It scores at the top of every dimension with no verbosity or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Inspect Sentry issues, summarize production errors, and pull health data via the Sentry API (read-only)' — matching the comprehensive-coverage anchor; 'pull health data' is mildly generic but the API qualifier and three distinct actions keep it at 5 rather than 4.	5 / 5
Completeness	Explicitly answers both 'what' (inspect issues, summarize errors, pull health data) and 'when' ('Use when user says...') with concrete trigger phrases, plus the SENTRY_AUTH_TOKEN requirement, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Provides natural phrases users would actually say — 'check Sentry', 'what errors in production?', 'summarize Sentry issues', 'recent crashes', 'production error report' — with synonym coverage, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Clear Sentry read-only niche with explicit negative boundary ('Do NOT use for setting up Sentry SDK, configuring alerts, or non-Sentry error monitoring'), minimizing overlap with adjacent skills.	5 / 5
	Total	20 / 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: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(monitoring)/sentry/SKILL.md
Commit: fe318be

Reviewed: 3 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.