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

88%

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.

A strong, highly actionable read-only API skill: executable commands throughout, a real bundled script whose interface matches the docs, sensible defaults, and PII-redaction output rules. The main improvements are removing the duplicated defaults/endpoints sections and adding a brief error-handling path for failed API calls.

Suggestions

Remove the duplicated defaults: the "Inputs and defaults" section repeats org/project, time_range, environment, and limit values already stated in Quick start — keep one canonical location.

Drop or compress the "API requirements" endpoint list: the bundled script already wraps these endpoints, so restating them adds tokens without adding executable value.

Add a short error-recovery note (e.g., what to do when an API call returns 401/403 or fails after the script's retry) to close the workflow-clarity validation gap.

Dimension	Reasoning	Score
Conciseness	The body is dense and command-driven with no concept over-explanation, but defaults are stated twice (Quick start and "Inputs and defaults") and the "API requirements" section re-lists endpoints the bundled script already wraps. This is more than the anchor-5 ideal of every token earning its place, but well above the anchor-3 midpoint since there is no filler prose.	4 / 5
Actionability	Every task is a fully executable `python3 "$SENTRY_API" ...` command with concrete flags, declared defaults, and realistic ID examples; the referenced `scripts/sentry_api.py` exists and implements all four subcommands. Covers the common cases copy-paste ready modulo user-specific org/project substitution.	5 / 5
Workflow Clarity	Clear ordered sequence (auth setup → path export → numbered tasks) with a short-ID resolution checkpoint and explicit empty-result handling; the skill is read-only so the destructive-operation validation cap does not apply. Falls short of anchor 5 because there is no explicit error-recovery loop (e.g., what to do when a call fails besides the script's single retry).	4 / 5
Progressive Disclosure	Well-sectioned body with one correctly signaled bundle reference (`scripts/sentry_api.py`) that actually exists and matches the documented subcommands. Minor gaps: the duplicated endpoint listing and defaults could be consolidated, keeping it below anchor 5's appropriately-split ideal for a >50-line skill.	4 / 5
	Total	17 / 20 Passed

Description

95%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.

The description is exemplary: third person, specific actions, explicit trigger phrases users would naturally say, a stated prerequisite, and clear negative triggers for conflict avoidance. Its only weakness is the slightly vague "pull health data" action compared to the other concrete verbs.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("Inspect Sentry issues, summarize production errors, and pull health data via the Sentry API"), though "pull health data" is less concrete than the others, leaving minor gaps in coverage.	4 / 5
Completeness	Explicitly answers what ("Inspect Sentry issues, summarize production errors, and pull health data") and when ("Use when user says...") with concrete trigger phrases, plus a prerequisite ("Requires SENTRY_AUTH_TOKEN") and negative triggers. Clearly matches the anchor-5 example structure.	5 / 5
Trigger Term Quality	Includes natural phrases users would actually say ("check Sentry", "what errors in production?", "recent crashes", "summarize Sentry issues", "production error report") with good synonym coverage. No common variations are obviously missing.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Sentry API, read-only) with distinct triggers and explicit exclusions ("Do NOT use for setting up Sentry SDK, configuring alerts, or non-Sentry error monitoring"), minimizing conflict risk with other observability 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: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(monitoring)/sentry/SKILL.md
Commit: 120b676

Reviewed: 5 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.