sentry

Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/sentry/SKILL.md

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 highly actionable, well-organized skill body with concrete copy-paste commands and correctly referenced bundle scripts. The main gaps are mild redundancy in the Tips/Quick Reference sections and the lack of explicit validation checkpoints in the debugging workflows.

Suggestions

Tighten redundancy by either trimming the 'Tips for Debugging' section (which restates workflow behavior) or merging its guidance into the workflows it describes.

Add explicit feedback loops to the workflows, e.g. 'If search-events returns nothing, widen the time window or drop the --level filter before drilling into a specific event.'

Optionally fold the Quick Reference table into the workflow section to avoid duplicating the same command invocations shown immediately below.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the 'Tips for Debugging' section and the top Quick Reference table restate commands and guidance already shown in the workflows, so it could be tightened to reach the lean score-3 anchor.	2 / 3
Actionability	It provides fully executable commands with real flags and concrete example values (org slugs, issue IDs, ISO timestamps, Sentry URLs), making the guidance copy-paste ready per the score-3 anchor.	3 / 3
Workflow Clarity	The goal-based workflows and Tips section convey a loose investigative sequence ('start broad, then narrow down'), but there are no explicit validation checkpoints or 'if no results, then...' feedback loops, matching the score-2 anchor of sequence present but checkpoints missing.	2 / 3
Progressive Disclosure	A clear Quick Reference overview leads into well-signaled, one-level-deep references to the actual script files (all five referenced scripts exist in ./scripts/), with content organized into scannable sections and no nested/deep references, fitting the score-3 anchor.	3 / 3
	Total	10 / 12 Passed

Description

82%

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 good natural trigger terms and a clear Sentry niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the 'when to use' guidance implied rather than stated.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks about Sentry errors, wants to investigate issues/events, or needs to find the root cause of a production error.'

Reframe 'Helps agents debug errors...' as a direct 'Use when...' statement so the activation condition is unambiguous to the model.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('Fetch and analyze Sentry issues, events, transactions, and logs') applied to specific object types, matching the score-3 anchor of several specific concrete actions rather than the vague or partial examples.	3 / 3
Completeness	It clearly states what the skill does, but the 'when' is only implied through capability phrasing ('Helps agents debug errors...'); there is no explicit 'Use when...' clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It uses natural terms a user would actually say ('Sentry', 'debug errors', 'find root causes', 'issues', 'events', 'logs'), giving good coverage of common phrasings rather than jargon-only or sparse keywords.	3 / 3
Distinctiveness Conflict Risk	Scoping everything to 'Sentry' gives it a clear, branded niche with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor rather than the overlapping score-2 example.	3 / 3
	Total	11 / 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: mitsuhiko/agent-stuff
Path: skills/sentry/SKILL.md
Commit: d265b8e

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.