sentry

Sentry error tracking and debugging specialist

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crates/openfang-skills/bundled/sentry/SKILL.md

Quality

Content

82%

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

The body is a well-organized, concise specialist reference with clear triage workflow and good validation cues. Its main gap is actionability: it describes config keys and query strings but includes no executable code or copy-paste examples to ground the guidance.

Suggestions

Add a minimal executable SDK init snippet (e.g. a short Python/JS Sentry.init block showing environment, release, traces_sample_rate, and a beforeSend scrubber) to move actionability from descriptive to copy-paste ready.

Show one concrete alert-condition example or a representative `beforeSend` PII-scrubbing code block so the Alert Configuration and SDK sections become executable rather than prescriptive.

Consider linking out detailed SDK/platform-specific setup to a reference file if platform coverage expands, keeping the overview lean while improving navigation.

Dimension	Reasoning	Score
Conciseness	The body is a lean, bullet-driven reference that assumes Claude's competence and avoids explaining what Sentry or error tracking is; every section adds operational guidance Claude wouldn't already encode, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	It gives concrete guidance (specific filter strings like `is:unresolved firstSeen:-24h`, config keys like `traces_sample_rate`, `beforeSend`, web vitals LCP/FID/CLS), but provides no executable code snippets or copy-paste SDK init examples, leaving the guidance instructive rather than fully executable.	2 / 3
Workflow Clarity	The Triage Workflow is a clearly numbered six-step sequence, and the SDK/principle sections pair each action with explicit validation/verification cues (scrub PII before transmission, set release on every event, avoid auto-resolve, validate stack traces vs expected behavior); the workflow is unambiguous and the operations are low-destructive so no missing feedback loop caps the score.	3 / 3
Progressive Disclosure	The skill is a self-contained overview under ~50 lines with no external bundle files and no nested references; per the rubric's simple-skills note, well-organized sections (Key Principles, SDK Setup, Triage, Alerts, Performance, Pitfalls) earn a 3 without requiring external file references.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 and clearly niched to Sentry, but it reads as a role label rather than a capability-and-trigger statement. It lacks concrete enumerated actions and an explicit 'Use when...' clause, which caps both specificity and completeness.

Suggestions

Enumerate concrete actions, e.g. "Set up Sentry SDKs, triage production errors, configure alerts, and analyze performance traces" to lift specificity to 3.

Add an explicit trigger clause such as "Use when the user mentions Sentry, production errors, crashes, stack traces, or error monitoring/CI debugging" to raise completeness from 2 to 3.

Include natural user phrasings (errors, crashes, production bugs, stack traces) alongside "Sentry" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ("Sentry error tracking and debugging") and a role ("specialist") but lists no concrete actions like setup, triage, alert configuration, or performance monitoring; it describes rather than enumerates capabilities, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	The "what" is conveyed (Sentry error tracking and debugging specialist), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	"Sentry" and "error tracking" are natural user terms, but common variations users actually say ("errors", "production bugs", "crashes", "stack traces") are absent, so coverage is partial rather than broad.	2 / 3
Distinctiveness Conflict Risk	The Sentry/tool-specific framing carves out a clear niche with a distinct trigger unlikely to overlap with unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 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: RightNow-AI/openfang
Path: crates/openfang-skills/bundled/sentry/SKILL.md
Commit: acf2587

Reviewed: about 6 hours 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.