CtrlK
BlogDocsLog inGet started
Tessl Logo

sentry

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

64

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 exemplary tool-skill body: concrete, verified, copy-paste-ready commands organized by real debugging questions with a lean quick-reference and per-command docs. The only material issue is in the bundle rather than the prose — every script imports a missing ../lib/auth.js, so the documented commands would fail at runtime until that shared library is added.

DimensionReasoningScore

Conciseness

The body assumes competence — no explanation of what Sentry is or how APIs work — and relies on a Quick Reference table and compact option lists, but there is minor duplication: search-events flags appear in the Quick Reference, the workflow examples, and the reference section, and "Tips for Debugging" partially restates workflow content. Fits 'Efficient; minor instances that could be trimmed' rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Every example is copy-paste ready (e.g. "./scripts/search-events.js --org myorg --start 2025-12-23T15:00:00 --end 2025-12-23T17:00:00", "./scripts/fetch-issue.js https://sentry.io/organizations/myorg/issues/123/ --latest", "--query \"times_seen:>50\"") and the documented flags match the scripts' actual help output, covering the common cases across all five scripts — a full match for the fully-executable anchor.

5 / 5

Workflow Clarity

"Common Debugging Workflows" sequences investigation by question (time-window search → level/transaction filter → drill into event), and the tips supply a strategy ("Start broad, then narrow down", "Check related events... same transaction name or trace ID") that acts as a drill-down feedback loop. Being read-only investigation, the destructive/batch validation cap does not apply, but there are no explicit verification checkpoints, so it fits 'clear sequence with most checkpoints present; minor validation gaps' rather than the validate-and-recover anchor.

4 / 5

Progressive Disclosure

All five script paths referenced in the body exist in the bundle, and the structure (Quick Reference → workflows → per-command reference → tips) is well-signaled with appropriate density for a single-file tool skill. Verified against the actual bundle: one defect — every script imports "../lib/auth.js", which is absent, so the referenced scripts cannot run as bundled; this is a script-internal dependency break rather than a body-reference defect, keeping it at the 'good structure; minor organization gaps' anchor rather than dropping to anchor 3's 'could be better organized'.

4 / 5

Total

17

/

20

Passed

Description

70%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 specific, distinctive description with good natural trigger phrases, weakened only by the absence of an explicit "Use when..." trigger clause, which leaves the 'when to use' guidance implied rather than stated. Adding a concrete trigger sentence would lift it into the top tier.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user mentions Sentry, crashes, error monitoring, or asks what went wrong at a given time."

Include common synonyms such as "error monitoring", "crash reports", "stack traces", or "exceptions" alongside "debug errors" to broaden natural trigger coverage.

Enumerate one or two more granular capabilities (e.g. "search logs by trace ID", "pull stack traces") to close the coverage gap between 'several specific actions' and comprehensive.

DimensionReasoningScore

Specificity

"Fetch and analyze Sentry issues, events, transactions, and logs" plus "debug errors, find root causes" lists several concrete actions applied to four concrete object types in a named domain, matching the 'several specific actions; minor gaps in coverage' anchor — not 5, since a comprehensive description would enumerate more granular operations (stack traces, issue lists, log search by trace ID).

4 / 5

Completeness

The 'what' is clear ("Fetch and analyze Sentry issues, events, transactions, and logs"), but there is no explicit "Use when..." clause or equivalent trigger guidance — the 'when' is only weakly implied through the purpose statement "Helps agents debug errors...", which per the judging guidelines caps completeness at 3. It carries more when-signal than the anchor-3 example but falls short of anchor 4's explicit 'Use when working with...' phrasing.

3 / 5

Trigger Term Quality

Natural phrases like "debug errors", "find root causes", "what happened at specific times" and the "Sentry" product name give good keyword coverage, but common variations such as "error monitoring", "crash", "stack trace", and "exception" are missing, so it fits the 'good coverage; a few natural terms missing' anchor rather than the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

"Sentry" is named twice alongside Sentry-specific objects ("issues, events, transactions"), giving a clear niche with distinct triggers and minimal conflict risk with any other skill — a full match for the anchor-5 example's structure. Anchor 4 would require residual overlap with closely related skills, which the explicit product branding avoids.

5 / 5

Total

16

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.