CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sentry-triage

Triage WorldMonitor Sentry issues — classify unresolved events as noise, already-fixed, product bugs, or needs-human; optionally ship a tested fix. Use when the user says triage Sentry, pastes a WORLDMONITOR-* ID or sentry.io URL, or asks to investigate production errors.

Quality

90%

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

88%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 exceptionally actionable, well-sequenced triage playbook with strong validation and recovery loops for risky writes, and virtually no padding — every rule is hard-won project-specific policy. The only structural improvement would be offloading the long policy and audit-procedure blocks into reference files to slim the main body.

DimensionReasoningScore

Conciseness

The body is dense with non-derivable project facts (tool quirks like "update_issue with status: 'ignored' on an already-ignored issue returns success and silently no-ops", policy rules, verified dates) and explains nothing Claude already knows. Minor trimmable redundancy exists — the status read-back rule and the resolving-keyword trap are each restated across the policy block and Step 4 — which keeps it off the lean 5 anchor.

4 / 5

Actionability

Guidance is fully executable: exact MCP tool calls with arguments (e.g. search_issues with query 'is:ignored', limit=100, period='90d'), a copy-paste bash scan command with the complete resolving-keyword regex, exact focused test commands (tsx --test tests/sentry-beforesend.test.mjs), specific file paths, and a precise numbered archive-transition write sequence.

5 / 5

Workflow Clarity

A clear five-step sequence (Find the work → Pull context → Classify → Act → Digest) with a done-checklist, and validation is exceptional: mandatory read-backs after every write ("Do not trust the write response"), an explicit retry-once-then-stop recovery loop for the destructive archive transition, and "Do not claim a timed-out run passed". Feedback loops for the batch/destructive operations are present, so no cap applies.

5 / 5

Progressive Disclosure

No bundle files exist, and the single-file body is well organized with clear section headers and clearly signaled one-level-deep references to repo docs (canonical write-ups, hosted-acceptance doc). However, at ~155 lines the inlined policy block (10 numbered rules plus migration context) and the ignored-board audit procedure are content that could live in a separate reference file, which keeps it off the top anchor while remaining clearly above anchor 3.

4 / 5

Total

18

/

20

Passed

Description

92%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 description: concrete capabilities with a full classification taxonomy, an explicit and varied trigger clause, third-person voice, and a tightly scoped project niche. The only weakness is slight under-coverage of natural trigger synonyms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with a complete four-class taxonomy ("classify unresolved events as noise, already-fixed, product bugs, or needs-human") plus "optionally ship a tested fix", covering the domain comprehensively with no generic filler. It is not 4 because coverage has no minor gaps rather than having them.

5 / 5

Completeness

It explicitly answers both what ("Triage WorldMonitor Sentry issues — classify unresolved events as …; optionally ship a tested fix") and when, with a concrete "Use when the user says triage Sentry, pastes a WORLDMONITOR-* ID or sentry.io URL, or asks to investigate production errors" clause — a direct match for anchor 5.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ("triage Sentry", "WORLDMONITOR-* ID", "sentry.io URL", "investigate production errors") but common variations like "Sentry errors", "Sentry alert", or "check Sentry" are missing. It exceeds anchor 3 ("some relevant keywords") but does not reach the synonym-complete coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"WorldMonitor Sentry" plus the project-specific WORLDMONITOR-* short-ID format carves out a clear niche with distinct, unambiguous triggers and minimal conflict risk with any generic skill.

5 / 5

Total

19

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository

koala73/worldmonitor

Path

.agents/skills/sentry-triage/SKILL.md

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.