triage

Run triage duty for CET/Cloud, Server, or Drivers/DBX. Retrieves Needs Triage tickets from Jira, builds a triage plan, and applies changes after human confirmation.

2.07x

Quality

—

Does it follow best practices?

Impact

79%

2.07x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

A well-structured, highly actionable triage workflow with clear sequencing, validation gates, and clean progressive disclosure across verified reference files. Its only real weakness is conciseness: a few rule passages could be tightened.

Suggestions

Break up the long single-paragraph Empty/Unactionable Ticket Rule into a short rule plus a bulleted list of qualifying signals to reduce scanning cost.

Consolidate the repeated 'one level only — do not follow transitive links' guidance into one shared definition referenced from each step rather than restating it three times.

Trim wordy rationale phrasing in the label-selection and routing sections where the rule itself already conveys the reasoning.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely needed domain rules (labels, component maps, JQL) and avoids explaining concepts Claude already knows, but a few passages — notably the long single-paragraph Empty/Unactionable Ticket Rule and some repeated 'one level only' clarifications — could be tightened, so it sits at 'mostly efficient but could be tighter' rather than fully lean.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: explicit JQL queries, a component-to-team map, enumerated label definitions, exact Jira field-write instructions, and a ready-to-paste Slack template, satisfying the 'fully executable / specific examples' anchor.	3 / 3
Workflow Clarity	The process is clearly sequenced (Steps 0–7 plus Part 5 B1–B4) with explicit validation checkpoints (tool availability check, human confirmation gates with 'STOP HERE'), feedback loops (revise and re-present on adjustment), and read-before-write verification for the batch Jira writes.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview holding the shared base layer, while team-specific rules/JQL/knowledge are split into one-level-deep reference files, all of which exist and are well-signaled via a routing table and inline callouts with loading context.	3 / 3
	Total	11 / 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 specific, third-person description with strong trigger terms and a clear niche, but it omits an explicit "Use when..." trigger clause, which caps completeness at 2.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when running docs triage duty for CET/Cloud, Server, or Drivers/DBX and Jira tickets are in Needs Triage status.'

Consider mirroring the user-facing trigger phrasing (e.g. 'triaging DOCSP tickets') to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Retrieves Needs Triage tickets from Jira, builds a triage plan, and applies changes after human confirmation" — matching the score-3 anchor of multiple specific concrete actions rather than just naming a domain.	3 / 3
Completeness	It clearly answers "what" (retrieve, build, apply) but lacks an explicit "Use when..." trigger clause, so per the guideline a missing explicit trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Natural trigger terms a target user would say are well covered ("triage duty", "Jira", "Needs Triage tickets", "CET/Cloud, Server, or Drivers/DBX"), and the voice is consistently third person, so it clears the score-3 bar.	3 / 3
Distinctiveness Conflict Risk	The niche is highly specific — MongoDB Docs triage for named teams over Jira "Needs Triage" tickets — making it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mongodb/docs
Commit: e765459

Reviewed: about 23 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.