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.
83
76%
Does it follow best practices?
Impact
95%
2.31xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/triage/SKILL.mdQuality
Discovery
67%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 strong in specificity and distinctiveness, clearly naming concrete actions and a narrow domain (Jira triage for specific teams). Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Trigger terms are adequate but could include more natural user phrasings.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to run triage, process Needs Triage tickets, or manage the triage queue for CET/Cloud, Server, or Drivers/DBX.'
Include additional natural trigger terms users might say, such as 'assign tickets', 'triage queue', 'prioritize backlog', or 'Needs Triage status'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Retrieves Needs Triage tickets from Jira', 'builds a triage plan', and 'applies changes after human confirmation'. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers 'what' (retrieves tickets, builds plan, applies changes) but lacks an explicit 'Use when...' clause. The 'when' is only implied by the nature of the task. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'triage', 'Jira', 'tickets', and team names (CET/Cloud, Server, Drivers/DBX), but these are somewhat domain-specific. Users would likely say 'triage' or 'Jira tickets', which are present, but common variations like 'assign tickets', 'prioritize', 'backlog grooming' are missing. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific team names (CET/Cloud, Server, Drivers/DBX), the specific workflow (triage duty), and the specific tool (Jira). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-architected skill for a complex multi-team triage workflow. Its greatest strengths are the clear step-by-step workflow with explicit human confirmation gates, concrete JQL queries and routing tables, and good progressive disclosure via team-specific module files. The main weakness is verbosity in some rule descriptions (particularly the global exceptions section), which could be tightened with more structured formatting without losing precision.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is detailed and mostly necessary given the complexity of the triage domain, but several sections are verbose — e.g., the 'Empty / Unactionable Ticket Rule' paragraph is dense and could be tightened with bullet points. Some explanations (like what constitutes a 'pure engineering task') border on over-specification but are arguably needed for correctness. The IA label two-step check with examples is well done but adds length. | 2 / 3 |
Actionability | The skill provides concrete JQL queries, specific component-to-team mapping tables, exact label names, explicit routing rules with examples, comment template references, and step-by-step instructions with clear tool usage (jira skill, glean_mcp). The guidance is highly specific and directly executable. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0–7) with explicit validation checkpoints — Step 0 verifies prerequisites, Step 3 and Step 7 both have mandatory STOP points requiring human confirmation before any Jira writes. There are feedback loops (revise plan and present again), error recovery (flag for manual review), and clear instructions to read current values before writing to avoid destructive overwrites. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with a clear overview (Parts 1–4), team-specific modules split into separate reference files (references/cet-cloud.md, references/server.md, references/drivers-dbx.md), comment templates in assets/comment-templates.md, and a routing table for which file to load. References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- mongodb/docs
- Commit
5985af5
- 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.