triage
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
90
87%
Does it follow best practices?
Impact
94%
1.42xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates both what the skill does and when to use it, with good trigger term coverage and a distinctive niche. The main weakness is that the specific capabilities could be more concrete—listing actions like prioritizing, labeling, assigning, or categorizing would strengthen the specificity dimension. Overall, it performs well as a skill selector in a multi-skill environment.
Suggestions
Add more concrete action verbs to improve specificity, e.g., 'prioritize, label, assign, and categorize issues' instead of the more generic 'triage issues' and 'manage issue workflow'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (issue triage) and mentions a state machine and triage roles, but the concrete actions are somewhat generic ('create an issue', 'triage issues', 'manage issue workflow') rather than listing specific operations like labeling, prioritizing, assigning, or categorizing. | 2 / 3 |
Completeness | Clearly answers both 'what' (triage issues through a state machine driven by triage roles) and 'when' (explicit 'Use when' clause listing multiple trigger scenarios including creating issues, triaging, reviewing bugs/feature requests, preparing for AFK agent, managing workflow). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'create an issue', 'triage issues', 'bugs', 'feature requests', 'AFK agent', 'issue workflow'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'state machine', 'triage roles', and 'AFK agent' creates a very distinct niche. This is unlikely to conflict with generic issue tracking or project management skills due to its specific methodology references. | 3 / 3 |
Total | 11 / 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 well-crafted skill that clearly defines a state machine workflow for issue triage with concrete actions, explicit validation checkpoints, and good progressive disclosure. The workflow is thorough yet navigable, with appropriate delegation to referenced documents for specialized concerns. Minor verbosity in role definitions and state transitions prevents a perfect conciseness score, but overall token efficiency is good for the complexity involved.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining concepts Claude already knows, but some sections could be tightened—e.g., the role definitions are somewhat verbose, and the state transition explanation could be more compact. The overall length is reasonable for the complexity of the workflow. | 2 / 3 |
Actionability | The skill provides concrete, specific guidance at every step: exact label names, a clear triage sequence (gather → recommend → reproduce → grill → apply), specific templates for needs-info comments, explicit actions per outcome state, and a quick override path. The invocation examples and bucket query structure are directly actionable. | 3 / 3 |
Workflow Clarity | The multi-step triage process is clearly sequenced with numbered steps, explicit validation checkpoints (wait for maintainer direction after recommendation, confirm before applying quick overrides, flag conflicting roles), and feedback loops (needs-info returns to needs-triage, resuming previous sessions checks for answered questions). Error recovery is addressed through the 'flag and ask' pattern. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to AGENT-BRIEF.md and OUT-OF-SCOPE.md for detailed guidance. The main content is appropriately scoped as an overview/workflow, delegating specialized knowledge to referenced files. The needs-info template is appropriately inline since it's short and directly used. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- coder/agent-tty
- Commit
a05d4e5
- 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.