github-bug-report-triage
Triage GitHub bug reports for actionability. Use when evaluating whether a bug issue has sufficient detail and identifying missing information from the reporter.
81
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/github-bug-report-triage/SKILL.mdQuality
Discovery
75%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 well-structured with a clear 'Use when' clause that explicitly defines both what the skill does and when to use it. Its main weakness is moderate specificity—it could enumerate more concrete actions involved in triage—and trigger terms could be expanded to cover more natural user phrasings. Overall it's a solid, functional description that would work well in a multi-skill environment.
Suggestions
Add more specific concrete actions, e.g., 'checks for reproduction steps, environment details, expected vs actual behavior, and error logs'
Expand trigger terms to include variations like 'incomplete issue', 'needs more info', 'reproduction steps', 'bug template', or 'issue quality'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub bug reports) and some actions (triage, evaluating detail, identifying missing information), but doesn't list multiple concrete specific actions like categorizing severity, checking reproducibility steps, validating environment info, etc. | 2 / 3 |
Completeness | Clearly answers both what ('Triage GitHub bug reports for actionability') and when ('Use when evaluating whether a bug issue has sufficient detail and identifying missing information from the reporter'), with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'GitHub', 'bug reports', 'triage', and 'missing information', but misses common variations users might say such as 'issue quality', 'bug template', 'reproduction steps', 'incomplete issue', or 'needs more info'. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused specifically on triaging GitHub bug reports for actionability, which is distinct enough to avoid conflicts with general GitHub skills, code review skills, or generic issue management skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%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-structured triage skill with a clear workflow, specific evaluation criteria, and good examples covering multiple scenarios. Its main weakness is verbosity in the examples section—four detailed examples with markdown-rendered issue content makes the file longer than necessary. The actionability and workflow clarity are strong, providing Claude with concrete decision-making criteria.
Suggestions
Consider moving examples 3 and 4 to a separate EXAMPLES.md file, keeping only examples 1 and 2 inline to demonstrate the ready/needs-info distinction.
Tighten the evaluation commentary in examples—phrases like 'Clear description' and 'Has reproduction link' repeat what the workflow section already defines as criteria.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but the four examples are somewhat verbose. The examples could be condensed—three would suffice, and the evaluation commentary repeats criteria already stated in the workflow. However, it avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete, specific guidance: exact file paths to check for templates, clear evaluation criteria with specific questions, and four detailed examples showing both positive and negative cases with explicit reasoning. The workflow is directly executable. | 3 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced (locate template → evaluate → determine → provide feedback), with explicit decision points (is it a bug? ready vs needs info?) and clear criteria for each determination. The 'be reasonable' section adds important judgment calibration. No destructive operations are involved, so validation checkpoints aren't needed. | 3 / 3 |
Progressive Disclosure | The skill references a fallback template at 'references/ISSUE_TEMPLATE.md' which is good progressive disclosure, but all four examples are inline making the file longer than necessary. The examples could be split into a separate reference file with just one or two kept inline for quick reference. | 2 / 3 |
Total | 10 / 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
- warpdotdev/oz-skills
- Commit
6c08c49
- 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.