github-bug-report-triage
Skill825 starsChanged 7 months agoMITView on GitHub
Triage GitHub bug reports for actionability. Use when evaluating whether a bug issue has sufficient detail and identifying missing information from the reporter.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analysis-artifactsSkill
- ci-fixSkill
- create-pull-requestSkill
- dbt-model-indexSkill
- docs-updateSkill
- github-issue-dedupeSkill
- mcp-builderSkill
- schedulerSkill
- seo-aeo-auditSkill
- slack-qa-investigateSkill
- terraform-style-checkSkill
- web-accessibility-auditSkill
- webapp-testingSkill
- web-performance-auditSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
If the issue is a feature request or a question, do not evaluate this issue
- Distinctive: line 43
Don't require every template field to be filled
- Distinctive: line 45
Consider context (obvious bugs vs.
- Distinctive: line 129
Note: No explicit repro steps, but error is clear enough to investigate
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub Bug Report Triage
Evaluate GitHub issues for bug reports only. Determine if they contain sufficient info to be actionable. If not, identify missing details and provide constructive feedback.
Workflow
1. Locate Issue Template
Check for existing templates:
.github/ISSUE_TEMPLATE/bug_report.md.github/ISSUE_TEMPLATE/bug_report.yml.github/ISSUE_TEMPLATE/*.md.github/ISSUE_TEMPLATE.mdISSUE_TEMPLATE.md
If no template exists, use references/ISSUE_TEMPLATE.md from this skill as the fallback template, then evaluate the issue against it.
2. Evaluate Issue Quality
Critical questions:
- Is this a bug report?
- If the issue is a feature request or a question, do not evaluate this issue
- Is the description clear?
- What's broken or wrong
- Expected behavior vs. what actually happens
- Impact or severity
- Can we reproduce it?
- Step-by-step reproduction
- OR sandbox/StackBlitz/CodeSandbox link
- OR minimal code example
Be reasonable:
- Don't require every template field to be filled
- Focus on minimum info needed to investigate
- Consider context (obvious bugs vs. edge cases)
3. Make Determination
Ready to be actionable:
- Has clear problem description
- Includes reproduction path OR enough context to debug
- Actually a bug (not feature/question)
Needs more info:
- Vague description ("it doesn't work")
- Missing reproduction steps AND no code example
- Unclear what the expected behavior should be
- Missing critical context (e.g., "crashes" but no error message)
4. Provide Feedback
If ready: Confirm issue is actionable.
If needs info: Specify what's missing. Be constructive and specific.
Examples
Example 1: Ready to Investigate
**Issue**: Dropdown menu doesn't close on mobile Safari
**Description**:
When clicking a dropdown menu item on iOS Safari, the menu stays
open instead of closing. Works fine on desktop Chrome/Firefox.
**Steps**:
1. Visit https://stackblitz.com/edit/my-repro
2. Open on iOS Safari
3. Click dropdown, select any item
4. Menu stays open (should close)
**Environment**: iOS 16.3, SafariEvaluation: ✅ Ready
- Clear description
- Has reproduction link
- Specific environment details
Example 2: Needs More Info
**Issue**: Button is broken
**Description**:
The submit button doesn't work properly.Evaluation: ❌ Needs info Missing:
- What does "doesn't work" mean? (no click? error? wrong behavior?)
- Expected vs. actual behavior
- Steps to reproduce
- Any error messages
Example 3: Edge Case - Reasonable
**Issue**: Console error on form submit
**Description**:
Getting "Cannot read property 'value' of null" when submitting
the contact form. Happens 100% of the time.
**Error**:TypeError: Cannot read property 'value' of null at handleSubmit (ContactForm.tsx:45)
**Environment**: Chrome 120, Windows 11Evaluation: ✅ Ready
- Clear error message with stack trace
- Specific file/line reference
- Reproducible (100% of time)
- Note: No explicit repro steps, but error is clear enough to investigate
Example 4: Bug Report with Insufficient Reproducibility
**Issue**: [glob-loader] Duplicate id warning on file update
**Description**:
I'm encountering an issue with the glob loader. Whenever I update
the watched file, I get a warning message in the logs.
The warning message:13:23:31 [WARN] [glob-loader] Duplicate id "russian-test" found in /Users/user/Code/project/content/posts/russian-test.md. Later items with the same id will overwrite earlier ones.
**Expected**: No warning message
**Link to Minimal Reproducible Example**: - N/AEvaluation: ❌ Needs info
- Describes a real bug (warning message)
- Has error output and code reference
- BUT: No minimal reproduction provided
- Code link points to private repo (can't access to debug)
Missing:
- Minimal reproduction (example code or link to a working reproduction)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

