[prompt-analysis] Copilot PR Prompt Analysis - Feb 5, 2026 #13897
Closed
Replies: 1 comment
-
|
This discussion was automatically closed because it expired on 2026-02-12T12:28:02.391Z.
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Analysis Period: Last 30 days
Total PRs: 1,000 | Merged: 685 (68.5%) | Closed: 313 (31.3%) | Open: 2 (0.2%)
Prompt Categories and Success Rates
Prompt Analysis
✅ Successful Prompt Patterns
Common characteristics in merged PRs:
Most common keywords in merged PRs:
test,should,files,file,code,update,error,testsExample successful prompts:
❌ Unsuccessful Prompt Patterns
Common characteristics in closed PRs:
Keywords more common in closed PRs:
----(template formatting),security,generated,engineExample unsuccessful prompts:
Key Insights
"Remove" operations have highest success rate (77%) - Prompts focused on deletion/cleanup are most likely to be merged, possibly because they are more straightforward with clear scope.
File mentions correlate with success - Merged PRs are 5% more likely to mention specific files (65% vs 60%), suggesting specificity improves outcomes.
Closed PRs have more issue references (54% vs 41%) - This counterintuitively suggests that being assigned to an issue doesn't guarantee success. Possible explanations:
Prompt length has minimal impact - Merged (394 words) vs closed (404 words) shows negligible difference. Quality over quantity matters.
WIP PRs frequently closed - Several closed PRs have
[WIP]markers, indicating work-in-progress submissions that weren't completed.Recommendations
Based on this analysis:
DO: Be specific about files and paths - PRs that mention specific files/directories have 5% higher success rates. Example: "Update
pkg/cli/compile.go" vs "Update compile logic"DO: Focus on test-related changes - Keywords like
test,tests,testingare strongly correlated with merged PRs. Test additions/improvements are valued.DO: Use remove/cleanup language when applicable - "Remove", "delete", "drop" operations have 77% success rate, highest of all categories.
AVOID: WIP/experimental submissions - Draft or work-in-progress PRs without clear completion criteria are more likely to be closed.
AVOID: Generic template language - The
----separator pattern appears frequently in closed PRs, suggesting over-reliance on templates without customization.Historical Trends
This is the first analysis run. Future reports will show week-over-week trends.
Baseline established: 68.5% overall merge rate with "remove" operations performing best at 77%.
References:
Analysis covers Copilot PRs from last 30 days. Statistics based on keyword pattern matching and prompt characteristic analysis.
Beta Was this translation helpful? Give feedback.
All reactions