Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query GitHub discussions with jq filtering and reusable selectors.
.claude/skills/github-github-discussion-query/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 11 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -56% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 43% | 0% |
Query GitHub discussions efficiently with built-in jq filtering.
The --jq parameter is optional. Without --jq, this skill returns schema and data size information instead of full data. Use this to avoid oversized responses and inspect structure before targeted queries.
Use --jq '.' to get all data, or use a more specific filter for targeted results.
Use this skill to query discussions from the current repository or any specified repository.
To list discussions from the current repository:
bash./query-discussions.sh # Returns schema and data size, not full data
To get all discussion data:
bash./query-discussions.sh --jq '.'
To query a specific repository:
bash./query-discussions.sh --repo owner/repo
Use the --jq argument to filter and transform the output:
bash# Get discussion numbers and titles ./query-discussions.sh --jq '.[] | {number, title}' # Get discussions by a specific author ./query-discussions.sh --jq '.[] | select(.author.login == "username")' # Get discussions in a specific category ./query-discussions.sh --jq '.[] | select(.category.name == "Ideas")' # Get answered discussions ./query-discussions.sh --jq '.[] | select(.answer != null)' # Count discussions by category ./query-discussions.sh --jq 'group_by(.category.name) | map({category: .[0].category.name, count: length})'
--limit: Maximum number of discussions to fetch. Default: 30--repo: Repository in owner/repo format. Default: current repo--jq: (Optional) jq expression for filtering/transforming output. If omitted, returns schema infoFind discussions with many comments:
bash./query-discussions.sh --jq '.[] | select(.comments.totalCount > 5) | {number, title, comments: .comments.totalCount}'
Get unanswered discussions:
bash./query-discussions.sh --jq '.[] | select(.answer == null) | {number, title, category: .category.name}'
List discussions with their labels:
bash./query-discussions.sh --jq '.[] | {number, title, labels: [.labels[].name]}'
Find discussions by category:
bash./query-discussions.sh --jq '.[] | select(.category.name == "Q&A") | {number, title, author: .author.login}'
Get recently updated discussions:
bash./query-discussions.sh --jq 'sort_by(.updatedAt) | reverse | .[0:10] | .[] | {number, title, updatedAt}'
The script outputs JSON by default, making it easy to pipe through jq for additional processing.
gh) authenticatedjq for filtering (installed by default on most systems)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,467 | 4,889 | -61% | 1 | 1 | 0% | 1,960 | 989 | -50% | 0 | 0 | — |
case-02 | fail→fail | 13,593 | 7,813 | -43% | 1 | 1 | 0% | 2,398 | 957 | -60% | 0 | 0 | — |
case-03 | fail→pass | 7,584 | 8,820 | +16% | 1 | 1 | 0% | 1,114 | 1,318 | +18% | 0 | 0 | — |
case-04 | fail→pass | 12,584 | 2,544 | -80% | 1 | 1 | 0% | 2,380 | 1,047 | -56% | 0 | 0 | — |
case-05 | fail→pass | 7,398 | 2,810 | -62% | 1 | 1 | 0% | 1,219 | 1,071 | -12% | 0 | 0 | — |
case-06 | fail→pass | 10,200 | 4,478 | -56% | 1 | 1 | 0% | 1,076 | 1,540 | +43% | 0 | 0 | — |
case-07 | fail→fail | 11,834 | 11,373 | -4% | 1 | 1 | 0% | 2,101 | 1,138 | -46% | 0 | 0 | — |
case-08 | fail→pass | 13,249 | 5,422 | -59% | 1 | 1 | 0% | 2,125 | 945 | -56% | 0 | 0 | — |
case-09 | fail→pass | 3,977 | 7,660 | +93% | 1 | 1 | 0% | 559 | 962 | +72% | 0 | 0 | — |
case-10 | fail→pass | 5,714 | 2,486 | -56% | 1 | 1 | 0% | 820 | 978 | +19% | 0 | 0 | — |
case-11 | fail→pass | 5,281 | 2,213 | -58% | 1 | 1 | 0% | 958 | 992 | +4% | 0 | 0 | — |
case-12 | fail→fail | 4,859 | 7,432 | +53% | 1 | 1 | 0% | 812 | 1,035 | +27% | 0 | 0 | — |
case-13 | fail→pass | 7,802 | 2,570 | -67% | 1 | 1 | 0% | 1,460 | 1,070 | -27% | 0 | 0 | — |
case-14 | fail→fail | 9,926 | 6,723 | -32% | 1 | 1 | 0% | 1,781 | 1,009 | -43% | 0 | 0 | — |
case-15 | fail→fail | 9,868 | 3,240 | -67% | 1 | 1 | 0% | 1,918 | 945 | -51% | 0 | 0 | — |
case-16 | pass→pass | 31,477 | 4,455 | -86% | 1 | 1 | 0% | 3,092 | 894 | -71% | 0 | 0 | — |
case-17 | fail→pass | 7,988 | 2,240 | -72% | 1 | 1 | 0% | 1,599 | 963 | -40% | 0 | 0 | — |
case-18 | fail→fail | 17,897 | 9,075 | -49% | 1 | 1 | 0% | 2,485 | 1,118 | -55% | 0 | 0 | — |
case-19 | fail→fail | 8,231 | 7,029 | -15% | 1 | 1 | 0% | 1,332 | 1,054 | -21% | 0 | 0 | — |
case-20 | pass→pass | 3,737 | 4,177 | +12% | 1 | 1 | 0% | 588 | 1,323 | +125% | 0 | 0 | — |
case-21 | pass→fail | 4,657 | 9,285 | +99% | 1 | 1 | 0% | 739 | 972 | +32% | 0 | 0 | — |
case-22 | pass→pass | 8,078 | 8,921 | +10% | 1 | 1 | 0% | 1,369 | 2,225 | +63% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 16 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +45 percentage points is the difference between those two pass rates over the 16 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.