src/autoskillit/skills_extended/pipeline-summary/SKILL.md
Create a GitHub issue and PR summarizing pipeline bugs and fixes. Use when a pipeline run completes with accumulated bug fixes on a feature branch.
npx skillsauth add talont-org/autoskillit pipeline-summaryInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create a GitHub issue documenting bugs encountered during a pipeline run and a PR from the feature branch into the target branch.
/autoskillit:pipeline-summary {bug_report_path} {feature_branch} {target_branch} {workspace} [{closing_issue}]
## Requirements section should be extracted and embedded in the PR body. When absent or empty, requirements extraction is skipped.collect_on_branch enabledNEVER:
gh is not available or not authenticated — write a local summary insteadALWAYS:
gh auth status before attempting GitHub operationssummary_path=<path> for capture by the orchestratorissue_url=<url> and pr_url=<url>Parse up to five positional arguments from the prompt. The fifth (closing_issue) is optional.
Read the JSON file at {bug_report_path}. Expected structure:
[
{
"step": "string — pipeline step where failure occurred",
"error": "string — error description",
"fix": "string — what was done to fix it",
"iteration": "number — which bugfix iteration"
}
]
If the file is empty, contains [], or doesn't exist, write a clean-run summary and exit successfully.
Write a markdown summary to {workspace}/run-summary.md:
Output: summary_path={workspace}/run-summary.md
Run gh auth status 2>/dev/null. If exit code is non-zero or gh is not found:
cd {workspace}
REMOTE=$(git remote get-url upstream >/dev/null 2>&1 && echo upstream || echo origin)
git push -u "$REMOTE" {feature_branch}
If push fails (no remote, network issue), log the error and exit successfully.
closing_issue was provided as the sixth argument:
gh issue view {closing_issue} --json body -q .body
Extract the ## Requirements section: requirements_section = everything from ## Requirements to the next ## heading or end of body, whichever comes first.closing_issue is not provided: skip gracefully — requirements_section = "".Write the issue body to a temp file, then:
TEMP_ISSUE_BODY="{{AUTOSKILLIT_TEMP}}/pipeline-summary/issue_body_$(date +%Y%m%d-%H%M%S).md"
mkdir -p "$(dirname "${TEMP_ISSUE_BODY}")"
# [write the issue body content to ${TEMP_ISSUE_BODY} here]
gh issue create \
--title "Pipeline Run Summary — {date}: {bug_count} bug(s) fixed" \
--body-file "${TEMP_ISSUE_BODY}" \
--label "pipeline-summary"
Capture the issue URL from stdout. If the label doesn't exist, retry without --label.
Output: issue_url={url}
Write the PR body to a temp file (reference the issue), then:
TEMP_PR_BODY="{{AUTOSKILLIT_TEMP}}/pipeline-summary/pr_body_$(date +%Y%m%d-%H%M%S).md"
mkdir -p "$(dirname "${TEMP_PR_BODY}")"
# [write the PR body content to ${TEMP_PR_BODY} here]
gh pr create \
--title "Pipeline fixes — {date}" \
--body-file "${TEMP_PR_BODY}" \
--base {target_branch} \
--head {feature_branch}
The PR body (temp_pr_body) contains:
## Summary — bug count and branch info## Requirements (if requirements_section is non-empty from Step 5b)Closes #{closing_issue} (if closing_issue was provided)Capture the PR URL from stdout.
Output: pr_url={url}
summary_path={workspace}/run-summary.mdissue_url={url} and pr_url={url}development
Generate YAML recipes for .autoskillit/recipes/. Use when user says "make script skill", "generate script", "script a workflow", "write a script", "create a script", "new recipe", "write a pipeline", or when loaded by other skills for script formatting.
data-ai
Create Uncertainty Representation visualization planning spec showing error bar definitions, distribution-aware alternatives, and multi-seed variance protocols. Statistical lens answering "How is uncertainty honestly represented?"
data-ai
Create Temporal Dynamics visualization planning spec showing axis scaling (linear vs log), smoothing disclosure, epoch/step alignment, run aggregation (mean + variance bands), early-stopping markers, and wall-clock vs step-count x-axis. Temporal lens answering "Are training dynamics shown clearly and honestly?"
data-ai
Create Narrative Story Arc visualization planning spec showing visual consistency across the report (same color = same model everywhere), logical figure progression, redundant figure detection, and narrative dependency between figures. Narrative lens answering "Do the figures tell a coherent story across the report?"