generic-automation-and-it/smooth-ai-stockanalysis / .agents/skills/ai-review
ai-review
VerifiedAnalyze and execute AI PR review feedback with fix/skip decisions. Use when a user asks to parse an AI review, apply selected fixes, and finalize review processing for GitHub or Azure DevOps pull requests. Detects the review source — for a GitHub Copilot agent review it replies to and resolves each linked review thread; otherwise it appends AI review notes to the PR description.
| File | Kind | Size |
|---|---|---|
| AGENTS.md | markdown | 4.1 KB |
| SKILL.md | skill md | 9.2 KB |
| agents/openai.yaml | config | 201 B |
| scripts/copilot-review.shexecutable | script | 5.2 KB |
scripts/copilot-review.sh
View on GitHub#!/usr/bin/env bash
# ai-review — deterministic GitHub plumbing for processing a Copilot PR review.
#
# The agent keeps all *judgment* (parsing the review, fix/skip decisions, and the
# text of every reply/summary). This script only performs the fixed GitHub calls so
# the raw REST/GraphQL never has to live in skill prose. Reply/summary bodies are
# read from STDIN to avoid quoting/newline breakage.
#
# Subcommands:
# detect <pr> Print COPILOT if the PR's review or review comments are
# authored by the Copilot reviewer bot, else OTHER.
# threads <pr> Print the PR's review threads as JSON: each node has
# { id, isResolved, comments:[{ databaseId, path, author, body }] }.
# The agent maps each parsed issue to a comment databaseId + thread id.
# reply <pr> <comment-id> Reply to inline review <comment-id> on <pr>; body read from STDIN.
# resolve <thread-id> Mark review thread <thread-id> resolved (GraphQL resolveReviewThread).
# summary <pr> Post a PR-level comment (the fix/skip summary table); body from STDIN.
#
# Repo is auto-detected by gh from the current directory ({owner}/{repo} placeholders).
# Usage examples:
# .../copilot-review.sh detect 48
# .../copilot-review.sh threads 48
# echo "**ai-review: FIX** — handled in <sha>" | .../copilot-review.sh reply 48 2101234567
# .../copilot-review.sh resolve PRRT_kwDOABC123
# cat summary.md | .../copilot-review.sh summary 48
set -euo pipefail
COPILOT_LOGINS_RE='^(copilot|copilot\[bot\]|copilot-pull-request-reviewer\[bot\])$'
repo_owner() { gh repo view --json owner -q .owner.login; }
repo_name() { gh repo view --json name -q .name; }
cmd_detect() {
local pr="$1"
# Check both the formal reviews and the inline review comments for a Copilot-bot author.
local hit
hit=$(
{
gh api --paginate "repos/{owner}/{repo}/pulls/${pr}/reviews" -q '.[].user.login'
gh api --paginate "repos/{owner}/{repo}/pulls/${pr}/comments" -q '.[].user.login'
} 2>/dev/null | grep -Ei "$COPILOT_LOGINS_RE" | head -n1 || true
)
if [ -n "$hit" ]; then echo "COPILOT"; else echo "OTHER"; fi
}
cmd_threads() {
local pr="$1"
local owner repo after page nodes has_next end_cursor tmp next_tmp truncated_comments
if ! command -v jq >/dev/null 2>&1; then
echo "ERROR: jq is required for paginated review thread fetching." >&2
exit 1
fi
owner="$(repo_owner)"
repo="$(repo_name)"
after=""
tmp="$(mktemp)"
next_tmp="$(mktemp)"
trap 'rm -f "$tmp" "$next_tmp"' EXIT
printf '[]\n' > "$tmp"
while :; do
page=$(gh api graphql \
-f owner="$owner" -f repo="$repo" -F pr="$pr" -f after="$after" \
-f query='
query($owner:String!,$repo:String!,$pr:Int!,$after:String){
repository(owner:$owner,name:$repo){
pullRequest(number:$pr){
reviewThreads(first:100, after:$after){
pageInfo{ hasNextPage endCursor }
nodes{
id isResolved
comments(first:100){
pageInfo{ hasNextPage }
nodes{ databaseId path author{ login } body }
}
}
}
}
}
}')
nodes="$(printf '%s' "$page" | jq -c '.data.repository.pullRequest.reviewThreads.nodes')"
jq -c --argjson nodes "$nodes" '. + $nodes' "$tmp" > "$next_tmp"
mv "$next_tmp" "$tmp"
next_tmp="$(mktemp)"
truncated_comments="$(printf '%s' "$page" | jq '[.data.repository.pullRequest.reviewThreads.nodes[] | select(.comments.pageInfo.hasNextPage == true)] | length')"
if [ "${truncated_comments:-0}" -gt 0 ]; then
echo "WARN: ${truncated_comments} review thread(s) have more than 100 comments; extra replies are omitted from thread JSON." >&2
fi
has_next="$(printf '%s' "$page" | jq -r '.data.repository.pullRequest.reviewThreads.pageInfo.hasNextPage')"
if [ "$has_next" != "true" ]; then
break
fi
end_cursor="$(printf '%s' "$page" | jq -r '.data.repository.pullRequest.reviewThreads.pageInfo.endCursor // ""')"
if [ -z "$end_cursor" ]; then
echo "WARN: GitHub reported additional reviewThreads but no endCursor; stopping pagination." >&2
break
fi
after="$end_cursor"
done
cat "$tmp"
rm -f "$tmp" "$next_tmp"
}
cmd_reply() {
local pr="$1" comment_id="$2"
gh api -X POST "repos/{owner}/{repo}/pulls/${pr}/comments/${comment_id}/replies" \
-F body=@- >/dev/null
echo "REPLIED ${comment_id}"
}
cmd_resolve() {
local thread_id="$1"
gh api graphql \
-f query='mutation($threadId:ID!){ resolveReviewThread(input:{threadId:$threadId}){ thread{ isResolved } } }' \
-f threadId="$thread_id" \
-q '.data.resolveReviewThread.thread.isResolved' >/dev/null
echo "RESOLVED ${thread_id}"
}
cmd_summary() {
local pr="$1"
gh api -X POST "repos/{owner}/{repo}/issues/${pr}/comments" \
-F body=@- -q '.html_url'
}
main() {
local sub="${1:-}"; shift || true
case "$sub" in
detect) cmd_detect "$@" ;;
threads) cmd_threads "$@" ;;
reply) cmd_reply "$@" ;;
resolve) cmd_resolve "$@" ;;
summary) cmd_summary "$@" ;;
*) echo "usage: copilot-review.sh {detect|threads|reply|resolve|summary} ..." >&2; exit 2 ;;
esac
}
main "$@"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |