leek/agent-skills / skills/implement-spec
implement-spec
VerifiedBuild a whole spec fast: parallel implementer subagents work the ticket frontier, each in its own worktree, merging onto one integration branch; then one review, one verification pass, and one PR or a stack of PRs.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 28.9 KB |
| agents/openai.yaml | config | 228 B |
| references/laravel.md | markdown | 691 B |
| references/leftovers.md | markdown | 846 B |
| references/resume-and-gates.md | markdown | 3.5 KB |
| scripts/screenshots-report.shexecutable | script | 3.5 KB |
| scripts/spec-run-state.shexecutable | script | 5.6 KB |
| scripts/test-screenshots-report.shexecutable | script | 3.4 KB |
| scripts/test-spec-run-state.shexecutable | script | 7.2 KB |
| scripts/test-worktree-idle.shexecutable | script | 2.2 KB |
| scripts/worktree-idle.shexecutable | script | 2.1 KB |
scripts/screenshots-report.sh
View on GitHub#!/bin/bash
# Which of an implement-spec run's screenshots reached a pull request, so the run cannot
# close as delivered while one did not. No network: "uploaded" is what the run recorded
# here after a successful upload-screenshots.sh call, not a lookup.
#
# Usage: screenshots-report.sh <notes dir> [--uploaded <image>... | --left-out <image>...]
# <notes dir> is the run's notes directory (spec-run-state.sh's "notes"); the images are
# the .png, .jpg, .jpeg, .gif and .webp files directly in <notes dir>/screenshots/.
# --uploaded <image>... record each image (a path or a file name) as uploaded, in
# screenshots/uploaded.txt, one file name per line; then report.
# --left-out <image>... record each as left out of every pull request on purpose (a
# failure fixed later, other work, PII), in screenshots/left-out.txt.
# An image named with a flag must exist in the folder (exit 1, nothing recorded).
# Without a flag it changes nothing. Needs jq.
#
# Output: JSON
# {"dir", "images": [{"file", "path", "ticket", "uploaded", "left_out"}],
# "counts": {"images", "uploaded", "left_out", "not_uploaded"}}
# "ticket" is the digits the file name starts with ("03" for 03-login.png), else "".
# "not_uploaded" counts the images neither uploaded nor left out. A missing screenshots/
# folder reports no images.
#
# Exit: 0 reported, 1 an image named with a flag is not in the folder or jq is missing,
# 2 usage error.
set -e
usage() { echo "Usage: screenshots-report.sh <notes dir> [--uploaded <image>... | --left-out <image>...]" >&2; exit 2; }
notes=${1:-}
[ -n "$notes" ] && [ -d "$notes" ] || { [ -z "$notes" ] || echo "Not a directory: $notes" >&2; usage; }
shift
command -v jq >/dev/null 2>&1 || { echo "screenshots-report.sh needs jq on PATH" >&2; exit 1; }
dir="$(cd "$notes" && pwd -P)/screenshots"
if [ $# -gt 0 ]; then
case "$1" in
--uploaded) list="$dir/uploaded.txt" ;;
--left-out) list="$dir/left-out.txt" ;;
*) echo "Unknown arg: $1" >&2; usage ;;
esac
shift
[ $# -gt 0 ] || usage
for f in "$@"; do
[ -f "$dir/$(basename "$f")" ] || { echo "Not in $dir: $(basename "$f")" >&2; exit 1; }
done
for f in "$@"; do
name=$(basename "$f")
grep -qxF -- "$name" "$list" 2>/dev/null || printf '%s\n' "$name" >> "$list"
done
fi
listed() { [ -f "$2" ] && grep -qxF -- "$1" "$2"; } # listed <name> <list file>
bool() { "$@" && echo true || echo false; }
images='[]'
if [ -d "$dir" ]; then
for f in "$dir"/*; do
[ -f "$f" ] || continue
name=$(basename "$f")
case "$name" in
*.png | *.jpg | *.jpeg | *.gif | *.webp | *.PNG | *.JPG | *.JPEG | *.GIF | *.WEBP) ;;
*) continue ;;
esac
ticket=$(printf '%s' "$name" | sed -n 's/^\([0-9][0-9]*\).*/\1/p')
images=$(jq -cn --argjson all "$images" --arg file "$name" --arg path "$f" --arg ticket "$ticket" \
--argjson uploaded "$(bool listed "$name" "$dir/uploaded.txt")" \
--argjson left_out "$(bool listed "$name" "$dir/left-out.txt")" \
'$all + [{file: $file, path: $path, ticket: $ticket, uploaded: $uploaded, left_out: $left_out}]')
done
fi
jq -cn --arg dir "$dir" --argjson images "$images" \
'{dir: $dir, images: $images,
counts: {images: ($images | length),
uploaded: ($images | map(select(.uploaded)) | length),
left_out: ($images | map(select(.left_out and (.uploaded | not))) | length),
not_uploaded: ($images | map(select((.uploaded or .left_out) | not)) | length)}}'
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |