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/test-worktree-idle.sh
View on GitHub#!/bin/bash
# Offline test for worktree-idle.sh with a 3-second limit and a 1-second poll.
# Usage: test-worktree-idle.sh (prints one "ok <case>" line per case; exits 1 on the first failure)
set -e
here=$(cd "$(dirname "$0")" && pwd)
script="$here/worktree-idle.sh"
T=$(cd "$(mktemp -d)" && pwd -P)
trap 'rm -rf "$T"' EXIT
export WORKTREE_IDLE_LIMIT_SECONDS=3 WORKTREE_IDLE_POLL_SECONDS=1
fail() { echo "FAIL $1" >&2; [ ! -f "$T/err" ] || sed 's/^/ stderr: /' "$T/err" >&2; exit 1; }
eq() { [ "$2" = "$3" ] || fail "$1: got '$2', want '$3'"; }
# untouched worktree: alarms once the limit passes
mkdir "$T/quiet"
start=$(date +%s)
out=$(bash "$script" "$T/quiet" 2>"$T/err") || fail "quiet: exit $?"
eq "quiet status" "$(printf '%s' "$out" | jq -r .status)" idle
eq "quiet worktree" "$(printf '%s' "$out" | jq -r .worktree)" "$T/quiet"
[ $(( $(date +%s) - start )) -ge 3 ] || fail "quiet: alarmed before the limit"
echo "ok quiet worktree alarms after the limit"
# a worktree written every second for 5 seconds: no alarm until the writes stop
mkdir "$T/busy"
( for i in 1 2 3 4 5; do echo "$i" > "$T/busy/f$i"; sleep 1; done ) &
writer=$!
start=$(date +%s)
out=$(bash "$script" "$T/busy" 2>"$T/err") || fail "busy: exit $?"
wait "$writer"
eq "busy status" "$(printf '%s' "$out" | jq -r .status)" idle
[ $(( $(date +%s) - start )) -ge 7 ] || fail "busy: alarmed while files were still changing"
echo "ok steady writes hold the alarm off"
# writes under .git only: still idle
mkdir -p "$T/gitonly/.git"
( for i in 1 2 3 4 5; do echo "$i" > "$T/gitonly/.git/f$i"; sleep 1; done ) &
writer=$!
start=$(date +%s)
out=$(bash "$script" "$T/gitonly" 2>"$T/err") || fail "gitonly: exit $?"
wait "$writer"
[ $(( $(date +%s) - start )) -lt 6 ] || fail "gitonly: .git writes held the alarm off"
echo "ok .git writes are ignored"
# worktree removed mid-watch: reports gone
mkdir "$T/gone"
( sleep 1; rm -rf "$T/gone" ) &
out=$(bash "$script" "$T/gone" 2>"$T/err") || fail "gone: exit $?"
wait
eq "gone status" "$(printf '%s' "$out" | jq -r .status)" gone
echo "ok removed worktree reports gone"
# bad input exits 1
if bash "$script" "$T/missing" 2>"$T/err"; then fail "missing dir accepted"; fi
if bash "$script" "$T/quiet" 2x 2>"$T/err"; then fail "bad minutes accepted"; fi
echo "ok bad input exits 1"
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: 469k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |