Skip to content

tanweiping1012-source/travel-planner

travel-planner-mvp

Verified

Create evidence-backed, read-only travel plans using Amap, a community 12306 rail MCP, and approved browser research. Use for 行程规划、路线安排、景点取舍、高铁或机票比较、酒店住宿比价、预算分析、旅行可行性检查,以及中国境内多城市旅行规划(境外目的地降级为浏览器辅助规划)。

FileKindSize
SKILL.mdskill md12.5 KB
agents/openai.yamlconfig344 B
examples/final_plan.jsonconfig2.6 KB
examples/itinerary.jsonconfig1020 B
examples/rail_query.jsonconfig2.9 KB
examples/social_research.jsonconfig1.3 KB
examples/trip_request.jsonconfig1.1 KB
references/browser-use.mdmarkdown14.8 KB
references/client-compatibility.mdmarkdown5.4 KB
references/data-contracts.mdmarkdown26.6 KB
references/intake-template.mdmarkdown4.9 KB
references/rail-mcp.mdmarkdown4.3 KB
references/script-tools.mdmarkdown3.5 KB
references/workflow.mdmarkdown13.3 KB
scripts/audit_release.shexecutablescript3.4 KB
scripts/prepare_release.shexecutablescript1.8 KB
scripts/setup_amap_key.shexecutablescript828 B
scripts/setup_rail_mcp.shexecutablescript3.8 KB
scripts/travel_planner.pyexecutablescript11.8 KB
scripts/validate_skill.pyexecutablescript5.5 KB

scripts/audit_release.sh

View on GitHub
#!/bin/sh
set -eu

SCRIPT_DIR=$(CDPATH='' cd -- "$(dirname -- "$0")" && pwd)
SKILL_ROOT=$(CDPATH='' cd -- "$SCRIPT_DIR/.." && pwd)
TARGET=${1:-"$SKILL_ROOT"}
FAILURES=0
AUDIT_TEMP_DIR=$(mktemp -d "${TMPDIR:-/tmp}/travel-planner-audit.XXXXXX")

cleanup() {
  rm -rf "$AUDIT_TEMP_DIR"
}

trap cleanup EXIT HUP INT TERM

fail() {
  printf 'ERROR: %s\n' "$1" >&2
  FAILURES=$((FAILURES + 1))
}

if [ ! -d "$TARGET" ]; then
  echo "Audit target does not exist: $TARGET" >&2
  exit 1
fi

TARGET=$(CDPATH='' cd -- "$TARGET" && pwd)

for name in vendor .venv venv runs artifacts output; do
  if find "$TARGET" -type d -name "$name" -print -quit | grep -q .; then
    fail "forbidden directory found: $name"
  fi
done

if find "$TARGET" -type d -name .git \
  ! -path "$TARGET/.git" -print -quit | grep -q .; then
  fail "nested .git directory found"
fi

for pattern in '.env' '.env.*' '*.pem' '*.key' '*.p12' '*.pfx' '*.har' \
  '*cookie*' '*session*' 'storage-state*.json' '*.log'; do
  if find "$TARGET" -type f -name "$pattern" \
    ! -path "$TARGET/.git/*" \
    ! -name '.env.example' -print -quit | grep -q .; then
    fail "sensitive file pattern found: $pattern"
  fi
done

if find "$TARGET" -type f \
  ! -name '*.pyc' \
  ! -path "$TARGET/.git/*" \
  ! -path '*/__pycache__/*' \
  ! -name 'audit_release.sh' \
  -print0 | xargs -0 grep -nE \
    'AKIA[0-9A-Z]{16}|sk-[A-Za-z0-9_-]{20,}|-----BEGIN (RSA |EC |OPENSSH )?PRIVATE KEY-----' \
    >"$AUDIT_TEMP_DIR/secrets.txt" 2>/dev/null; then
  cat "$AUDIT_TEMP_DIR/secrets.txt" >&2
  fail "high-confidence secret pattern found"
fi

if find "$TARGET" -type f \
  ! -name '*.pyc' \
  ! -path "$TARGET/.git/*" \
  ! -path '*/__pycache__/*' \
  ! -name 'audit_release.sh' \
  -print0 | xargs -0 grep -niE \
    "AMAP(_API)?_KEY[[:space:]]*[:=][[:space:]]*['\"]?[A-Za-z0-9]{20,}" \
    >"$AUDIT_TEMP_DIR/amap-secrets.txt" 2>/dev/null; then
  cat "$AUDIT_TEMP_DIR/amap-secrets.txt" >&2
  fail "possible Amap API key assignment found"
fi

if find "$TARGET" -type f \
  ! -name '*.pyc' \
  ! -path "$TARGET/.git/*" \
  ! -path '*/__pycache__/*' \
  ! -name 'audit_release.sh' \
  -print0 | xargs -0 grep -nE \
    '/Users/[^/]+/|/home/[^/]+/|[A-Za-z]:\\\\Users\\\\[^\\\\]+' \
    >"$AUDIT_TEMP_DIR/paths.txt" 2>/dev/null; then
  cat "$AUDIT_TEMP_DIR/paths.txt" >&2
  fail "absolute user path found"
fi

if find "$TARGET" -type f \
  ! -name '*.pyc' \
  ! -path "$TARGET/.git/*" \
  ! -path '*/__pycache__/*' \
  ! -name 'audit_release.sh' \
  -print0 | xargs -0 grep -nE \
    'xiaohongshu\.com/explore/[0-9a-f]{20,}' \
    >"$AUDIT_TEMP_DIR/xhs.txt" 2>/dev/null; then
  cat "$AUDIT_TEMP_DIR/xhs.txt" >&2
  fail "real-looking Xiaohongshu note ID found"
fi

if find "$TARGET" -type f \
  ! -name '*.pyc' \
  ! -path "$TARGET/.git/*" \
  ! -path '*/__pycache__/*' \
  ! -name 'audit_release.sh' \
  -print0 | xargs -0 grep -nE \
    '2026-09-(24|27)|"budget_cny"[[:space:]]*:[[:space:]]*4000' \
    >"$AUDIT_TEMP_DIR/private-examples.txt" 2>/dev/null; then
  cat "$AUDIT_TEMP_DIR/private-examples.txt" >&2
  fail "private planning fingerprint found"
fi

if command -v gitleaks >/dev/null 2>&1; then
  gitleaks dir --redact --exit-code 1 "$TARGET" \
    >/dev/null || fail "gitleaks detected a possible secret"
else
  printf 'WARNING: gitleaks is not installed; built-in checks only.\n' >&2
fi

if [ "$FAILURES" -ne 0 ]; then
  printf 'Release audit failed with %s issue(s).\n' "$FAILURES" >&2
  exit 1
fi

printf 'Release audit passed: %s\n' "$TARGET"
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall