alirezarezvani/claude-skills / agent-launcher/skills/run-without-you
run-without-you
VerifiedUse when a graded managed agent should run on a schedule, on an event trigger or on demand ('run it every morning'). Validates cron with cron_validator.py and builds the deployment with deployment_builder.py.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.1 KB |
| SKILL.md | skill md | 3.6 KB |
| scripts/cron_validator.py | script | 5.2 KB |
| scripts/deployment_builder.py | script | 5.9 KB |
| scripts/next_directions_writer.py | script | 3.9 KB |
scripts/cron_validator.py
View on GitHub#!/usr/bin/env python3
"""cron_validator.py — validate a 5-field POSIX cron expression + IANA timezone.
CMA scheduled deployments use standard 5-field POSIX cron (minute granularity)
with an IANA timezone and wall-clock DST semantics. This validates the shape and
ranges, resolves the timezone against the local zoneinfo database when available,
and prints the DST behavior note. Exit 0 valid, 1 invalid. Stdlib-only.
Fields: minute(0-59) hour(0-23) day-of-month(1-31) month(1-12) day-of-week(0-6).
Each supports *, a-b ranges, a,b,c lists, and */step.
Examples:
cron_validator.py --cron "0 9 * * *" --timezone Europe/Berlin
cron_validator.py --cron "*/15 0-6 * * 1-5" --timezone America/New_York
cron_validator.py --sample
"""
import argparse
import json
import sys
RANGES = [(0, 59), (0, 23), (1, 31), (1, 12), (0, 6)]
NAMES = ["minute", "hour", "day-of-month", "month", "day-of-week"]
def _valid_field(field: str, lo: int, hi: int):
for part in field.split(","):
if part == "*":
continue
step_base, _, step = part.partition("/")
if step:
if not step.isdigit() or int(step) < 1:
return False, f"bad step '{part}'"
if step_base == "*" or step_base == "":
continue
if "-" in step_base:
a, _, b = step_base.partition("-")
if not (a.isdigit() and b.isdigit()):
return False, f"bad range '{part}'"
a, b = int(a), int(b)
if a < lo or b > hi or a > b:
return False, f"range '{part}' outside {lo}-{hi}"
else:
if not step_base.isdigit():
return False, f"non-numeric '{part}'"
v = int(step_base)
if v < lo or v > hi:
return False, f"value {v} outside {lo}-{hi}"
return True, None
def validate_cron(expr: str):
fields = expr.split()
if len(fields) != 5:
return False, [f"expected 5 fields, got {len(fields)}: {expr!r}"]
errors = []
for field, (lo, hi), name in zip(fields, RANGES, NAMES):
ok, err = _valid_field(field, lo, hi)
if not ok:
errors.append(f"{name}: {err}")
return (not errors), errors
def validate_tz(tz: str):
if not tz:
return False, "no timezone given (IANA id required, e.g. Europe/Berlin)"
try:
from zoneinfo import ZoneInfo, ZoneInfoNotFoundError
try:
ZoneInfo(tz)
return True, None
except ZoneInfoNotFoundError:
return False, f"IANA timezone '{tz}' not found in the zoneinfo database"
except ImportError:
# zoneinfo unavailable; do a light sanity check.
if "/" in tz or tz in ("UTC",):
return True, "zoneinfo unavailable; shape looks like an IANA id (not verified)"
return False, f"'{tz}' does not look like an IANA id and zoneinfo is unavailable"
DST_NOTE = ("Wall-clock DST: the expression fires at literal local time. On "
"spring-forward, a nonexistent local time is skipped; on fall-back, a "
"repeated local time fires twice. Avoid scheduling 02:00-03:00 in "
"DST-observing zones if exactly-once matters.")
def main() -> int:
ap = argparse.ArgumentParser(description="Validate a 5-field POSIX cron + IANA timezone for a CMA deployment.")
ap.add_argument("--cron", help="5-field cron expression.")
ap.add_argument("--timezone", default="UTC")
ap.add_argument("--json", action="store_true")
ap.add_argument("--sample", action="store_true")
args = ap.parse_args()
if args.sample:
results = []
for expr, tz in [("0 9 * * *", "Europe/Berlin"), ("*/15 0-6 * * 1-5", "America/New_York"),
("0 25 * * *", "UTC"), ("0 9 * *", "Mars/Olympus")]:
ok, errs = validate_cron(expr)
tzok, tznote = validate_tz(tz)
if args.json:
results.append({"cron": expr, "cron_valid": ok, "cron_errors": errs,
"timezone": tz, "timezone_valid": tzok, "timezone_note": tznote})
continue
print(f"[{'OK ' if ok and tzok else 'BAD'}] {expr!r} @ {tz}: "
f"{'valid' if ok else errs}; tz {'valid' if tzok else tznote}")
if args.json:
print(json.dumps({"samples": results, "dst_note": DST_NOTE}, indent=2))
return 0
print(f"\n{DST_NOTE}")
return 0
if not args.cron:
print("Provide --cron.", file=sys.stderr)
return 2
ok, errs = validate_cron(args.cron)
tzok, tznote = validate_tz(args.timezone)
result = {"cron": args.cron, "cron_valid": ok, "cron_errors": errs,
"timezone": args.timezone, "timezone_valid": tzok, "timezone_note": tznote,
"dst_note": DST_NOTE}
if args.json:
print(json.dumps(result, indent=2))
else:
print(f"cron: {'VALID' if ok else 'INVALID'} — {args.cron}")
for e in errs:
print(f" - {e}")
print(f"timezone: {'VALID' if tzok else 'INVALID'} — {args.timezone}")
if tznote:
print(f" {tznote}")
print(f"DST: {DST_NOTE}")
return 0 if (ok and tzok) else 1
if __name__ == "__main__":
raise SystemExit(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 |