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/next_directions_writer.py
View on GitHub#!/usr/bin/env python3
"""next_directions_writer.py — write/refresh ./my-agent/NEXT-DIRECTIONS.md.
Renders the versioned roadmap from a build sheet's deferrals + the current goal
state: v0 (live) plus a table of deferred upgrades (version/item/reason/mechanism)
and the suggested next 1-2 moves. Uses the assets/NEXT-DIRECTIONS.template.md
shape. Stdlib-only; no network calls.
Examples:
next_directions_writer.py --sheet ./my-agent/build-sheet.json --out-dir ./my-agent
next_directions_writer.py --sample
"""
import argparse
import datetime as dt
import json
import sys
from pathlib import Path
def _now():
return dt.datetime.now(dt.timezone.utc).replace(microsecond=0).isoformat()
def render(sheet, loop_shape, last_verdict):
goal = sheet.get("goal", "")
name = sheet.get("agent_name", "agent")
prim = sheet.get("primitives", {})
live = []
if prim.get("agent", {}).get("model"):
live.append(f"agent[{prim['agent']['model']}]")
live.append(f"env[{prim.get('environment', {}).get('type', 'cloud')}]")
if prim.get("outcome"):
live.append("outcome[rubric]")
if prim.get("session", {}).get("memory_stores"):
live.append(f"memory[{len(prim['session']['memory_stores'])}]")
if prim.get("deployment"):
live.append("deployment[cron]")
deferrals = sheet.get("deferrals", []) or []
if deferrals:
rows = "\n".join(
f"| {d.get('version','v?')} | {d.get('item','')} | {d.get('reason','')} | {d.get('mechanism','')} |"
for d in deferrals
)
else:
rows = "| — | (none recorded) | | |"
next_moves = _next_moves(deferrals, prim)
tmpl_path = Path(__file__).resolve().parents[3] / "assets" / "NEXT-DIRECTIONS.template.md"
tmpl = tmpl_path.read_text()
return tmpl.format(
agent_name=name,
goal=goal,
loop_shape=loop_shape or sheet.get("loop_hint", "single-pass"),
live_primitives=", ".join(live),
last_verdict=last_verdict or "(not graded yet)",
deferral_rows=rows,
next_moves=next_moves,
updated_at=_now(),
)
def _next_moves(deferrals, prim):
moves = []
v1s = [d for d in deferrals if d.get("version") == "v1"]
if v1s:
moves.append(f"1. Ship {v1s[0].get('item')} — {v1s[0].get('mechanism')}")
if not prim.get("deployment"):
moves.append(f"{len(moves)+1}. Promote to a scheduled deployment once a version passes the rubric.")
elif prim.get("environment", {}).get("networking") == "unrestricted":
moves.append(f"{len(moves)+1}. Harden networking to 'limited' with an allowed_hosts list.")
if not moves:
moves.append("1. Monitor the first few scheduled runs; tighten the rubric if verdicts drift.")
return "\n".join(moves)
def main() -> int:
ap = argparse.ArgumentParser(description="Write/refresh NEXT-DIRECTIONS.md from a build sheet.")
ap.add_argument("--sheet", help="build-sheet.json.")
ap.add_argument("--out-dir", default="./my-agent")
ap.add_argument("--loop-shape", default=None)
ap.add_argument("--last-verdict", default=None)
ap.add_argument("--stdout", action="store_true")
ap.add_argument("--sample", action="store_true")
args = ap.parse_args()
if args.sample:
sheet = json.loads((Path(__file__).resolve().parents[3] / "assets" / "example-build-sheet.json").read_text())
print(render(sheet, "cron-loop", "satisfied"))
return 0
if not args.sheet:
print("Provide --sheet path.", file=sys.stderr)
return 2
sheet = json.loads(Path(args.sheet).read_text())
md = render(sheet, args.loop_shape, args.last_verdict)
if args.stdout:
print(md)
return 0
out_dir = Path(args.out_dir)
out_dir.mkdir(parents=True, exist_ok=True)
dest = out_dir / "NEXT-DIRECTIONS.md"
dest.write_text(md)
print(f"Wrote {dest}")
return 0
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 |