Guide accessibility reviews for UI, documents, and workflows. Use for WCAG-oriented audits, keyboard review, semantics, contrast, and remediation planning.
日本語の概要は準備中です。原文の説明を表示しています。
Use when managing cron from a repo-local manifest: time triggers, on-boot-with-delay, sequenced tasks; create, remove, reorder, install.
日本語の概要は準備中です。原文の説明を表示しています。
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
Define triggers and tasks in a single YAML manifest. One trigger (for example, midnight-utc) runs multiple tasks in sequence; on-boot triggers can delay before execution. Tooling creates, removes, reorders, enables, disables, validates, and installs generated crontab fragments.
This skill owns cron manifest and scheduling behavior. Public harness docs may reference cron, but cron validation, argv command handling, install fragments, and sequencing rules live here.
ls-codex-heartbeat-checks for heartbeat-specific scheduling instead of duplicating heartbeat activation rules here.triggers:
midnight-utc:
schedule: "0 0 * * *"
after-boot:
on_boot_delay_minutes: 5
tasks:
- id: snapshot-daily
trigger: midnight-utc
sequence_order: 1
command:
- python3
- ls/skills/ls-system-baseline-diagnostics/scripts/system_snapshot.py
- --output-basename
- reports/system-snapshots/daily
enabled: true
timeout_seconds: 3600
schedule with five numeric Linux cron fields (lists, ranges, and steps) or on_boot_delay_minutes from 0 to 1440.id, trigger, sequence_order (integer 0 to 86400), command, and optional enabled plus timeout_seconds.shlex and reject shell operators such as &&, |, redirects, backticks, and command substitution. Shell expansion is not performed.Use python3 ls/skills/ls-cron-job-scheduling/scripts/cron_ctl.py --manifest cron/manifest.yaml <command>.
| Command | Purpose |
|---|---|
validate | Check manifest schema, trigger refs, command shape, timeouts, and schedules |
list [--trigger NAME] | List tasks (optionally for one trigger) |
add-task --trigger NAME --command "..." [--sequence-order N] [--id ID] | Add task |
remove-task --id ID or --trigger NAME | Remove by id or all for trigger |
reorder --trigger NAME --order id1,id2,id3 | Set run order for that trigger |
enable --id ID / disable --id ID | Toggle task |
install [--repo-root PATH] [--output PATH] [--log-dir PATH] | Generate a reviewable user-crontab fragment; it never modifies a live crontab. --output writes the fragment, otherwise it prints to standard output. |
Runner (used by cron): python3 ls/skills/ls-cron-job-scheduling/scripts/run_trigger.py --manifest PATH --repo-root PATH TRIGGER runs that trigger's tasks in sequence with subprocess.Popen(..., shell=False), relaying output while retaining bounded byte tails for logs.
Add --log-dir PATH when cron output may otherwise disappear; the runner appends
timestamped start, task exit, stdout tail, and stderr tail records to
PATH/<trigger>.log.
Because stdout/stderr tails can include sensitive data, use a protected log
directory with restricted permissions.
See references/manifest.md for the accepted manifest schema and security model.
add-task --trigger midnight-utc --command "python3 ls/skills/ls-system-baseline-diagnostics/scripts/system_snapshot.py --output-basename reports/system-snapshots/daily".on_boot_delay_minutes: 5; then add tasks to it.reorder --trigger midnight-utc --order snapshot-daily,cleanup,notify.remove-task --id snapshot-daily. Remove all for a trigger: remove-task --trigger midnight-utc.install --output cron/crontab.generated, inspect the generated user-crontab fragment, then merge it manually with the existing user crontab only after an explicit operational decision. Do not write /etc/cron.d or replace an existing crontab from this skill.まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Guide accessibility reviews for UI, documents, and workflows. Use for WCAG-oriented audits, keyboard review, semantics, contrast, and remediation planning.
日本語の概要は準備中です。原文の説明を表示しています。
Use when choosing a LocalSetup Agent-* lane for exploration, research, bounded implementation, or review. Consult the static capability matrix; do not probe account or network availability.
日本語の概要は準備中です。原文の説明を表示しています。
Guide agent email inbox workflows with prompt-injection defenses. Use for inbound email processing, webhooks, routing, and safety review.
日本語の概要は準備中です。原文の説明を表示しています。
Navigate and understand codebases using agentlens hierarchical documentation. Use when exploring new projects, finding modules, locating symbols in large files, finding TODOs/warnings, or understanding code structure.
日本語の概要は準備中です。原文の説明を表示しています。
Use for Agent Q signed encrypted file-drop or mail ship and ingest, private registry v2 setup, queue status, and transport maintenance.
日本語の概要は準備中です。原文の説明を表示しています。
Inventory wrapper for the alirezarezvani Claude skills bundle. Use when triaging its broad skill catalog and large script surface before any targeted import.
日本語の概要は準備中です。原文の説明を表示しています。