skills/delayed-command/SKILL.md
This skill should be used when the user asks to "run npm test after 30 minutes", "git commit after 1 hour", "wait 2h then deploy", "sleep 45m and run build", "after 10m run prettier", or provides a duration followed by a shell command to execute later.
npx skillsauth add paulrberg/agent-skills delayed-commandInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Wait for a specified duration, then execute a Bash command.
30s, 5m, 1h, 1h30m)| Format | Example | Meaning |
| -------- | --------- | ----------------- |
| Xs | 30s | 30 seconds |
| Xm | 5m | 5 minutes |
| Xh | 1h | 1 hour |
| XhYm | 1h30m | 1 hour 30 minutes |
| XhYmZs | 1h5m30s | 1 hour 5 min 30 s |
Convert the duration argument to seconds:
h), minutes (m), and seconds (s) componentshours * 3600 + minutes * 60 + secondsParsing logic:
duration="$1"
seconds=0
# Extract hours
if [[ $duration =~ ([0-9]+)h ]]; then
seconds=$((seconds + ${BASH_REMATCH[1]} * 3600))
fi
# Extract minutes
if [[ $duration =~ ([0-9]+)m ]]; then
seconds=$((seconds + ${BASH_REMATCH[1]} * 60))
fi
# Extract seconds
if [[ $duration =~ ([0-9]+)s ]]; then
seconds=$((seconds + ${BASH_REMATCH[1]}))
fi
For durations up to 10 minutes (600 seconds):
Run synchronously using the Bash tool with appropriate timeout:
sleep <seconds> && <command>
Set the Bash tool's timeout parameter to at least (seconds + 60) * 1000 milliseconds.
For durations over 10 minutes:
Run in background using run_in_background: true:
sleep <seconds> && <command>
Inform the user the command is running in background and provide the task ID for checking status.
After execution completes:
User: /delayed-command 5m npm test
sleep 300 && npm test (timeout: 360000ms)User: /delayed-command 1h git commit -m "auto-commit"
sleep 3600 && git commit -m "auto-commit"User: /delayed-command 1h30m ./deploy.sh
sleep 5400 && ./deploy.sh| Error | Response | | ------------------------ | -------------------------------------------- | | Invalid duration format | Show supported formats and examples | | Missing command argument | Prompt for the command to execute | | Command not found | Report error after delay completes | | Duration exceeds 24h | Warn user and suggest alternative (cron, at) |
development
This skill should be used when the user asks to "debrief", "debrief this task", "debrief the session", "save findings", "save analysis", "save this as a report", "create an HTML report from the transcript", or wants to persist the current task's findings as a self-contained interactive HTML playground at `./.ai/reports/<slug>/index.html`. Flag: --md emits a plain Markdown report at `./.ai/reports/<slug>/index.md` and skips the playground dependency.
documentation
This skill should be used when the user asks to create or update a GitHub PR, file or update an issue, post a comment, or start a discussion. Trigger phrases include "create PR", "open PR", "file an issue", "update issue", "yeet a PR/issue/discussion", "comment on an issue".
development
This skill should be used when the user asks to resolve an EVM chain name or chain ID; find chain metadata such as a default public RPC, native currency symbol, or block explorer URL; determine whether a chain is supported by RouteMesh; or read on-chain account data for any EVM chain — "check ETH balance", "query ERC-20 balance", "get wallet balance", "check token holdings", "fetch NFT transfers", "ERC-721 or ERC-1155 transfer history", "transaction history", "find first funding transaction", "trace fund origin", "who funded this address", "query Etherscan", "query Blockscout", or "look up a chain on Chainscout". It routes each data query through Etherscan API V2 (preferred) or the Blockscout/Chainscout APIs (fallback for chains Etherscan doesn't serve), with direct JSON-RPC as a last resort. Also use it for chain resolution before fetching data from or interacting with an EVM chain.
development
This skill should be used when the user asks to commit changes, craft a commit message, or run a commit workflow. Creates atomic git commits with conventional-commit formatting and optional deep analysis or push. Flags: --all, --deep, --close, --push.