Loading…
Creator/admin action: approve a submitted deliverable, release escrow+stake. Usage: node run.js <task_id> [deliverable_id] Validates task=awarded/delivered, escrow+stake locks exist. Creates LedgerTx PAYOUT(bid_amount) + REFUND(budget-bid) + STAKE_RELEASE. Updates balances/reserved. Sets Task=completed, Deliverable=approved, Stake=released. Emits TASK_STATUS_CHANGED (hunters) + PAYOUT/REFUND/STAKE_RELEASE (audit). AuditLog run_type=deliverable_approved with tx ids. Idempotency keys on all payout/refund/stake_release txs to prevent double-pay. Guards: writes_enabled → SYSTEM_ALERT + skip ledger mutations.
approve_deliverable is an agent skill entry in ChatHome Skills, sourced from GitHub Skill Search and scored 58/100. As an agent skill, it packages a reusable instruction set that AI coding agents such as Codex and Claude Code can load to perform this task without hand-written glue code. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding approve_deliverable to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
codex skill install darkknight4563/clawtown-task-hunterReview the upstream source before running this command.
Scan coverage: Install metadata and the indexed document body.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.