AGENT SKILL

sheet-audit

Use when a spreadsheet needs its formulas audited before a financial close, and the reviewer wants every cell reference traced back to a source sheet.

License 许可
Apache-2.0
最近更新
2026-10-23
Stars
★ 94
Forks
0

01 前言 Front Matter

name
sheet-audit
description
Use when a spreadsheet needs its formulas audited before a financial close, and the reviewer wants every cell reference traced back to a source sheet.

03 SKILL.md 正文

Sheet audit

Trace formulas back to their sources.

04 同仓库更多 Skills

3338902669-ops
3338902669-ops/agent-orchestra

image_search

Search the web by text query for image URLs and source pages for feeds, artifacts, and visual references. Does not identify a supplied image or person.

★ 94
3338902669-ops
3338902669-ops/agent-orchestra

changelog-writer

Use when a release needs a changelog entry drafted from merged pull requests, grouped by the kind of change rather than by the order they landed.

★ 94
3338902669-ops
3338902669-ops/agent-orchestra

agent-team-os

Run a team of AI agents (or one agent in several role sessions) as one governed unit — layered long-term memory, hub-coordinated governance with evidence anchors and human approval gates, an identity-based agent mailbox with receipts, and an event-driven doorbell that wakes seats on new mail without polling. Use when setting up or operating a multi-agent team, when agents must share durable memory and verifiable hand-offs, or when a single agent should work in the same pattern across multiple sessions. Do not use for adversarial or multi-tenant environments, or for any flow where a single message by itself authorizes payment, deployment, or credential release — on the mailbox's CLI path the sender is self-declared.

★ 94
3338902669-ops
3338902669-ops/agent-orchestra

agent-orchestra

Use when three or more AI agents are available and a task needs coordinated execution, or when work must be handed to another agent, session or tool. It ships the coordination rules as ENFORCED invariants rather than advice: one writer per resource (a conflicting claim is refused and names the holder), a verifier that is never the implementer and whose PASS must carry criterion-linked evidence, a failed verification that blocks both done and dispatch to evidence, three failed rounds that block the task outright, an external action that cannot be dispatched until an approval covering it is recorded, a domain review by a third party for consequential work, rigorous E1-E4 evidence grading with enforced floors, capability-scored role assignment from a roster of any size (any agent names), a shared handoff record with a checker, a dependency-free task-queue CLI, an important-task intake gate, and a coordination anti-pattern guide. One command - scripts/gate.mjs - runs sixteen checks and injects twelve known faults it must reject before reporting PASS. Activation is configurable: global, keyword-triggered (three-valued: engage / surface / silent), or manual. Do not use for: container or infrastructure orchestration (k8s, docker-compose, service meshes), ordinary job queues and schedulers, comparing or evaluating AI models against each other, or splitting work between people. Those share vocabulary with this skill and none of them is multi-agent coordination.

★ 94