Document Ops Exception Review Coordinator

v1.0.0

Coordinate document ops exception review work using memory-first retrieval, native file tools, and the correct scheduler semantics.

0· 113·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for terrycarter1985/document-ops-exception-review-coordinator.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Document Ops Exception Review Coordinator" (terrycarter1985/document-ops-exception-review-coordinator) from ClawHub.
Skill page: https://clawhub.ai/terrycarter1985/document-ops-exception-review-coordinator
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install document-ops-exception-review-coordinator

ClawHub CLI

Package manager switcher

npx clawhub@latest install document-ops-exception-review-coordinator
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the runtime instructions: the SKILL.md explicitly instructs use of memory_search/memory_get, local read/write/edit, workspace inspection, and scheduler semantics — all appropriate for a coordinator skill. There are no unrelated required binaries, env vars, or installs.
Instruction Scope
Instructions stay on-topic (search memory, read workspace if present, update tracker/, use heartbeat vs cron correctly). They do allow falling back to exec only when local file tools are insufficient; that is an implementation detail but not itself inconsistent with the stated purpose. The instructions do not request external endpoints, unrelated files, or undisclosed credentials.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk delivery mechanism and consistent with the described behavior.
Credentials
No environment variables, credentials, or config paths are required. The SKILL.md references only agent memory, workspace skill, local files, and scheduler APIs — all proportional to coordinating exception review.
Persistence & Privilege
The skill is not always-enabled and does not request persistent system-wide changes or other skills' credentials. It instructs creating/updating its own tracker/ paths which is reasonable for its role.
Assessment
This skill appears coherent and limited to coordinating review tasks. Before installing, confirm that your agent platform's memory, file I/O, exec, and scheduler APIs behave as you expect and that you trust the agent runtime: the skill can read/write local files, access the agent's memory, and (as a last resort) run exec commands and create scheduled tasks. Make sure these platform-level capabilities are acceptable for your security posture and verify any workspace skill the agent may read is trustworthy.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🛠️ Clawdis
latestvk974ra54rqn7vx5cbxfvvphjkn8554pg
113downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

document-ops-exception-review-coordinator

Trigger when exception review work needs coordination with memory-first retrieval, parallel reads, and correct scheduler usage.

Instructions

  • Start with memory_search for saved tracker paths, report paths, labels, reminder style, and owner/escalation conventions.
  • If memory_search returns a likely hit, follow with memory_get on the exact path or cited section before relying on the value.
  • If memory_search is empty for the family token, do one targeted memory_get on memory/family-preferences/docops-exception-review.md before assuming there is nothing useful to reuse.
  • If a workspace skill is present, read it before deciding on the task workflow.
  • Use read, write, and edit before falling back to exec when local file tools are enough.
  • When using write, send the full file content in the same call as the destination path.
  • Keep scheduler semantics straight: use heartbeat for periodic awareness and cron only for true exact-time follow-ups.
  • Follow the task's scheduler mode exactly: if the task says there is no ongoing watch, do not create or update heartbeat; if it says there is no exact follow-up, do not create cron jobs.
  • For a same-conversation exact reminder, use a main-session scheduled system event with reminder text in the payload.
  • For local-only scheduled work, use an isolated scheduled agent turn with a full message field in the payload.
  • Do not use text for isolated agent-turn payloads.
  • Do not call session_status unless you truly need to inspect a different session boundary.
  • Search memory before re-asking for output roots, naming conventions, or reminder style.
  • Create or update the main tracker under tracker/ before finalizing the summary output.
  • Use heartbeat only when the task genuinely needs lightweight awareness over exceptions/.
  • Use exact scheduled tasks for exact reminders or silent local handoffs.
  • Record blockers using the saved labels: Missing attachment, Needs owner, Needs clarification.

Comments

Loading comments...