Quality Eval Prompt: Multi-Skill Workflow Execution Gate
# Quality Eval Prompt: Multi-Skill Workflow Execution Gate
Use `coff0xc-skill-router` to compose and execute a recoverable multi-skill workflow for a billing anomaly that also has a security alert and customer-facing deliverables.
Goal: prove the agent did more than pick skills. It must leave a machine-readable execution trace that records phases, skills, inputs, artifacts, gates, re-routing, and final verification.
Required behavior:
- Start with `coff0xc-skill-router` and create a task-specific skill graph.
- Use support skills for software repair, API/data contract, AppSec/security regression, compliance evidence, UI review, and Office customer deliverables.
- Execute in phases and record each phase's inputs, produced artifacts, and gate status.
- Record at least one re-route when new evidence changes the skill graph.
- Save final verification commands and result.
Expected output directory shape:when to use it
Community prompt sourced from the open-source GitHub repo Coff0xc/coffee-skill (NOASSERTION). A "Quality Eval Prompt: Multi-Skill Workflow Execution Gate" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
productivitycommunitydeveloper
source
Coff0xc/coffee-skill · NOASSERTION
more in Productivity
Productivity✓ tested
Summarize a doc into decisions & actions
chief of staff who extracts what to DO, not just what was said
Productivity✓ tested
Draft a reply to a hard email
calm, direct communicator who de-escalates without caving
Productivity✓ tested
Turn a brain-dump into a weekly plan
planning coach who protects your focus, not just your calendar