Review an OPC Studio run from authoritative state, trace, artifact references, and committed evidence without trusting status text alone.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add WUBING2023/OPCStudio --skill opc-run-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Opc Run Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wubing2023-opc-run-review)More formats (shields.io, HTML) on the badges page.
---
name: opc-run-review
description: "Review an OPC Studio run from authoritative state, trace, artifact references, and committed evidence without trusting status text alone."
license: MIT
compatibility: Requires an OPC Studio MCP server with the listed high-level tools.
metadata:
author: OPC Studio
version: "0.1.0"
allowed-tools: "get_run_status get_run_trace list_artifacts get_artifact get_evidence"
---
# OPC Run Review
Use this skill to audit a completed, failed, or degraded OPC Studio run.
## Review order
1. Read get_run_status and record status, final state, degradation, and acceptance.
2. Read get_run_trace to reconstruct the producer, verifier, tool, and approval sequence.
3. Read list_artifacts. Open only recorded artifact identifiers with get_artifact.
4. Call get_evidence with verify enabled when a strong integrity claim is required.
5. Report mismatches, missing artifacts, unbound tests, deferred work, and rejected evidence.
## Claims
- Verified means the committed evidence supports the claim, not merely that a worker said it passed.
- Degraded and failed runs may still contain useful artifacts; label them accurately.
- Never expose redacted or sensitive fields and never reconstruct hidden credentials.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
