skills.rest
gaofeng21cn
gaofeng21cnCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

opl-foundry-agent-improver

Analyze OPL Foundry Lab agent failures and plan minimal rewrites.

8|5|Updated Apr 2, 2026
Search Tags:#failure-analysis#agent-improvement#opl-foundry#rewrite-planning#conformance-review#work-order-analysis#promotion-briefing
One-click install
npx skills add https://github.com/gaofeng21cn/one-person-lab --skill opl-foundry-agent-improver
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: opl-foundry-agent-improver
Source: https://github.com/gaofeng21cn/one-person-lab/tree/main/plugins/opl-foundation-skills/skills/opl-foundry-agent-improver
Command: npx skills add https://github.com/gaofeng21cn/one-person-lab --skill opl-foundry-agent-improver

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill eliminates the guesswork of diagnosing why OPL Foundry Lab agents fail to meet performance or conformance standards, saving teams hours of manual root cause analysis and risky broad rewrites.

Core Features & Use Cases

  • Failure Classification: Categorize agent failures into contract defects, skill prompt defects, or source boundary defects using Foundry Lab packet references.
  • Minimal Rewrite Planning: Propose targeted, small changes to fix agent behavior instead of broad, untested process overhauls.
  • Promotion & Rollback Briefings: Generate evidence-backed recommendations for promoting improved agents or rolling back faulty rewrites, with clear authority caveats. Use Case: If an OPL grant writing agent is consistently generating non-compliant grant section drafts, use this skill to analyze the failure from the work-order envelope and scorecard, then plan a minimal prompt rewrite to resolve the issue.

Quick Start

Use the opl-foundry-agent-improver skill to analyze the latest failed work-order for the OPL medical research agent and produce a rewrite plan.

Frequently Asked Questions about opl-foundry-agent-improver

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze OPL Foundry agent failures from work-order review packets?▼

Minimal rewrite planning for agent improvement proposes targeted, small changes to fix agent behavior instead of broad, untested process overhauls. This ensures evidence-backed modifications that respect authority boundaries and align with Foundry Lab harness standards.

How do I plan minimal rewrites for non-compliant OPL Foundry skills?▼

Minimal rewrite planning for agent improvement proposes targeted, small changes to fix agent behavior instead of broad, untested process overhauls. This ensures evidence-backed modifications that respect authority boundaries and align with Foundry Lab harness standards.

What is the best way to generate promotion or rollback briefings for OPL Foundry agents?▼

Generating promotion or rollback briefings for agent improvement candidates requires evidence-backed recommendations derived from conformance review and evaluation results. This skill produces clear authority caveats to help teams decide whether to promote improved agents or roll back faulty rewrites.

Can I use this skill to diagnose conformance issues in any OPL Foundry Lab agent?▼

Yes, you can diagnose conformance issues in OPL Foundry Lab agents by interpreting evaluation results and scorecard references. The skill applies to any agent within the OPL Foundry ecosystem that generates work-order failures or non-compliant outputs.

Why does my OPL Foundry agent produce non-conforming output despite correct prompt instructions?▼

Non-conforming output from OPL Foundry agents can stem from contract defects or source boundary defects rather than prompt issues. Analyzing the failure pattern from the Foundry Lab receipt reference categorizes the root cause to determine if a minimal rewrite is appropriate.

Related Skills

Explore More Software Engineering Skills→
gaofeng21cngaofeng21cn
8

opl-foundry-promotion-reviewer

Review OPL Foundry Lab promotion candidates against scorecards, work orders, and rollback evidence.

Community
Intermediate
gaofeng21cngaofeng21cn
8

opl-eval-harness-designer

Design structured evaluation harnesses for OPL Foundry Lab candidates.

Community
Intermediate
travisjneumantravisjneuman
88

fundraising-analyzer

Analyze nonprofit fundraising performance with donor segmentation and campaign ROI metrics.

Community
Intermediate
saboteur-labssaboteur-labs

debug-issue-minimal

Diagnose and fix bugs by identifying root causes and implementing minimal, verifiable changes.

Official
Intermediate