Improve Agent

Run the guided, end-to-end loop that makes one Duvo Agent better. Use when the user wants to "improve this Agent", "make my Agent better", "help me tune this Agent", "this Agent isn't good enough", "fix this Agent based on its Runs", or asks you to take an Agent from where it is to a concrete, applied improvement — not just a read-only audit. You drive the conversation: pin the Agent, survey its whole setup (AOP, Connections, Skills, triggers, memory, recent Runs), agree on what to base the improvement on (the user's feedback or the evidence in the Runs), propose a Run range and confirm it, ge

9 stars 4 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add duvoai/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add duvoai/skills --skill improve-agent
Manual install
git clone --depth 1 https://github.com/duvoai/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/improve-agent ~/.claude/skills/improve-agent

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Improve an Agent

## What this skill is

This is the **guided improvement loop** for a single Agent: the conversational shell that takes the user from "this Agent could be better" to a change that is actually applied. You own the loop and the judgement calls — _which_ Agent, _what to base the improvement on_, _which Runs to look at_, _what to change_, _whether to apply it_. You do **not** re-derive the run analysis or the AOP rewrite yourself: the `workflow-debugger` skill already knows how to audit an Agent across many Runs and name evidence-backed inefficiencies, and `aop-writer` already knows how to rewrite an AOP. You orchestrate them.

So the value you add over running `workflow-debugger` directly is the loop around it: pinning the Agent, surveying its full setup, getting the user to choose the basis, proposing and confirming a Run range, and closing the loop by applying what they accept. Keep that shape; delegate the heavy lifting.

## Where this sits among the skills

- **`workflow-debugger`** — the read-only audit of an Agent across many Runs (status mix, eval scores, recurring complaints, the AOP the Runs ran). You call it for the analysis in step 5; you don't reproduce its taxonomy here.
- **`run-debugger`** — transcript-level diagnosis of one Run. Reach for it when a recurring failure needs depth on a representative Run.
Read the full skill on GitHub

Details

Skill name
improve-agent
Repository
duvoai/skills
Path
skills/improve-agent/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Improve Agent skill do?

Run the guided, end-to-end loop that makes one Duvo Agent better. Use when the user wants to "improve this Agent", "make my Agent better", "help me tune this Agent", "this Agent isn't good enough", "fix this Agent based on its Runs", or asks you to take an Agent from where it is to a concrete, applied improvement — not just a read-only audit. You drive the conversation: pin the Agent, survey its whole setup (AOP, Connections, Skills, triggers, memory, recent Runs), agree on what to base the improvement on (the user's feedback or the evidence in the Runs), propose a Run range and confirm it, ge

How do I install the Improve Agent skill?

Claude Code plugin: /plugin marketplace add duvoai/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Improve Agent popular?

It lives in duvoai/skills, which has 9 GitHub stars and 4 forks.

Related skills

Aop Writer

9

duvoai/skills

Draft, rewrite, or critique a Duvo Agent AOP. Use when the user wants to improve an existing AOP or write a new one from a brief. Returns the AOP as a single complete markdown document in the canonical GOAL / STEPS / NOTES shape.

Writing & Content

Clarity Mapping

9

duvoai/skills

Map how a process works with Duvo Clarity. Use when the user asks to map, document or understand how their team does a piece of work, to interview people about a process, or to analyze what those interviews found. Sets up a Duvo workspace if the user has none, creates the process, invites people to short voice interviews within the plan's allowance, tracks who has done theirs, and analyzes the process map.

Images, Video & Audio

Code Step Author

9

duvoai/skills

Answer questions about writing the Python program of a Duvo code step and the `duvo` SDK it calls. Use when the user asks how a code step reads its case, claims or settles work on a Queue, reaches a Connection, reads Policy values or attached files, what `duvo.execution` holds, which errors the SDK raises, or wants a snippet for a code step. Grounds every answer in the SDK surface that actually ships into the sandbox, and hands the writing of the program itself to the step's own AI generation rather than pasting code the user must transcribe.

Software Development

Logseq Outline

6

kerim/logseq-outline-skill

Format any content as a Logseq-compatible outline using nested bullets (no markdown headers, no bold). Works in both Claude Code and Claude Desktop.

AI, LLMs & Agents

End Game Thinking

5

shosmer/end-game-thinking-skill

Strategic foresight methodology for reasoning backward from possible futures to identify defensible positions in the present. Combines backward induction, inversion, premortem analysis, regret minimization, and scenario stress-testing into a structured exercise that produces a written artifact. MANDATORY TRIGGERS: end game thinking, endgame, what positions should I hold, how do I prepare for AI, future-proofing, strategic positioning, what happens when AI, stress test my strategy, what are my blindspots, competitive positioning for AI, scenario planning, backward induction, inversion exercise,

AI, LLMs & Agents

Scout

9

claudekit/skillmark

Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) and external (Gemini/OpenCode) agents.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.