Inspect
agentevals-dev/agentevals
Inspect and debug live streaming agent sessions to understand what the agent did.
Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once…
Install Improve Prompt
$ npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AgentX-ai/AgentX-Trace-Eval improve-prompt --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AgentX-ai/AgentX-Trace-Eval.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/improve-prompt .claude/skills/improve-prompt && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "improve-prompt" agent skill from https://github.com/AgentX-ai/AgentX-Trace-Eval/tree/main/skills/improve-prompt into .claude/skills/improve-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-prompt", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AgentX-ai/AgentX-Trace-Eval/tree/main/skills/improve-promptType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AgentX-ai/AgentX-Trace-Eval improve-prompt --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgentX-ai/AgentX-Trace-Eval.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/improve-prompt .agents/skills/improve-prompt && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "improve-prompt" agent skill from https://github.com/AgentX-ai/AgentX-Trace-Eval/tree/main/skills/improve-prompt into .agents/skills/improve-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-prompt", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AgentX-ai/AgentX-Trace-Eval improve-prompt --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgentX-ai/AgentX-Trace-Eval.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/improve-prompt .cursor/skills/improve-prompt && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "improve-prompt" agent skill from https://github.com/AgentX-ai/AgentX-Trace-Eval/tree/main/skills/improve-prompt into .cursor/skills/improve-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-prompt", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AgentX-ai/AgentX-Trace-Eval.git --path skills/improve-prompt--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AgentX-ai/AgentX-Trace-Eval improve-prompt --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgentX-ai/AgentX-Trace-Eval.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/improve-prompt .gemini/skills/improve-prompt && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "improve-prompt" agent skill from https://github.com/AgentX-ai/AgentX-Trace-Eval/tree/main/skills/improve-prompt into .gemini/skills/improve-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-prompt", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AgentX-ai/AgentX-Trace-Eval improve-promptInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AgentX-ai/AgentX-Trace-Eval.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/improve-prompt .github/skills/improve-prompt && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "improve-prompt" agent skill from https://github.com/AgentX-ai/AgentX-Trace-Eval/tree/main/skills/improve-prompt into .github/skills/improve-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-prompt", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AgentX-ai/AgentX-Trace-Eval improve-prompt --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgentX-ai/AgentX-Trace-Eval.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/improve-prompt .opencode/skills/improve-prompt && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "improve-prompt" agent skill from https://github.com/AgentX-ai/AgentX-Trace-Eval/tree/main/skills/improve-prompt into .opencode/skills/improve-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "improve-prompt", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
improve-prompt- GitHub stars
- 106
- Token cost
- ~2k tokens
- SKILL.md length
- 998 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once…
- Works in 6 steps: Discover the engine → Resolve which prompt → Fetch real evidence - no judge call → …
- The user asks to improve
- SKILL.md covers 1. Discover the engine, 2. Resolve which prompt, 3. Fetch real evidence - no… and 4. Propose a rewrite yourself, plus 3 more sections
- Calls curl; needs API_KEY
What it does
Improve Prompt is an agent skill from AgentX-ai/AgentX-Trace-Eval. Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once the user explicitly approves. Use when the user asks to improve, tune, optimize, or "autotune" a prompt tracked in AgentX self-host.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Observability and LLM evaluation. It works with OpenTelemetry. The repository describes itself as: The trust layer for your AI agent on any platform. Trace and evaluate your agent. Full Observability. Run Model portability analysis. Autotune your agent.
When your agent uses it
- The user asks to improve
- Autotune a prompt tracked in AgentX self-host
Example prompts
- “autotune”
- “/improve-prompt”
Requirements
- A credential in API_KEY
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Discover the engine
- Resolve which prompt
- Fetch real evidence - no judge call
- Propose a rewrite yourself
- Wait for explicit approval
- Publish the new version
What it can do on your machine
Read from SKILL.md and the folder at commit 74660b7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Improve Prompt loads about 2k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 998 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 998 words (~2,035 tokens).
“AgentX self-host has no access to the agent you're improving - it only stores versioned prompt text your own code pulls at runtime (client.evaluations.prompts.get(name)) and the eval results you tag with that prompt's name. This skill is the Claude-Code-native way…”
- name
- improve-prompt
Files
Just SKILL.md in skills/improve-prompt of AgentX-ai/AgentX-Trace-Eval.
Open the folder on GitHubat commit 74660b7
Compare with similar skills
Improve Prompt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Improve Prompt this skillAgentX-ai/AgentX-Trace-Eval | 106 | — | ~2k | Automated safety check: Pass | Custom licence | |
| Inspectagentevals-dev/agentevals | 163 | — | ~534 | Automated safety check: Pass | Apache-2.0 | |
| Evalagentevals-dev/agentevals | 163 | — | ~904 | Automated safety check: Pass | Apache-2.0 | |
| Dt Obs GenaiDynatrace/dynatrace-for-ai | 163 | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Agent Kill Switchvivekchand/clawmetry | 426 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Sls Dashboard Builderalibaba/loongsuite-pilot | 201 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Eval
agentevals-dev/agentevals
Evaluate and score agent behavior against a golden reference.
Dt Obs Genai
Dynatrace/dynatrace-for-ai
Analyze & debug GenAI/LLM apps: token cost & caching by prompt, model & provider; latency/errors; agent & tool loops/failures; conversations; guardrails; evaluations; OpenTelemetry/dt-evals setup.
Agent Kill Switch
vivekchand/clawmetry
Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry.
Sls Dashboard Builder
alibaba/loongsuite-pilot
当任务需要创建、修改、扩展或重组阿里云 SLS 的 dashboard JSON 或可导入的大盘配置时使用；尤其适用于线上大盘、强对比的分析看板、已校验的查询包，或需要专业中文标签与指标定义的运维向大盘。
Clawmetry Selfcheck
vivekchand/clawmetry
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task.
Related
Works with
Categories
Questions about Improve Prompt
What does Improve Prompt do?
Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once…. Improve Prompt is an agent skill from AgentX-ai/AgentX-Trace-Eval. Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once the user explicitly approves.
When should I use Improve Prompt?
Improve Prompt fits situations like: the user asks to improve; autotune a prompt tracked in AgentX self-host.
How do I install Improve Prompt in Claude Code?
Run `npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a claude-code`. Or copy the skill folder (skills/improve-prompt in AgentX-ai/AgentX-Trace-Eval) into .claude/skills/improve-prompt in your project. Claude Code loads it when a task matches its description.
How do I install Improve Prompt in Codex?
Run `npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a codex`. Or copy the skill folder (skills/improve-prompt in AgentX-ai/AgentX-Trace-Eval) into .agents/skills/improve-prompt in your project. Codex loads it when a task matches its description.
Can I use Improve Prompt in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AgentX-ai/AgentX-Trace-Eval --skill improve-prompt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/improve-prompt, .gemini/skills/improve-prompt, .github/skills/improve-prompt and .opencode/skills/improve-prompt in your project.
What does Improve Prompt need to run?
Going by SKILL.md and its folder, Improve Prompt needs the command-line tools its instructions call (curl) and credentials named API_KEY. Our summary lists: A credential in API_KEY.
Does Improve Prompt access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Improve Prompt safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Improve Prompt use?
Improve Prompt has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Improve Prompt use?
About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Improve Prompt?
Skills that share tags, products or a category with Improve Prompt: Inspect (agentevals-dev/agentevals, 163 stars), Eval (agentevals-dev/agentevals, 163 stars), Dt Obs Genai (Dynatrace/dynatrace-for-ai, 163 stars) and Agent Kill Switch (vivekchand/clawmetry, 426 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Improve Prompt?
AgentX-ai (a GitHub organization) maintains it in AgentX-ai/AgentX-Trace-Eval, which has 106 GitHub stars. The repository was last updated on October 7, 2026.
Source: AgentX-ai/AgentX-Trace-Eval on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.