Agent Setup Health Audit
tw93/Waza
Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side…
Install Empirical Prompt Tuning
$ npx skills add mizchi/skills --skill empirical-prompt-tuning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mizchi/skills empirical-prompt-tuning --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/mizchi/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/empirical-prompt-tuning .claude/skills/empirical-prompt-tuning && 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 "empirical-prompt-tuning" agent skill from https://github.com/mizchi/skills/tree/main/empirical-prompt-tuning into .claude/skills/empirical-prompt-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "empirical-prompt-tuning", 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/mizchi/skills/tree/main/empirical-prompt-tuningType 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 mizchi/skills --skill empirical-prompt-tuning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mizchi/skills empirical-prompt-tuning --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mizchi/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/empirical-prompt-tuning .agents/skills/empirical-prompt-tuning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "empirical-prompt-tuning" agent skill from https://github.com/mizchi/skills/tree/main/empirical-prompt-tuning into .agents/skills/empirical-prompt-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "empirical-prompt-tuning", 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 mizchi/skills --skill empirical-prompt-tuning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mizchi/skills empirical-prompt-tuning --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mizchi/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/empirical-prompt-tuning .cursor/skills/empirical-prompt-tuning && 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 "empirical-prompt-tuning" agent skill from https://github.com/mizchi/skills/tree/main/empirical-prompt-tuning into .cursor/skills/empirical-prompt-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "empirical-prompt-tuning", 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/mizchi/skills.git --path empirical-prompt-tuning--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 mizchi/skills --skill empirical-prompt-tuning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mizchi/skills empirical-prompt-tuning --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mizchi/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/empirical-prompt-tuning .gemini/skills/empirical-prompt-tuning && 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 "empirical-prompt-tuning" agent skill from https://github.com/mizchi/skills/tree/main/empirical-prompt-tuning into .gemini/skills/empirical-prompt-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "empirical-prompt-tuning", 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 mizchi/skills empirical-prompt-tuningInstalls 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 mizchi/skills --skill empirical-prompt-tuning -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mizchi/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/empirical-prompt-tuning .github/skills/empirical-prompt-tuning && 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 "empirical-prompt-tuning" agent skill from https://github.com/mizchi/skills/tree/main/empirical-prompt-tuning into .github/skills/empirical-prompt-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "empirical-prompt-tuning", 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 mizchi/skills --skill empirical-prompt-tuning -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mizchi/skills empirical-prompt-tuning --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mizchi/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/empirical-prompt-tuning .opencode/skills/empirical-prompt-tuning && 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 "empirical-prompt-tuning" agent skill from https://github.com/mizchi/skills/tree/main/empirical-prompt-tuning into .opencode/skills/empirical-prompt-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "empirical-prompt-tuning", 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
empirical-prompt-tuning- GitHub stars
- 360
- Token cost
- ~5k tokens
- SKILL.md length
- 2,315 words
- Files
- 3
- Skills in repo
- 69
- Repo updated
- First seen
- Licence
- None found
At a glance
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side…
- Works in 8 steps: Iteration 0 — description / body… → Baseline preparation: Fix the target… → Bias-free read: Have a "blank-slate"… → …
- Explicitly asks for an empirical eval of a prompt
- SKILL.md covers When to use, Workflow, Evaluation axes and Subagent invocation contract, plus 8 more sections
- Calls npx
What it does
Empirical Prompt Tuning is an agent skill from mizchi/skills. Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side metrics). Meta-skill, invoke ONLY when the user explicitly asks for an "empirical" eval of a prompt or skill, or for the Iter-0 description / body consistency check. Do NOT auto-invoke after every skill edit; this loop is operator-triggered by name.
Its SKILL.md is about 5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `README.md` and `SKILL-ja.md`).
It sits in Agent Workflows, covering Hooks and plugins and Agent instruction files. The repository describes itself as: Agent skills by mizchi, distributed via APM.
When your agent uses it
- Explicitly asks for an empirical eval of a prompt
- For the Iter-0 description / body consistency check
Example prompts
- “empirical”
- “/empirical-prompt-tuning”
Requirements
- Node.js
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Iteration 0 — description / body consistency check (static, no dispatch needed)
- Baseline preparation: Fix the target prompt and prepare the following two things.
- Bias-free read: Have a "blank-slate" executor read the instruction. Dispatch a new subagent via the Task tool. Do not substitute with a…
- Execution: Hand the subagent a prompt that follows the subagent invocation contract described below, and have it execute the scenario. The…
- Two-sided evaluation: Record the following from the returned results.
- Apply the diff: Put the minimum fix into the prompt to eliminate the unclear points. One theme per iteration (multiple related fixes are…
- Re-evaluate: Run 2 → 5 again with a new subagent (do not reuse the same agent: it has learned the previous improvements). Increase…
- Convergence check: The rough rule is "stop when 2 consecutive iterations have zero new unclear points AND metric improvements fall below…
What it can do on your machine
Read from SKILL.md and the folder at commit 62f5808. 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:
npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Empirical Prompt Tuning loads about 5k tokens when it runs. Until then it costs about 118 tokens; SKILL.md has 2,315 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
Without a licence we can't republish the file, so here is its outline and opening line. It has 2,315 words (~4,956 tokens).
“The author of a prompt cannot judge its quality. The clearer the writer thinks something is, the more likely another agent will stumble on it. The core of this skill is to have a bias-free executor actually run the instruction…”
- name
- empirical-prompt-tuning
Files
SKILL.md and 2 other files in empirical-prompt-tuning of mizchi/skills.
- SKILL.md
- README.md
- SKILL-ja.md
Open the folder on GitHubat commit 62f5808
Compare with similar skills
Empirical Prompt Tuning 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 |
|---|---|---|---|---|---|---|
| Empirical Prompt Tuning this skillmizchi/skills | 360 | — | ~5k | Automated safety check: Pass | None | |
| Agent Setup Health Audittw93/Waza | 7.2k | — | ~5.2k | Automated safety check: Notes | MIT | |
| Working With Claude Code Docsobra/superpowers-developing-for-claude-code | 142 | — | ~1.5k | Automated safety check: Pass | None | |
| Directional Promptingkingbootoshi/directional-prompting | 143 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Agenticashibing624/agentica | 352 | — | ~1.8k | Automated safety check: Notes | Apache-2.0 | |
| Claude Code Mastery Squadohmyjahh/xquads-squads | 277 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Working With Claude Code Docs
obra/superpowers-developing-for-claude-code
Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.
Directional Prompting
kingbootoshi/directional-prompting
Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition)…
Agentica
shibing624/agentica
How to answer questions about the agentica product you are running inside — CLI flags, config.yaml profiles, API keys, models, sessions, resume, workspace, AGENTS.md standing rules, skills, logs…
Claude Code Mastery Squad
ohmyjahh/xquads-squads
Routes a request to one of eight specialist agents covering hooks, skills, subagents, MCP integration and context engineering for Claude Code.
Vault Setup
earlyaidopters/second-brain
Interactive Obsidian vault configurator. An agent skill from earlyaidopters/second-brain.
More from mizchi/skills
All 69 skills in this repoPublish Agent Skill
mizchi/skills
Package, publish, verify and update an agent skill through a Claude Code plugin marketplace, APM or the npx skills CLI.
AI Index
mizchi/skills
Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English.
Cloudflare Deploy
mizchi/skills
Deploy applications and infrastructure to Cloudflare with the cf CLI and typed cloudflare.config.ts.
Review Image
mizchi/skills
Review screenshots or other images with OpenRouter vision models via bundled Deno scripts.
Sqlc Gen Moonbit Safety
mizchi/skills
Post-generation safety checks for sqlc-gen-moonbit + Cloudflare D1.
Apm Usage
mizchi/skills
Reference for APM (Agent Package Manager) — apm.yml syntax, install / uninstall / update commands, target detection, lockfile workflow.
Related
Categories
Questions about Empirical Prompt Tuning
What does Empirical Prompt Tuning do?
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side…. Empirical Prompt Tuning is an agent skill from mizchi/skills.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side metrics).
When should I use Empirical Prompt Tuning?
Empirical Prompt Tuning fits situations like: explicitly asks for an empirical eval of a prompt; for the Iter-0 description / body consistency check.
How do I install Empirical Prompt Tuning in Claude Code?
Run `npx skills add mizchi/skills --skill empirical-prompt-tuning -a claude-code`. Or copy the skill folder (empirical-prompt-tuning in mizchi/skills) into .claude/skills/empirical-prompt-tuning in your project. Claude Code loads it when a task matches its description.
How do I install Empirical Prompt Tuning in Codex?
Run `npx skills add mizchi/skills --skill empirical-prompt-tuning -a codex`. Or copy the skill folder (empirical-prompt-tuning in mizchi/skills) into .agents/skills/empirical-prompt-tuning in your project. Codex loads it when a task matches its description.
Can I use Empirical Prompt Tuning 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 mizchi/skills --skill empirical-prompt-tuning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/empirical-prompt-tuning, .gemini/skills/empirical-prompt-tuning, .github/skills/empirical-prompt-tuning and .opencode/skills/empirical-prompt-tuning in your project.
What does Empirical Prompt Tuning need to run?
Going by SKILL.md and its folder, Empirical Prompt Tuning needs the command-line tools its instructions call (npx). Our summary lists: Node.js.
Does Empirical Prompt Tuning access the network?
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Empirical Prompt Tuning 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 Empirical Prompt Tuning use?
No licence was found for Empirical Prompt Tuning or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Empirical Prompt Tuning use?
About 5k tokens (SKILL.md is roughly 20k 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 Empirical Prompt Tuning?
Skills that share tags, products or a category with Empirical Prompt Tuning: Agent Setup Health Audit (tw93/Waza, 7.2k stars), Working With Claude Code Docs (obra/superpowers-developing-for-claude-code, 142 stars), Directional Prompting (kingbootoshi/directional-prompting, 143 stars) and Agentica (shibing624/agentica, 352 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Empirical Prompt Tuning?
mizchi (a GitHub user) maintains it in mizchi/skills, which has 360 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on October 2, 2026.
Source: mizchi/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.