Empirical Prompt Tuning

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.

423 stars 6 forksAI, LLMs & Agents

Install

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

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

From the SKILL.md

# Empirical Prompt Tuning

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, evaluate it two-sidedly, and iterate**. Do not stop until improvements plateau.

## When to use

- Right after creating or substantially revising a skill / slash command / task prompt
- When an agent does not behave as expected and you want to attribute the cause to ambiguity on the instruction side
- When hardening high-importance instructions (frequently used skills, automation-core prompts)

When not to use:
- One-off throwaway prompts (evaluation cost does not pay off)
- When the goal is not to improve success rate but merely to reflect the writer's subjective preferences

## Workflow

0. **Iteration 0 — description / body consistency check** (static, no dispatch needed)
   - Read the triggers / use cases claimed by the frontmatter `description`
   - Read the scope the body actually covers
   - If there is a gap, reconcile description or body before moving to iter 1
   - Example: description says "navigation / form filling / data extraction" but the body is only a CLI reference for `npx playwright test` — detect that kind of gap
Read the full skill on GitHub

Details

Skill name
empirical-prompt-tuning
Repository
mizchi/skills
Path
empirical-prompt-tuning/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Empirical Prompt Tuning skill 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 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.

How do I install the Empirical Prompt Tuning skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizchi/skills --skill empirical-prompt-tuning. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Empirical Prompt Tuning popular?

It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.

Related skills

Actions CI Tuning

423

mizchi/skills

Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.

Testing & QA

AI Index

423

mizchi/skills

Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.

AI, LLMs & Agents

Apm Usage

423

mizchi/skills

Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.

DevOps & Cloud

Formal Methods Drift Guard

423

mizchi/skills

Use after a formal model or verifier check already exists and the user wants to maintain it over time. Helps Codex compare specs/docs, implementation code/tests/config/logs, and formal models or CI checks for drift; classify whether the drift is in the spec, code, model abstraction, harness, or unresolved domain decision; run or plan verifier checks; and translate SAT/UNSAT changes, counterexample traces, proof failures, stale models, and CI results into domain-language review questions and ledger entries.

AI, LLMs & Agents

Creating Internal Agents

237

medusajs/medusa-agent-skills

Use when building an internal admin-facing AI agent in a Medusa project. These agents are operated by merchants and store operators — not customers. Covers data models, module service, agent runtime (tools, system prompt, streamText), streaming API routes (NDJSON), and admin UI chat extensions. Load for any internal agent type: store operations assistant, product audit, cohort analysis, customer service tooling for support staff, etc. Do NOT use for customer-facing agents (storefront chatbots, buyer-side assistants).

AI, LLMs & Agents29

Multi Agent Orchestration

423

mizchi/skills

Use when deciding whether to spawn subagents, choosing sequential vs fan-out vs supervisor vs debate vs dynamic DAG, designing a coding-agent workflow with write-scope isolation, or when extra agents may waste tokens without independent evidence. Trigger on multi-agent, orchestration, fan-out, worktree, blackboard, verifier, AgentTask, or "should I parallelize this".

AI, LLMs & Agents

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