Prompt Optimizer

What it does

When your agent uses it

• Tasks that involve Prompt engineering
• Tasks that involve A/B testing

Example prompts

• “/prompt-optimizer”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Add Specificity — Vague prompts ("write well") → Specific ("write in present tense, under 3000 words, with a cliffhanger ending")
2. 2Add Examples — Show the AI what "good" looks like for this task
3. 3Add Constraints — Boundaries improve output ("exactly 3 paragraphs", "no adverbs", "start with dialogue")
4. 4Role Framing — "You are a [expert role]" can dramatically change quality
5. 5Chain of Thought — For complex tasks, add "First analyze X, then plan Y, then write Z"
6. 6Negative Examples — "Do NOT do X" can be as powerful as "Do Y"
7. 7Output Format — Specifying exact output format reduces parsing errors

What it can do on your machine

Read from SKILL.md and the folder at commit 47e9570. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  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

Prompt Optimizer loads about 1.5k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 505 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~28

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

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

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

The full file from Ckokoski/AuthorAgent at commit 47e9570, republished under its MIT licence (© Ckokoski). 505 words, ~1,462 tokens.

name

prompt-optimizer

description

Automatically improves prompts based on output quality, user feedback, and A/B testing results

author

AuthorAgent

version

1.0.0

triggers

optimize prompt, improve prompt, better prompt, prompt quality, test prompts, prompt a/b test, prompt lab

permissions

file:read, file:write

{
  "promptId": "p-347",
  "timestamp": "2026-02-24T15:00:00Z",
  "template": "Write a compelling book blurb for: {{description}}...",
  "skill": "blurb-writer",
  "taskType": "marketing",
  "provider": "gemini",
  "inputTokens": 450,
  "outputTokens": 890,
  "outcome": "accepted",
  "userEdited": false,
  "qualitySignals": {
    "wordCount": 147,
    "completeness": true,
    "followedInstructions": true,
    "userAccepted": true
  }
}

Prompt Lab: "blurb-writer" skill
════════════════════════════════

Original (Score: 6.2/10 across 14 uses):
"Write a compelling book blurb for: {{description}}.
Create 3 versions: (1) short tagline, (2) back-cover
blurb (150 words), (3) Amazon description with HTML."

Variation A (Score: 7.8/10 across 6 uses):
"You are a bestselling book marketer. Write a blurb
for: {{description}}.
Rules: Hook in first sentence. No spoilers past Act 1.
End with a question or cliffhanger.
Format: tagline (10 words max), back cover (150 words),
Amazon listing (with <b> tags for emphasis)."

Variation B (Score: 8.1/10 across 4 uses):
"Study these bestselling blurbs for pacing and hooks:
[example 1], [example 2].
Now write a blurb for: {{description}} using the same
techniques. Output: tagline, 150-word back cover,
Amazon description."

→ RECOMMENDATION: Promote Variation B to primary.

workspace/memory/prompts/
├── prompt-log.jsonl          # All prompt executions and outcomes
├── prompt-variants.json      # Active A/B test variants
├── prompt-winners.json       # Promoted prompt improvements
└── prompt-archive.jsonl      # Retired prompt versions

optimize prompt for blurb-writer

test prompt: "Write a blurb for {{description}} using the hook-mystery-stakes formula"

prompt stats

update prompt for [skill]: [new prompt text]

© Ckokoski, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/core/prompt-optimizer of Ckokoski/AuthorAgent.

Open the folder on GitHubat commit 47e9570