/refine
Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.
$ npx -y skills add automagik-dev/genie --skill refine --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/refine
Context preview
The summary Claude sees to decide when to auto-load this skill.
Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.
SKILL.md
refine.SKILL.mdname: refine
description: "Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode."
refine — Prompt Optimizer
**Runtime syntax:** in Codex, invoke the plugin copy with the owner-qualified `$genie:<skill>` selector; use bare `$<skill>` only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Claude Code and Hermes use `/<skill>`. Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active tier.
Transform any brief, draft, or one-liner into a production-ready structured prompt.
When to Use
- User wants to improve a prompt or brief
- User references `refine` with text or a file path
- A worker needs to optimize a prompt before dispatching it
Flow
1. **Detect mode:** argument starts with `@` → file mode; otherwise → text mode. 2. **Read input:** file mode reads the target file; text mode uses the raw argument. 3. **Load the optimizer prompt:** at dispatch time, Read `prompts/optimizer.md` (relative to this skill's directory — `skills/refine/prompts/optimizer.md`). Its full contents are the refiner's system prompt. 4. **Dispatch refiner subagent:** system prompt = the full text of `prompts/optimizer.md`; user message = the input. Single turn. 5. **Write output:** file mode overwrites the source file in place; text mode writes to `/tmp/prompts/<slug>.md`. 6. **Report:** lead with the path of the written file — that is the deliverable.
Modes
| | File mode | Text mode | |---|-----------|-----------| | Invocation | `refine @path/to/file.md` | `refine <text>` | | Input | file contents (strip `@` prefix) | the raw argument | | Output | overwrite the same file | `/tmp/prompts/<slug>.md` (`mkdir -p /tmp/prompts/` first) | | Report | the updated file path | the created file path |
Slug: `<unix-timestamp>-<word1>-<word2>-<word3>` — first 3 words, lowercased, hyphenated. Example: `1708190400-fix-auth-bug`.
Subagent Contract
The refiner is a single-turn subagent: input in, optimized prompt out.
- **System prompt:** the full contents of `prompts/optimizer.md` — passed whole, never summarized.
- **Input:** the raw text or file contents as the user message.
- **Output:** optimized prompt body only — no labels, meta-commentary, rationale, or follow-up questions.
- No tool calls. Receive input, produce output, terminate.
Rules
- Preserve the original intent — the simplest rewrite that satisfies the input, no added features or scope.
- Never execute the prompt — only rewrite it.
- Never enter a clarification loop — act on what you have, single turn.
- Never add wrapper text or status messages to the output file.
- File mode overwrites in place; text mode writes only to `/tmp/prompts/`.
Read more
name: refine description: "Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode."
refine — Prompt Optimizer
**Runtime syntax:** in Codex, invoke the plugin copy with the owner-qualified `$genie:<skill>` selector; use bare `$<skill>` only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Claude Code and Hermes use `/<skill>`. Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active tier.
Transform any brief, draft, or one-liner into a production-ready structured prompt.
When to Use
- User wants to improve a prompt or brief
- User references `refine` with text or a file path
- A worker needs to optimize a prompt before dispatching it
Flow
1. **Detect mode:** argument starts with `@` → file mode; otherwise → text mode. 2. **Read input:** file mode reads the target file; text mode uses the raw argument. 3. **Load the optimizer prompt:** at dispatch time, Read `prompts/optimizer.md` (relative to this skill's directory — `skills/refine/prompts/optimizer.md`). Its full contents are the refiner's system prompt. 4. **Dispatch refiner subagent:** system prompt = the full text of `prompts/optimizer.md`; user message = the input. Single turn. 5. **Write output:** file mode overwrites the source file in place; text mode writes to `/tmp/prompts/<slug>.md`. 6. **Report:** lead with the path of the written file — that is the deliverable.
Modes
| | File mode | Text mode | |---|-----------|-----------| | Invocation | `refine @path/to/file.md` | `refine <text>` | | Input | file contents (strip `@` prefix) | the raw argument | | Output | overwrite the same file | `/tmp/prompts/<slug>.md` (`mkdir -p /tmp/prompts/` first) | | Report | the updated file path | the created file path |
Slug: `<unix-timestamp>-<word1>-<word2>-<word3>` — first 3 words, lowercased, hyphenated. Example: `1708190400-fix-auth-bug`.
Subagent Contract
The refiner is a single-turn subagent: input in, optimized prompt out.
- **System prompt:** the full contents of `prompts/optimizer.md` — passed whole, never summarized.
- **Input:** the raw text or file contents as the user message.
- **Output:** optimized prompt body only — no labels, meta-commentary, rationale, or follow-up questions.
- No tool calls. Receive input, produce output, terminate.
Rules
- Preserve the original intent — the simplest rewrite that satisfies the input, no added features or scope.
- Never execute the prompt — only rewrite it.
- Never enter a clarification loop — act on what you have, single turn.
- Never add wrapper text or status messages to the output file.
- File mode overwrites in place; text mode writes only to `/tmp/prompts/`.
Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.
Repo: automagik-dev/genie
Other skills on genie.
- /architecture
Use when reviewing architecture in any codebase — module boundaries, stated design contracts, abstraction depth, error-handling design. Assess by default, apply changes on request; complexity is dependencies plus obscurity, and deep modules win.
Open skill - /brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
Open skill - /code-quality
Use when auditing code quality in any codebase — discover and run the repo's real gates (typecheck, lint, dead-code, complexity), judge type discipline and duplication. Assess by default, apply changes on request; the compiler is the first reviewer.
Open skill - /council
Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested.
Open skill - /docs
Dispatch docs subagent to audit, generate, and validate documentation against the codebase.
Open skill - /dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
Open skill

