reprompter

Your prompt sucks. Let's fix that.

What's new (v13 — RePrompter v2): two intents (improve my prompt / build this whole thing), specifiability routing, One-Shot build prompts, team execution seeded from a build brief — digest

RePrompter is a prompt engineering skill for AI coding agents. It takes rough, low-quality prompts and transforms them into structured, high-scoring prompts that produce dramatically better results. Templates are aligned with 2026 vendor guidance: clear sectioning, calibrated emphasis, outcome-first instructions, load-bearing constraints, structured-output routing, context budgeting, and tool-description quality. Works with Claude Code, OpenClaw, Codex, Grok CLI, Hermes Agent, or any LLM that accepts structured prompts.

---

Two intents

You say	You get
"reprompt this: ..." — make my prompt better	Interview → the right shape for the job: a structured, scored spec prompt for bounded work, or an autonomous build prompt for whole-product asks (announced, overridable)
"one-shot this: ..." — build this whole thing	Plain-language interview (max 4 questions) → a prose build prompt that finishes in one session — or, on request, the same brief split across an agent team

Where the result goes. Improve outputs can be pasted (default), compressed to a /goal command (Codex, Claude Code, Hermes), compiled to a runnable Claude .workflow.js, or delivered to another model via headless-relay. Build runs as one prompt or splits across a team. Everything that used to be a separate "lane" is now one of these — a format the result takes or the way it executes.

Nothing was removed. Team execution (repromptverse, smart run, swarm triggers), the /goal and Workflow formats, cross-model relay delivery, and Reverse mode (extract the prompt DNA from a great output) all work exactly as before — see SKILL.md. v13 changed the map, not the machinery: every v12 trigger still routes to its intent. The one behavior change is honest and opt-out — a clearly whole-product "reprompt this" now offers an autonomous build prompt (say "spec" for the old structured, scored output); bounded and ambiguous asks stay spec-XML exactly as before.

---

Improve: a rough prompt becomes a good one

Input:  "uhh build a crypto dashboard, maybe coingecko data, add caching, test it too"
Score:  1.6/10

Output: Structured XML prompt with role, context, task, requirements,
        constraints, output format, and success criteria
Score:  9.0/10  (+462%)

<role>
Senior full-stack engineer specializing in real-time dashboard systems,
REST API integration, and cache-aware data pipelines.
</role>

<context>
- Frontend + backend + tests required (cross-layer scope)
- Data source: CoinGecko API (free tier, 30 calls/min rate limit)
- Existing API behavior must be preserved
</context>

<task>
Deliver a real-time crypto dashboard backed by a cache-aware CoinGecko proxy API,
with unit tests for both API and UI, without breaking existing API contracts.
</task>

<requirements>
- Build dashboard UI with loading, error, empty, and stale-data states
- Implement backend CoinGecko proxy with JSON schema validation + configurable cache TTL
- Preserve backward compatibility for all existing API consumers
- Add deterministic unit tests for frontend rendering states and backend edge cases
- Cache must serve stale data on upstream failure (stale-while-revalidate pattern)
</requirements>

<constraints>
- No direct client-side calls to CoinGecko (all traffic through proxy)
- No breaking changes to existing API response fields or status codes
- Mock all external network boundaries in tests
- Rate limit CoinGecko calls to stay within free tier (30/min)
</constraints>

<output_format>
- Backend: /api/prices endpoint returning { prices: [...], cached: bool, updatedAt: ISO }
- Frontend: React component with 5s auto-refresh interval
- Tests: Vitest suite with >=80% branch coverage
</output_format>

<success_criteria>
- Dashboard auto-updates every 5s and shows "stale" indicator when cache is old
- Proxy returns normalized data within 200ms (cache hit) / 2s (cache miss)
- Existing API integration tests still pass with zero modifications
</success_criteria>

Dimension	Before	After	Change
Clarity	3	9	+200%
Specificity	2	9	+350%
Structure	1	10	+900%
Constraints	0	8	new
Verifiability	1	9	+800%
Decomposition	2	9	+350%
Overall	1.6	9.0	+462%

Scores are self-assessed. Treat as directional indicators, not absolutes.

---

Build: a rough idea becomes a working thing

You say:  one-shot this: a first-person shooter like the recent Call of Duty games, in the browser

RePrompter asks a few plain questions, then emits one prose build prompt you paste into any coding agent. It names a real reference, staffs the work with a separate harsh critic that judges the running artifact (never the builder's summary), and ends on a checkable bar. The image below is one real frame from a single maximal-mode dogfood run — a browser FPS in a self-contained HTML file, textures/models/audio generated in code — captured by the run's own screenshot harness at 1600x900 with device pixel ratio 1 — the image is 1600x900, which is what a 1600x900 viewport produces only at pixel ratio 1. That is the condition behind the 269 FPS in the corner, and it is the whole point of this release: at the owner's real pixel ratio of 2 the same build did not hold that number. The run itself is not in this repository, so the frame and its stated conditions are what is auditable here; the rest is the maintainer's report. One run's result under stated conditions, not a guarantee for every run:

Two dogfood runs, same lane:

Mode	Prompt	Result
Default (one session)	Vampire-Survivors-style browser roguelite	a naive "build me X" prompt produced only scaffolding — a module contract, a build system, a test harness, no game; the One-Shot prompt produced a complete playable game (146 kills, level 7, ~70fps with 200+ enemies in an automated soak test driven by the build's own bot — viewport and pixel ratio were not recorded at the time, so by this release's own rule read that frame rate as unverified)
Maximal (opt-in)	the CoD-style FPS above	one run: 7 sub-agents in isolated repo copies judged each round against 10 real Call-of-Duty stills; ~11.8k lines / 34 modules. Rough edges remain (see below)

Lands at a strong working prototype — expect to keep iterating after it stops. It does not produce a shipped AAA title; the FPS above still has rough edges (muzzle-flash bloom, one stray additive box), and the honest close says so up front.

Credit where the shape came from: the one-prompt build pattern is @mattshumer_'s — a CoD-like browser FPS from 152 dictated words — reproduced and dissected by @ziwenxu_ as the "Gauntlet Loop" (name a real bar, separate builder from critic, loop on real output). RePrompter's One-Shot template is that shape made fillable, plus the checklist stop so a run ends on its own instead of at your rate limit.

---

Install

Claude Code

Recommended: install the Claude Code plugin. One install registers the RePrompter skill namespace and both Ambient Prompt Gate hooks; future updates use Claude Code's native plugin update flow.

/plugin marketplace add AytuncYildizli/reprompter
/plugin install reprompter@reprompter

If you previously installed ~/.claude/skills/reprompter, remove that personal copy before using the plugin. Personal skills shadow/duplicate plugin skills, so leaving it in place can make Claude Code load the old copy instead of /reprompter:reprompter.

The plugin ships the Ambient Prompt Gate enabled for Claude Code UserPromptSubmit and Stop. Use REPROMPTER_AMBIENT=0 as the per-feature off switch; Claude Code's disableAllHooks still disables all hooks, including plugin hooks.

Fallback for copy-based or non-plugin setups:

mkdir -p skills/reprompter
curl -sL https://github.com/aytuncyildizli/reprompter/archive/main.tar.gz | \
  tar xz --strip-components=1 -C skills/reprompter

Source archives are runtime-only (.gitattributes export-ignore): they contain SKILL.md, references/, and scripts/ but not dev/dist trees like skills/ (the Hermes-only install package — see Install paths), plugin/, .claude-plugin/, benchmarks/, assets/, or docs/. Plugin installs use git clone through Claude Code's marketplace flow, so export-ignoring the plugin tree does not affect plugin installs. Installed an older full copy? It's safe to delete those directories from it — upgrades won't bring them back.

For the /goal output format on Claude Code, pin the CLI to v2.1.139 or later. /goal depends on the hooks layer — if disableAllHooks or allowManagedHooksOnly is set in settings.json the command is unavailable on any version (v2.1.140 only made the failure visible). Managed environments that block hooks should stick to Single mode for goal-shaped work.

claude --version
# Expect 2.1.139 or later. Upgrade if older.

Staying current (version self-check)

Copy-based RePrompter installs can tell you when they are behind the latest release. Claude Code plugin installs stay silent here because native plugin update detection owns freshness. On the first invocation in a copy-based session, RePrompter runs a fail-soft check (scripts/version-check.js) that compares your local SKILL.md version against the latest GitHub release and prints a notice only if you're behind (silent when up to date). The result is cached ~24h (keyed by repo), so repeat runs add no latency; the first uncached check waits up to ~3s for GitHub, then fails soft and silent if it can't reach it (a failed lookup is cached ~1h so offline sessions don't repeat the timeout). Disable it entirely with REPROMPTER_VERSION_CHECK=0.

The notice's upgrade command is path-aware: it re-fetches into the exact directory this skill is installed in, so it works the same whether you run Claude Code (~/.claude/skills/reprompter), Codex (~/.codex/skills/reprompter), OpenClaw, Grok CLI, or a project-local skills/reprompter/. (Hermes installs ship no scripts/, so the check doesn't run there — use hermes skills install to update.)

Run it manually any time: