Skip to content

MantaDigital/stingray-agent-skills / skills/stingray

stingray

Verified

Trading strategy builder for coding agents. Use when Codex, Claude, Cursor, or a SKILL.md host needs to turn a trading idea into market Evidence, an inspectable Signal, a private Replay, Replay status, or an opt-in Studio Publication. Stingray does not place trades.

references/signal-definitions.md

View on GitHub
# Signal Definition Notes

Read this file when the user wants to understand what makes a good Stingray
Signal candidate.

## Signal Candidate Expectations

`signal.design` asks Stingray Studio to translate the Idea into a Signal
candidate. The candidate should make these assumptions visible when possible:

- market or venue;
- asset or market symbol;
- condition family, such as price move, threshold, technical indicator, funding,
  news, or composite condition;
- timeframe or lookback window;
- threshold and units;
- whether the condition is replayable today;
- whether the condition is supported and replayable today.

If a required assumption is missing, the correct response is `needs_input`, not
a guessed Signal.

## Replayable First Slice

The public examples should prefer Signal shapes that Stingray can replay today.
Reliable examples include generic BTC spot movement theses and Hyperliquid
funding-rate theses.

## Unsupported Hyperliquid Primitives

Hyperliquid open interest, whale movement, liquidation, and
mark-to-liquidation primitives are not supported in the public skill today. Do
not draft Signals for them as if they were available. Offer a supported
funding-rate example or a privacy-safe product feedback note.

## Acceptance

`artifact.accept` commits only a staged `signal_candidate` artifact in the first
public slice. It should be called after a candidate is returned and the user or
caller intent clearly includes acceptance. It does not update existing Signal
versions, accept Evidence, accept Monitor candidates, or enable live monitoring.

## Monitor Boundary

Signals can express live-monitoring intent, but monitor lifecycle mutation is
outside `skills:full` for now. If the user asks to enable, pause, resume, or
retire live monitoring, explain that this is outside the public skill's current
surface.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall