MantaDigital/stingray-agent-skills / skills/stingray
stingray
VerifiedTrading 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.
| File | Kind | Size |
|---|---|---|
| LICENSE.txt | markdown | 11.1 KB |
| README.md | markdown | 4.3 KB |
| SKILL.md | skill md | 10.8 KB |
| prompts.md | markdown | 3.6 KB |
| references/access-policy.md | markdown | 2.3 KB |
| references/agent-positioning.md | markdown | 2.5 KB |
| references/business-capabilities.md | markdown | 2.8 KB |
| references/capabilities.json | config | 5.8 KB |
| references/co-development.md | markdown | 1.8 KB |
| references/data-coverage.md | markdown | 1.3 KB |
| references/examples.md | markdown | 3.2 KB |
| references/intent-rubrics.md | markdown | 1.9 KB |
| references/north-star-scenarios.md | markdown | 2.4 KB |
| references/replays-and-publications.md | markdown | 3.3 KB |
| references/signal-definitions.md | markdown | 1.8 KB |
| references/token-lifecycle.md | markdown | 1.5 KB |
| references/troubleshooting.md | markdown | 1.6 KB |
| references/workflows.md | markdown | 2.3 KB |
references/agent-positioning.md
View on GitHub# Agent Positioning
Read this file when a user asks why Stingray belongs in a coding-agent workflow.
## One-Line Position
Stingray is a trading strategy builder for Codex, Claude Code, Cursor, and other
SKILL.md hosts. It turns a trading idea into a product-level research loop:
Idea -> Evidence -> Signal -> Replay -> optional Publication.
Start with the trading idea and the strategy being tested. Use Studio product
names when they help explain the next step. Stingray does not place trades.
## Why It Complements Generic Agents
Generic coding agents are good at planning, editing code, searching files, and
orchestrating local tools. They should not hand-roll market data ingestion,
market entity resolution, signal persistence, Replay processing, or publication
state. Stingray supplies those product objects through a small action API.
Use Stingray when the user wants:
- a raw market thesis turned into a Studio Idea;
- Evidence or coverage checks before committing a Signal;
- a staged Signal candidate that can be inspected before acceptance;
- a committed Signal that can be replayed against supported history;
- a lightweight way to recover status after long-running Replay work;
- a public Studio demo link only after explicit sharing intent.
## Do Not Position As
- a trading executor;
- a delegated wallet service;
- an order router;
- a generic market-data dump API;
- a raw CRUD API over account objects;
- a social-posting bot;
- a monitor lifecycle manager in the first public slice.
## User-Facing Language
Prefer:
- "Studio Idea"
- "Evidence"
- "Signal"
- "staged Signal candidate"
- "private Replay"
- "Studio Publication"
Avoid leading with:
- endpoint names;
- raw JSON;
- legacy implementation terms.
## Example Framing
Good:
```text
I will create a Studio Idea for this thesis, ask Stingray to stage a Signal,
accept the Signal only if it matches the intent, then run a private Replay.
```
Good:
```text
Stingray does not currently support that Hyperliquid primitive in the public
skill. I can offer a funding-rate example or write a product feedback note.
```
Bad:
```text
I will bypass the Studio Skills API and drive old implementation routes myself.
```
## Public Demo Loop
For XAgent or public-demo workflows, the public agent can use the same skill as
any other external agent. The special part is the authenticated user that owns
the demo Ideas and Publications, not a special API surface. Public demos should
use generic, non-private theses and publish only after explicit publish intent.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |